Review your GitHub Actions workflows from your own tools
Send a GitHub Actions workflow — on its own, or together with its companion workflows and composite actions —
and get back one JSON object: a production-readiness
posture, the inventory of every file and function with its
role, prioritized findings across correctness, security, robustness, cost,
performance, maintainability and hygiene, each with a corrected YAML fragment, quick wins, and
the focus areas to work through first. Everything this app does goes through the SkillSafe
App API — plain JSON over HTTPS — so you can hang a review off a pull request
that touches *.sh, a scheduled sweep of your cron scripts, or a pre-merge gate in
the pipeline that owns your automation. Every code step below is shown in cURL, Python,
JavaScript, Go, Java, Ruby, PHP and C#; pick a language once and the whole page follows.
Basics
Base URL: https://api.skillsafe.ai/v1/app-api, app slug
actions-clinic. Every request sends
Authorization: Bearer <token> and JSON bodies with
Content-Type: application/json. Responses are wrapped in an envelope:
{"data": …} on success, {"error": {"code", "message"}} on failure.
The review itself is produced by the gpt-terra model. Estimates are free;
runs are metered against your credit balance. There is a single run task — one set of
build files in, one review out, no follow-up calls and no session state to carry.
| Status | Meaning |
|---|---|
401 | Missing or expired token — create a new session. |
402 | Not enough credits — top up at skillsafe.ai/account/credits. |
403 | The token isn't allowed to do this (e.g. a guest reviewing a very large set of files). |
404 | Unknown job or record id. |
5xx | Transient platform error — retry with backoff. |
Browsers enforce CORS for this API, so run these examples from a server, script or terminal — not from another website's frontend.
Step 0 — A tiny client
Every task below is a single HTTP call, so start with a short helper that adds the auth
header, sends JSON and unwraps the data envelope. The later steps reuse it.
export API="https://api.skillsafe.ai/v1/app-api"
export TOKEN="YOUR_TOKEN" # see step 1
# every call looks like:
# curl -s "$API/..." -H "Authorization: Bearer $TOKEN" [-d '{json}']
# jq is used below to pull fields out of the {"data": ...} envelope
import json, requests
API = "https://api.skillsafe.ai/v1/app-api"
TOKEN = "YOUR_TOKEN" # see step 1 — read it from your shell environment in real code
def api(method, path, body=None, **headers):
res = requests.request(method, API + path, json=body,
headers={"Authorization": f"Bearer {TOKEN}", **headers})
payload = res.json()
if not res.ok:
raise RuntimeError(payload.get("error", {}).get("message", res.reason))
return payload["data"]
// Node 18+ (built-in fetch)
const API = "https://api.skillsafe.ai/v1/app-api";
const TOKEN = "YOUR_TOKEN"; // see step 1 — read it from your shell environment in real code
async function api(method, path, body, extraHeaders = {}) {
const res = await fetch(API + path, {
method,
headers: { Authorization: `Bearer ${TOKEN}`, "Content-Type": "application/json", ...extraHeaders },
body: body === undefined ? undefined : JSON.stringify(body),
});
const json = await res.json();
if (!res.ok) throw new Error(json.error?.message ?? res.statusText);
return json.data;
}
package main
import (
"bytes"
"encoding/json"
"fmt"
"net/http"
"os"
)
const API = "https://api.skillsafe.ai/v1/app-api"
var token = os.Getenv("SKILLSAFE_TOKEN") // see step 1
func call(method, path string, body, out any) error {
var buf bytes.Buffer
if body != nil {
json.NewEncoder(&buf).Encode(body)
}
req, _ := http.NewRequest(method, API+path, &buf)
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("Content-Type", "application/json")
res, err := http.DefaultClient.Do(req)
if err != nil {
return err
}
defer res.Body.Close()
var env struct {
Data json.RawMessage `json:"data"`
Error *struct{ Message string `json:"message"` } `json:"error"`
}
json.NewDecoder(res.Body).Decode(&env)
if res.StatusCode >= 400 {
return fmt.Errorf("api %s %s: %s", method, path, env.Error.Message)
}
if out == nil {
return nil
}
return json.Unmarshal(env.Data, out)
}
// Java 17+, no dependencies. Pair with your JSON library (Jackson, Gson…)
// to read fields out of the returned envelope.
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
public class SkillSafe {
static final String API = "https://api.skillsafe.ai/v1/app-api";
static final String TOKEN = System.getenv("SKILLSAFE_TOKEN"); // see step 1
static final HttpClient HTTP = HttpClient.newHttpClient();
static String api(String method, String path, String jsonBody) throws Exception {
var req = HttpRequest.newBuilder(URI.create(API + path))
.header("Authorization", "Bearer " + TOKEN)
.header("Content-Type", "application/json")
.method(method, jsonBody == null
? HttpRequest.BodyPublishers.noBody()
: HttpRequest.BodyPublishers.ofString(jsonBody))
.build();
var res = HTTP.send(req, HttpResponse.BodyHandlers.ofString());
if (res.statusCode() >= 400) throw new RuntimeException(res.body());
return res.body(); // envelope: {"data": …}
}
}
require "net/http"
require "json"
API = "https://api.skillsafe.ai/v1/app-api"
TOKEN = ENV.fetch("SKILLSAFE_TOKEN") # see step 1
def api(method, path, body = nil)
uri = URI(API + path)
req = Net::HTTP.const_get(method.capitalize).new(uri)
req["Authorization"] = "Bearer #{TOKEN}"
req["Content-Type"] = "application/json"
req.body = body.to_json if body
res = Net::HTTP.start(uri.host, uri.port, use_ssl: true) { |h| h.request(req) }
payload = JSON.parse(res.body)
raise (payload.dig("error", "message") || res.message) unless res.is_a?(Net::HTTPSuccess)
payload["data"]
end
<?php
const API = "https://api.skillsafe.ai/v1/app-api";
$TOKEN = getenv("SKILLSAFE_TOKEN"); // see step 1
function api(string $method, string $path, ?array $body = null): mixed {
global $TOKEN;
$ch = curl_init(API . $path);
curl_setopt_array($ch, [
CURLOPT_CUSTOMREQUEST => $method,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_HTTPHEADER => [
"Authorization: Bearer $TOKEN",
"Content-Type: application/json",
],
CURLOPT_POSTFIELDS => $body === null ? null : json_encode($body),
]);
$payload = json_decode(curl_exec($ch), true);
$status = curl_getinfo($ch, CURLINFO_RESPONSE_CODE);
curl_close($ch);
if ($status >= 400) {
throw new Exception($payload["error"]["message"] ?? "HTTP $status");
}
return $payload["data"];
}
// .NET 8+
using System.Net.Http.Json;
using System.Text.Json;
static class SkillSafe
{
const string Api = "https://api.skillsafe.ai/v1/app-api";
static readonly HttpClient Http = new();
static SkillSafe() =>
Http.DefaultRequestHeaders.Authorization =
new("Bearer", Environment.GetEnvironmentVariable("SKILLSAFE_TOKEN")); // see step 1
public static async Task<JsonElement> ApiAsync(HttpMethod method, string path, object? body = null)
{
var req = new HttpRequestMessage(method, Api + path);
if (body != null) req.Content = JsonContent.Create(body);
var res = await Http.SendAsync(req);
var json = await res.Content.ReadFromJsonAsync<JsonElement>();
if (!res.IsSuccessStatusCode)
throw new Exception(json.GetProperty("error").GetProperty("message").GetString());
return json.GetProperty("data");
}
}
Step 1 — Get a token
A guest token lets you check balances and estimate costs for free. For metered review runs
billed to your own account, use your personal token: open the
token page, sign in with SkillSafe, and press
Copy shell export — it puts export SKILLSAFE_TOKEN="…" on your
clipboard, which every example below reads. Treat the token like a password: it can spend
your credits. For fully headless scripts, POST /guest mints a guest token with
no browser involved.
curl -s -X POST "$API/guest" \
-H "Content-Type: application/json" \
-d '{"slug":"actions-clinic"}' | jq -r '.data.token'
token = api("POST", "/guest", {"slug": "actions-clinic"})["token"]
const { token } = await api("POST", "/guest", { slug: "actions-clinic" });
var guest struct{ Token string `json:"token"` }
err := call("POST", "/guest", map[string]string{"slug": "actions-clinic"}, &guest)
String envelope = api("POST", "/guest", """
{"slug":"actions-clinic"}""");
// token is at data.token in the returned JSON
token = api("POST", "/guest", { slug: "actions-clinic" })["token"]
$token = api("POST", "/guest", ["slug" => "actions-clinic"])["token"];
var guest = await SkillSafe.ApiAsync(HttpMethod.Post, "/guest",
new { slug = "actions-clinic" });
var token = guest.GetProperty("token").GetString();
The app stores this browser's token under the localStorage key
skillsafe_app_token:actions-clinic, on the app's own origin. The
token page reads and manages it for you — you never need
to open developer tools.
Step 2 — Check who you are and your balance
Returns subject_type ("user" or "guest"),
subject_id and your credits balance. Check this before reviewing a
large set of files.
curl -s "$API/me" -H "Authorization: Bearer $TOKEN" | jq '.data'
me = api("GET", "/me")
print(me["subject_type"], me["credits"])
const me = await api("GET", "/me");
console.log(me.subject_type, me.credits);
var me struct {
SubjectType string `json:"subject_type"`
Credits int64 `json:"credits"`
}
err := call("GET", "/me", nil, &me)
String envelope = api("GET", "/me", null);
// data.subject_type, data.credits
me = api("GET", "/me")
puts "#{me["subject_type"]}: #{me["credits"]} credits"
$me = api("GET", "/me");
echo "{$me['subject_type']}: {$me['credits']} credits\n";
var me = await SkillSafe.ApiAsync(HttpMethod.Get, "/me");
Console.WriteLine($"{me.GetProperty("subject_type")}: {me.GetProperty("credits")} credits");
Step 3 — Estimate the cost
Send exactly the input you would send to /run; the response's
hold_credits is the worst-case cost. Nothing is charged and no job is created,
so estimating is free — useful when you are piping a long workflow plus its companion
files in and want a ceiling before spending credits.
| Input field | Type | Notes |
|---|---|---|
workflow_text | string, required | The workflow YAML, exactly as it runs. A bare workflow, or several files each introduced by a header line of the form # === file: .github/workflows/deploy.yml ===. This is the model's only evidence — nothing is executed and no repository is inspected. Input longer than 80,000 characters is clipped middle-out, with a # [... clipped ...] comment showing where. At least 30 characters are needed for a review. |
target | string | deploy | ci | release | scheduled | unknown — changes what counts as a finding: a deploy pipeline is judged hardest on permissions, environments and concurrency, a CI workflow on speed, caching and PR-injection safety, a release workflow on provenance and pinning, a scheduled one on idempotency and failure alerting. |
concern | string | general | security | correctness | cost | maintainability — the review emphasis. It weights the findings and the summary, but it is emphasis and not exclusivity: a high-severity finding from another category is never suppressed. |
context | string, optional | Extra context: what the pipeline builds or deploys, whether the repository is public and accepts fork PRs, what secrets it holds, what protections exist outside this file, and any gap you have already chosen to accept. Clipped at 20,000 characters. |
prescan_facts | object, optional | What a client-side scanner mechanically matched in the text: {"files": [], "flags": []}. Each entry is {id, label}. File ids look like file:deploy.yml for a file and job:deploy.yml:build for a job; flag ids are <check>:<where> — unpinned:deploy.yml:14, old-action:deploy.yml:9, no-permissions:deploy.yml, write-all:deploy.yml:6, injection:deploy.yml:22, prt-checkout:deploy.yml:12, secret-echo:deploy.yml:30, no-timeout:deploy.yml:build, no-concurrency:deploy.yml, deprecated-cmd:deploy.yml:25, job-continue-on-error:deploy.yml:build, cache-missing:deploy.yml:10, self-hosted:deploy.yml:8. Every flag id you send comes back in coverage_check. The web UI fills this from its own scan; API callers may omit the field or send the two empty arrays. |
retry_note | string, optional | Only set by the app's automatic reformat retry when a first reply was not valid JSON. Leave it out. |
cat > deploy.yml <<'WORKFLOW'
name: deploy
on:
push:
branches: [main]
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@main
- run: ./deploy.sh production
WORKFLOW
# to review several files at once, concatenate them with header lines:
# { echo "# === file: deploy.yml ==="; cat deploy.yml;
# echo "# === file: ci.yml ==="; cat ci.yml; } > bundle.txt
jq -n --rawfile wf deploy.yml \
'{workflow_text: $wf,
target: "deploy",
concern: "general",
context: "Deploys the marketing site to a single VM on every push to main.",
prescan_facts: {files: [], flags: []}}' > input.json
curl -s -X POST "$API/estimate" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-d @input.json | jq '.data.hold_credits'
WORKFLOW_TEXT = """name: deploy
on:
push:
branches: [main]
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@main
- run: ./deploy.sh production
"""
payload = {
"workflow_text": WORKFLOW_TEXT,
"target": "deploy",
"concern": "general",
"context": "Deploys the marketing site to a single VM on every push to main.",
"prescan_facts": {"files": [], "flags": []},
}
est = api("POST", "/estimate", payload)
print("worst case:", est.get("hold_credits", est.get("credits")), "credits")
const workflowText = [
"name: deploy",
"on:",
" push:",
" branches: [main]",
"jobs:",
" deploy:",
" runs-on: ubuntu-latest",
" steps:",
" - uses: actions/checkout@main",
" - run: ./deploy.sh production"
].join("\n");
const payload = {
workflow_text: workflowText,
target: "deploy",
concern: "general",
context: "Deploys the marketing site to a single VM on every push to main.",
prescan_facts: { files: [], flags: [] },
};
const est = await api("POST", "/estimate", payload);
console.log("worst case:", est.hold_credits ?? est.credits, "credits");
const workflowText = "name: deploy\n" +
"on:\n" +
" push:\n" +
" branches: [main]\n" +
"jobs:\n" +
" deploy:\n" +
" runs-on: ubuntu-latest\n" +
" steps:\n" +
" - uses: actions/checkout@main\n" +
" - run: ./deploy.sh production\n"
payload := map[string]any{
"workflow_text": workflowText,
"target": "deploy",
"concern": "general",
"context": "Deploys the marketing site to a single VM on every push to main.",
"prescan_facts": map[string]any{
"files": []any{}, "flags": []any{},
},
}
var est struct{ HoldCredits int64 `json:"hold_credits"` }
err := call("POST", "/estimate", payload, &est)
String workflowText = """
name: deploy
on:
push:
branches: [main]
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@main
- run: ./deploy.sh production
""";
String jsonPayload = """
{"workflow_text": %s,
"target": "deploy",
"concern": "general",
"context": "Deploys the marketing site to a single VM on every push to main.",
"prescan_facts": {"files": [], "flags": []}}
""".formatted(toJsonString(workflowText));
String envelope = api("POST", "/estimate", jsonPayload);
// worst-case cost is at data.hold_credits
WORKFLOW_TEXT = <<~WORKFLOW
name: deploy
on:
push:
branches: [main]
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@main
- run: ./deploy.sh production
WORKFLOW
payload = { workflow_text: WORKFLOW_TEXT,
target: "deploy",
concern: "general",
context: "Deploys the marketing site to a single VM on every push to main.",
prescan_facts: { files: [], flags: [] } }
est = api("POST", "/estimate", payload)
puts "worst case: #{est["hold_credits"] || est["credits"]} credits"
$workflowText = <<<'WORKFLOW'
name: deploy
on:
push:
branches: [main]
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@main
- run: ./deploy.sh production
WORKFLOW;
$payload = [
"workflow_text" => $workflowText,
"target" => "deploy",
"concern" => "general",
"context" => "Deploys the marketing site to a single VM on every push to main.",
"prescan_facts" => ["files" => [], "flags" => []],
];
$est = api("POST", "/estimate", $payload);
echo "worst case: " . ($est["hold_credits"] ?? $est["credits"]) . " credits\n";
var workflowText = """
name: deploy
on:
push:
branches: [main]
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@main
- run: ./deploy.sh production
""";
var payload = new {
workflow_text = workflowText,
target = "deploy",
concern = "general",
context = "Deploys the marketing site to a single VM on every push to main.",
prescan_facts = new {
files = Array.Empty<object>(), flags = Array.Empty<object>(),
},
};
var est = await SkillSafe.ApiAsync(HttpMethod.Post, "/estimate", payload);
Console.WriteLine($"worst case: {est.GetProperty("hold_credits")} credits");
prescan_facts.flags is how you make the review answer for things you already
know about. Send {"files": [{"id": "file:deploy.yml", "label": "deploy.yml - 24 lines"}],
"flags": [{"id": "no-permissions:deploy.yml", "label": "deploy.yml never declares a permissions block"}]} and
every flag id comes back in coverage_check — addressed by a finding, or set
aside with the reason. Nothing you flag is silently dropped, which makes it the field to assert
on in a CI check.
Step 4 — Run the review and wait for the result
/run takes the same input as /estimate, places a credit hold and
returns a job_id. Poll /jobs/{job_id} every 1–2 seconds
until status is succeeded or failed (a run typically
takes 30–90 s, since every finding carries a corrected YAML fragment). Always send
an Idempotency-Key header so a network retry can't start a second,
double-charged run. The review is in output — usually nested as
output.output, and as a JSON string, so parse defensively. The samples
below print the posture, the inventory, the prioritized findings and the focus areas, then
save the whole object to review.json.
JOB_ID=$(curl -s -X POST "$API/run" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-H "Idempotency-Key: sc-$(date +%s)" \
-d @input.json | jq -r '.data.job_id')
while :; do
JOB=$(curl -s "$API/jobs/$JOB_ID" -H "Authorization: Bearer $TOKEN")
STATUS=$(echo "$JOB" | jq -r '.data.status')
[ "$STATUS" = "succeeded" ] || [ "$STATUS" = "failed" ] && break
sleep 2
done
# unwrap the review once, then read it
echo "$JOB" | jq -r '.data.output.output' > review.json
jq -r '
"\(.review_name) [\(.posture)]: \(.verdict)",
"",
"INVENTORY",
(.inventory[] | " \(.file) \(.unit) [\(.runner)] - \(.role)"),
"",
"FINDINGS",
(.findings[] | " [\(.priority)] \(.id) \(.category) \(.location): \(.problem)"),
"",
"QUICK WINS",
(.quick_wins[] | " - \(.)"),
"",
"FOCUS AREAS",
(.focus_areas[] | " \(.area) - \(.why)"),
"",
"COVERAGE",
(.coverage_check[] | " \(.id): \(if .addressed then "ok" else "SET ASIDE" end) - \(.note)")' \
review.json
# fail the pipeline on anything critical
jq -e '[.findings[] | select(.priority == "critical")] | length == 0' review.json > /dev/null \
|| { echo "critical findings present"; exit 1; }
import time
job_id = api("POST", "/run", payload,
**{"Idempotency-Key": "sc-001"})["job_id"]
while True:
job = api("GET", f"/jobs/{job_id}")
if job["status"] in ("succeeded", "failed"):
break
time.sleep(1.5)
if job["status"] == "failed":
raise RuntimeError(job.get("error", "run failed"))
raw = job["output"]
if isinstance(raw, dict) and "output" in raw:
raw = raw["output"]
review = json.loads(raw) if isinstance(raw, str) else raw
print(f'{review["review_name"]} [{review["posture"]}]: {review["verdict"]}')
for r in review["inventory"]:
print(f' {r["file"]:<18} {r["unit"]:<22} {r["runner"]:<24} {r["role"]}')
for f in review["findings"]:
print(f' [{f["priority"]:>8}] {f["id"]} {f["category"]} {f["location"]}')
print(f' L:{f["likelihood"]}/S:{f["severity"]} {f["problem"]}')
print(f' fix: {f["fix"]}')
if f["snippet"]:
print(" snippet:", f["snippet"].splitlines()[0], "...")
for w in review["quick_wins"]:
print(" win:", w)
for a in review["focus_areas"]:
print(f' focus {a["area"]} {a["finding_ids"]} - {a["why"]}')
for c in review["coverage_check"]:
print(f' {c["id"]}: {"ok" if c["addressed"] else "SET ASIDE"} - {c["note"]}')
with open("review.json", "w", encoding="utf-8") as fh:
json.dump(review, fh, indent=2)
critical = [f for f in review["findings"] if f["priority"] == "critical"]
if critical:
raise SystemExit(f"{len(critical)} critical finding(s)")
import { writeFileSync } from "node:fs";
const { job_id } = await api("POST", "/run", payload,
{ "Idempotency-Key": crypto.randomUUID() });
let job;
do {
await new Promise((r) => setTimeout(r, 1500));
job = await api("GET", `/jobs/${job_id}`);
} while (job.status !== "succeeded" && job.status !== "failed");
if (job.status === "failed") throw new Error(job.error ?? "run failed");
const raw = job.output?.output ?? job.output;
const review = typeof raw === "string" ? JSON.parse(raw) : raw;
console.log(`${review.review_name} [${review.posture}]: ${review.verdict}`);
for (const r of review.inventory) {
console.log(` ${r.file} ${r.unit} [${r.runner}]: ${r.role}`);
}
for (const f of review.findings) {
console.log(` [${f.priority}] ${f.id} ${f.category} ${f.location}`);
console.log(` L:${f.likelihood}/S:${f.severity} - ${f.fix}`);
}
for (const w of review.quick_wins) console.log(` win: ${w}`);
for (const a of review.focus_areas) {
console.log(` focus ${a.area} (${a.finding_ids.join(", ")}): ${a.why}`);
}
for (const c of review.coverage_check) {
console.log(` ${c.id}: ${c.addressed ? "ok" : "SET ASIDE"} - ${c.note}`);
}
writeFileSync("review.json", JSON.stringify(review, null, 2));
const critical = review.findings.filter((f) => f.priority === "critical");
if (critical.length) process.exitCode = 1;
var started struct{ JobID string `json:"job_id"` }
if err := call("POST", "/run", payload, &started); err != nil {
log.Fatal(err)
}
var job struct {
Status string `json:"status"`
Error string `json:"error"`
Output json.RawMessage `json:"output"`
}
for {
if err := call("GET", "/jobs/"+started.JobID, nil, &job); err != nil {
log.Fatal(err)
}
if job.Status == "succeeded" || job.Status == "failed" {
break
}
time.Sleep(1500 * time.Millisecond)
}
// job.Output is {"output": "<json string>"} — unwrap, then unmarshal:
type Review struct {
ReviewName string `json:"review_name"`
Posture string `json:"posture"`
Verdict string `json:"verdict"`
ExecSummary string `json:"exec_summary"`
Assumptions []string `json:"assumptions"`
OpenQuestions []string `json:"open_questions"`
Inventory []struct {
File, Unit, Runner, Role string
} `json:"inventory"`
Findings []struct {
ID, Category, Severity, Likelihood, Priority string
Location, Problem, Impact, Fix, Snippet string
} `json:"findings"`
CoverageCheck []struct {
ID, Note string
Addressed bool
} `json:"coverage_check"`
QuickWins []string `json:"quick_wins"`
FocusAreas []struct {
Area, Why string
FindingIDs []string `json:"finding_ids"`
} `json:"focus_areas"`
Summary string `json:"summary"`
}
var wrapper struct{ Output string `json:"output"` }
json.Unmarshal(job.Output, &wrapper)
var review Review
json.Unmarshal([]byte(wrapper.Output), &review)
fmt.Printf("%s [%s]: %s\n", review.ReviewName, review.Posture, review.Verdict)
for _, r := range review.Inventory {
fmt.Printf(" %s %s [%s]: %s\n", r.File, r.Unit, r.Runner, r.Role)
}
for _, f := range review.Findings {
fmt.Printf(" [%s] %s %s %s: %s\n", f.Priority, f.ID, f.Category, f.Location, f.Problem)
}
for _, a := range review.FocusAreas {
fmt.Printf(" focus %s %v: %s\n", a.Area, a.FindingIDs, a.Why)
}
os.WriteFile("review.json", []byte(wrapper.Output), 0o644)
String envelope = api("POST", "/run", jsonPayload);
String jobId = /* data.job_id via your JSON library */;
while (true) {
String job = api("GET", "/jobs/" + jobId, null);
String status = /* data.status */;
if (status.equals("succeeded") || status.equals("failed")) break;
Thread.sleep(1500);
}
// The review is at data.output.output as a JSON string — parse it again, then read
// review_name, posture, verdict, exec_summary, assumptions[], open_questions[],
// inventory[] (file/unit/runner/role),
// findings[] (id/category/severity/likelihood/priority/location/problem/impact/fix/snippet),
// coverage_check[] (id/addressed/note), quick_wins[],
// focus_areas[] (area/why/finding_ids[]) and summary.
// Finally keep the review on disk:
// Files.writeString(Path.of("review.json"), reviewJson);
started = api("POST", "/run", payload)
job = nil
loop do
job = api("GET", "/jobs/#{started["job_id"]}")
break if %w[succeeded failed].include?(job["status"])
sleep 1.5
end
raise (job["error"] || "run failed") if job["status"] == "failed"
raw = job["output"].is_a?(Hash) ? job["output"].fetch("output", job["output"]) : job["output"]
review = raw.is_a?(String) ? JSON.parse(raw) : raw
puts "#{review["review_name"]} [#{review["posture"]}]: #{review["verdict"]}"
review["inventory"].each { |r| puts " #{r["file"]} #{r["unit"]} [#{r["runner"]}]: #{r["role"]}" }
review["findings"].each do |f|
puts " [#{f["priority"]}] #{f["id"]} #{f["category"]} #{f["location"]}"
puts " L:#{f["likelihood"]}/S:#{f["severity"]} - #{f["fix"]}"
end
review["quick_wins"].each { |w| puts " win: #{w}" }
review["focus_areas"].each { |a| puts " focus #{a["area"]} #{a["finding_ids"].join(", ")}" }
review["coverage_check"].each { |c| puts " #{c["id"]}: #{c["addressed"] ? "ok" : "SET ASIDE"}" }
File.write("review.json", JSON.pretty_generate(review))
exit 1 if review["findings"].any? { |f| f["priority"] == "critical" }
$started = api("POST", "/run", $payload);
do {
sleep(2);
$job = api("GET", "/jobs/" . $started["job_id"]);
} while (!in_array($job["status"], ["succeeded", "failed"]));
if ($job["status"] === "failed") {
throw new Exception($job["error"] ?? "run failed");
}
$raw = is_array($job["output"]) ? ($job["output"]["output"] ?? $job["output"]) : $job["output"];
$review = is_string($raw) ? json_decode($raw, true) : $raw;
echo "{$review['review_name']} [{$review['posture']}]: {$review['verdict']}\n";
foreach ($review["inventory"] as $r) {
echo " {$r['file']} {$r['unit']} [{$r['runner']}]: {$r['role']}\n";
}
foreach ($review["findings"] as $f) {
echo " [{$f['priority']}] {$f['id']} {$f['category']} {$f['location']}\n";
echo " L:{$f['likelihood']}/S:{$f['severity']} - {$f['fix']}\n";
}
foreach ($review["quick_wins"] as $w) {
echo " win: $w\n";
}
foreach ($review["focus_areas"] as $a) {
echo " focus {$a['area']}: " . implode(", ", $a["finding_ids"]) . "\n";
}
foreach ($review["coverage_check"] as $c) {
echo " {$c['id']}: " . ($c["addressed"] ? "ok" : "SET ASIDE") . "\n";
}
file_put_contents("review.json", json_encode($review, JSON_PRETTY_PRINT));
var started = await SkillSafe.ApiAsync(HttpMethod.Post, "/run", payload);
var jobId = started.GetProperty("job_id").GetString();
JsonElement job;
while (true)
{
job = await SkillSafe.ApiAsync(HttpMethod.Get, $"/jobs/{jobId}");
var status = job.GetProperty("status").GetString();
if (status is "succeeded" or "failed") break;
await Task.Delay(1500);
}
var rawText = job.GetProperty("output").GetProperty("output").GetString();
using var doc = JsonDocument.Parse(rawText!);
var review = doc.RootElement;
Console.WriteLine($"{review.GetProperty("review_name")} " +
$"[{review.GetProperty("posture")}]: {review.GetProperty("verdict")}");
foreach (var r in review.GetProperty("inventory").EnumerateArray())
{
Console.WriteLine($" {r.GetProperty("file")} {r.GetProperty("unit")}: {r.GetProperty("role")}");
}
foreach (var f in review.GetProperty("findings").EnumerateArray())
{
Console.WriteLine($" [{f.GetProperty("priority")}] {f.GetProperty("id")} " +
$"{f.GetProperty("category")} {f.GetProperty("location")} " +
$"(L:{f.GetProperty("likelihood")}/S:{f.GetProperty("severity")})");
}
foreach (var a in review.GetProperty("focus_areas").EnumerateArray())
{
Console.WriteLine($" focus {a.GetProperty("area")}: {a.GetProperty("why")}");
}
await File.WriteAllTextAsync("review.json", rawText!);
The model is asked for one JSON object and nothing else, but a stray code fence or preamble
is always possible. Strip a leading ```json fence, take the text between the
first { and the last }, and only then parse — that is what
the app does before it falls back to a retry_note reformat run.
The review object — output schema
One JSON object, always the same shape. Every array is present, and the review is grounded in
the pasted text alone: findings cite only workflows, jobs, steps, actions and expressions that
actually appear in workflow_text, and something that is simply absent (no
permissions: block, no timeout-minutes, no concurrency
group) is reported against the closest real location or against
(missing from the workflow). Where the
YAML is silent on something that changes the verdict you get an entry in
assumptions and, if it would change the ranking, in open_questions.
Expect five to fifteen findings on a typical workflow — a well-built one may honestly
yield two or three, and findings is never empty.
| Field | Type | Meaning |
|---|---|---|
review_name | string | A short title naming the workflow, taken from the files' own naming — e.g. deploy.yml — CI/CD review. |
posture | string | production-ready | hardening-recommended | not-production-ready. See the table below. |
verdict | string | One sentence justifying the posture and naming the single most important change. |
exec_summary | string | Two or three paragraphs, separated by blank lines, on the dominant themes across the set. |
assumptions | string[] | Explicit assumptions filling gaps the files left open. Read these first — a wrong assumption invalidates the findings built on it. |
open_questions | string[] | Questions whose answers would change the ranking. |
inventory | array | {file, unit, runner, role} — one entry per pasted file (unit workflow) plus one per job (unit job: <name>), and the part it plays. runner is taken from runs-on — e.g. ubuntu-latest — or unknown when there is none. |
findings | array | The prioritized findings table — ids WF-001, WF-002, … in sequence, at least one entry. Columns are listed below. |
coverage_check | array | {id, addressed, note} — one entry per prescan_facts.flags id you sent, each appearing exactly once. See the semantics below. |
quick_wins | string[] | One-line changes worth doing immediately, ahead of any planning. May be empty when nothing here is a one-liner. |
focus_areas | array | {area, why, finding_ids} — what to work through first, one sentence tied to the review, and the finding ids that motivate it. Every id in finding_ids exists in findings. |
summary | string | Closing paragraph: what to fix first, and what risk remains after that. |
The three posture values:
| posture | What it means |
|---|---|
production-ready | The pipeline holds up as written: a least-privilege permissions: block, third-party actions pinned to commit SHAs, no attacker-controlled event text inside run:, timeout-minutes and a concurrency group on the jobs that need them, secrets passed through env: rather than printed. Findings still exist, but they are additions and refinements, not blockers. A genuinely well-built workflow lands here rather than having severity manufactured for it. |
hardening-recommended | The shape is right, but named gaps should be closed before this pipeline is trusted unattended — a missing or over-broad permissions: block, actions on mutable tags, an end-of-life action major, no timeout-minutes, no concurrency group, setup-* steps with no dependency cache, deprecated ::set-output commands. |
not-production-ready | At least one thing is a real security exposure or silently corrupts a release as written: pull_request_target checking out the PR head, ${{ github.event.* }} text interpolated into a run: script, a secret echoed into the log, permissions: write-all alongside deploy credentials, or continue-on-error on a whole job so failures report green. |
Each entry in findings:
| Column | Meaning |
|---|---|
id | Sequential WF-001, WF-002, … — the stable handle referenced from focus_areas[].finding_ids. |
category | correctness | security | robustness | cost | performance | maintainability | hygiene. Weighted by the concern you sent, but never restricted to it. |
severity | low | medium | high — how bad it is when it bites. |
likelihood | low | medium | high — how likely it is to bite. |
priority | critical | high | medium | low — severity by likelihood. critical is reserved for something exploitable, outage-causing or build-breaking as written, so sort on this field and work top-down. This is also the field to gate a pipeline on. |
location | The file and job/step or line this is about — e.g. deploy.yml job deploy, step Push image or ci.yml line 14. Always something that appears in workflow_text, or the literal (missing from the workflow) when the finding is about something absent. |
problem | What is wrong, in this script specifically. |
impact | What happens in a real run because of it. |
fix | The concrete change to make — not "harden the workflow". |
snippet | A corrected YAML fragment you can paste: the fixed block, correctly indented, not the whole file. Empty string when a snippet would add nothing. Secret values are never echoed — a placeholder appears instead. |
coverage_check semantics:
| Case | What you get |
|---|---|
| Every flag id you sent | Each prescan_facts.flags id appears in coverage_check exactly once. Nothing you flagged is silently dropped, which makes this the field to assert on in a CI check. Ids in prescan_facts.files are not reconciled here — they shape the inventory instead. |
addressed: true | The flag is covered by the review; note names the finding id that covers it. |
addressed: false | The flag was deliberately set aside; note gives the reason — a check that fired but is not a real problem for this workflow (a self-hosted runner in a private repo with no fork PRs, a missing cache input on a job with no dependencies, called out in context). |
| Nothing sent | Omit prescan_facts, or send the two empty arrays, and coverage_check comes back empty. The rest of the review is unaffected. |
A small, realistic result for the workflow above, trimmed for length:
{
"review_name": "deploy.yml — CI/CD review",
"posture": "not-production-ready",
"verdict": "An action on a mutable ref and no permissions block put the deploy pipeline one
compromised branch away from arbitrary code with a broad token; pin and scope first.",
"exec_summary": "One short deploy workflow with no permissions block, an action pinned to a
branch, and no timeout or concurrency control.
None of it needs a redesign — pin the action to a SHA, declare least-privilege
permissions, and add timeout-minutes and a concurrency group.",
"assumptions": [
"The repository is public and accepts pull requests from forks.",
"deploy.sh performs the actual deployment and needs only the checked-out tree."
],
"open_questions": [
"Does the deploy environment require a manual approval before this job runs?",
"Is there a staging deploy elsewhere, or does every push to main ship straight to production?"
],
"inventory": [
{ "file": "deploy.yml", "unit": "workflow", "runner": "",
"role": "Deploys the site to a VM on every push to main." },
{ "file": "deploy.yml", "unit": "job: deploy", "runner": "ubuntu-latest",
"role": "Checks out the tree and runs the deploy script." }
],
"findings": [
{ "id": "WF-001", "category": "security",
"severity": "high", "likelihood": "medium", "priority": "critical",
"location": "deploy.yml job deploy, step uses: actions/checkout@main",
"problem": "The checkout action is pinned to a branch, not a SHA or tag.",
"impact": "Whatever the branch points to at run time executes in a job that deploys to
production — a compromised or force-pushed action ships straight through.",
"fix": "Pin to a full commit SHA with a version comment.",
"snippet": "- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v5.0.1" },
{ "id": "WF-002", "category": "security",
"severity": "high", "likelihood": "high", "priority": "high",
"location": "deploy.yml (missing from the workflow)",
"problem": "No permissions block: the workflow inherits the repository default token grant.",
"impact": "Every step, including the third-party action, runs with whatever the repo
default allows — often broad write.",
"fix": "Declare least privilege at the top of the workflow.",
"snippet": "permissions:\n contents: read" },
{ "id": "WF-003", "category": "robustness",
"severity": "medium", "likelihood": "medium", "priority": "medium",
"location": "deploy.yml job deploy",
"problem": "No timeout-minutes and no concurrency group on a deploy job.",
"impact": "A hung deploy burns the 6-hour default, and two quick pushes can interleave
deploys so stale code ships last.",
"fix": "Set a realistic timeout and serialize deploys per ref.",
"snippet": "timeout-minutes: 15\nconcurrency:\n group: deploy-${{ github.ref }}" }
],
"coverage_check": [
{ "id": "unpinned:deploy.yml:9", "addressed": true, "note": "WF-001." },
{ "id": "no-permissions:deploy.yml", "addressed": true, "note": "WF-002." },
{ "id": "no-timeout:deploy.yml:deploy", "addressed": true, "note": "WF-003." }
],
"quick_wins": [
"Add a top-level permissions: contents: read block.",
"Pin actions/checkout to a full commit SHA with a version comment."
],
"focus_areas": [
{ "area": "Supply-chain and token scope",
"why": "Nothing else matters while a mutable action runs with a broad default token.",
"finding_ids": ["WF-001", "WF-002"] },
{ "area": "Deploy serialization",
"why": "Concurrent deploys of a fast-moving main branch can ship stale code last.",
"finding_ids": ["WF-003"] }
],
"summary": "Pin the action and scope the token, then add timeout-minutes and a concurrency
group. …"
}
This is AI-generated review from pasted text, not a production sign-off: it sees only the
text you sent, never the repository, its settings or a live run. Check
assumptions and open_questions before you act on the rankings,
prove every snippet with a real run (and actionlint / zizmor where you have
them), and keep a human reviewer in the loop.
Step 5 — Stream the review as it is written
/run-stream takes exactly the same body as /run but answers with
server-sent events, so you can show progress instead of a spinner — useful here
because a full findings table with corrected YAML fragments makes for a long reply. This app's own
progress panel is this endpoint. Events are separated by a blank line; each has an
event: line and a data: line carrying JSON.
| Event | Payload | Meaning |
|---|---|---|
job | {job_id, status} | Sent once, when the job is accepted — show "starting". |
delta | {text} | A chunk of the reply, in order. Append it; the accumulated length is your only progress signal (the total is not known in advance). The app advances its step list by watching for the "review_name", "inventory", "findings", "coverage_check" and "focus_areas" keys as they arrive. |
done | {job_id, status, charged_credits, output} | The final, authoritative result — read the review from output.output rather than trusting concatenated deltas, and the settled price from charged_credits. |
error | {code, message} | Replaces done when the run fails. |
# -N disables buffering so events print as they arrive
curl -N -s -X POST "$API/run-stream" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-H "Idempotency-Key: sc-$(date +%s)" \
-d @input.json
# event: job
# data: {"job_id":"job_...","status":"running"}
#
# event: delta
# data: {"text":"{\"review_name\":\"node api"}
# ...
# event: done
# data: {"job_id":"job_...","status":"succeeded","charged_credits":612,"output":{"output":"{...}"}}
import json, requests
result = None
with requests.post(
API + "/run-stream",
headers={"Authorization": f"Bearer {TOKEN}",
"Idempotency-Key": "sc-001"},
json=payload,
stream=True,
) as r:
r.raise_for_status()
event = None
for line in r.iter_lines(decode_unicode=True):
if not line:
continue
if line.startswith("event:"):
event = line[len("event:"):].strip()
elif line.startswith("data:"):
data = json.loads(line[len("data:"):].strip())
if event == "delta":
print(".", end="", flush=True) # live progress
elif event == "done":
result = data
elif event == "error":
raise RuntimeError(data.get("message", "run failed"))
review = json.loads(result["output"]["output"]) # authoritative
print("charged:", result["charged_credits"], "-", review["review_name"])
print("posture:", review["posture"])
for f in review["findings"]:
print(f' [{f["priority"]}] {f["id"]} {f["location"]}: {f["problem"]}')
with open("review.json", "w", encoding="utf-8") as fh:
json.dump(review, fh, indent=2)
const res = await fetch(API + "/run-stream", {
method: "POST",
headers: {
Authorization: `Bearer ${TOKEN}`,
"Content-Type": "application/json",
"Idempotency-Key": crypto.randomUUID(),
},
body: JSON.stringify(payload),
});
const reader = res.body.getReader();
const decoder = new TextDecoder();
let buf = "", done = null;
for (;;) {
const chunk = await reader.read();
if (chunk.done) break;
buf += decoder.decode(chunk.value, { stream: true });
const frames = buf.split("\n\n");
buf = frames.pop();
for (const frame of frames) {
const name = /^event:\s*(.+)$/m.exec(frame)?.[1];
const body = /^data:\s*(.+)$/m.exec(frame)?.[1];
if (!name || !body) continue;
const data = JSON.parse(body);
if (name === "delta") process.stdout.write("."); // live progress
if (name === "done") done = data;
if (name === "error") throw new Error(data.message ?? "run failed");
}
}
const review = JSON.parse(done.output.output);
console.log(`\n${done.charged_credits} credits - ${review.review_name} [${review.posture}]`);
for (const f of review.findings) console.log(` [${f.priority}] ${f.id} ${f.location}`);
writeFileSync("review.json", JSON.stringify(review, null, 2));
body, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", API+"/run-stream", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Idempotency-Key", "sc-001")
res, err := http.DefaultClient.Do(req)
if err != nil {
log.Fatal(err)
}
defer res.Body.Close()
var event string
var final map[string]any
sc := bufio.NewScanner(res.Body)
sc.Buffer(make([]byte, 0, 64*1024), 4*1024*1024)
for sc.Scan() {
line := sc.Text()
switch {
case strings.HasPrefix(line, "event:"):
event = strings.TrimSpace(strings.TrimPrefix(line, "event:"))
case strings.HasPrefix(line, "data:"):
var data map[string]any
json.Unmarshal([]byte(strings.TrimPrefix(line, "data:")), &data)
switch event {
case "delta":
fmt.Print(".") // live progress
case "done":
final = data
case "error":
log.Fatal(data["message"])
}
}
}
// final["output"].(map[string]any)["output"].(string) is the review JSON —
// unmarshal it into the Review struct from step 4, then write it to review.json.
// Java 17+ — read the stream line by line instead of buffering the body.
var req = HttpRequest.newBuilder(URI.create(API + "/run-stream"))
.header("Authorization", "Bearer " + TOKEN)
.header("Content-Type", "application/json")
.header("Idempotency-Key", "sc-001")
.POST(HttpRequest.BodyPublishers.ofString(jsonPayload))
.build();
var res = HTTP.send(req, HttpResponse.BodyHandlers.ofLines());
String event = null, done = null;
for (String line : (Iterable<String>) res.body()::iterator) {
if (line.startsWith("event:")) {
event = line.substring(6).trim();
} else if (line.startsWith("data:")) {
String data = line.substring(5).trim();
if ("delta".equals(event)) System.out.print("."); // live progress
else if ("done".equals(event)) done = data;
else if ("error".equals(event)) throw new RuntimeException(data);
}
}
// parse `done`, then parse data.output.output again — it is a JSON string holding
// review_name, posture, verdict, inventory[], findings[], coverage_check[],
// quick_wins[], focus_areas[] and the rest.
require "net/http"
require "json"
uri = URI(API + "/run-stream")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer #{TOKEN}"
req["Content-Type"] = "application/json"
req["Idempotency-Key"] = "sc-001"
req.body = payload.to_json
event = nil
done = nil
Net::HTTP.start(uri.host, uri.port, use_ssl: true) do |http|
http.request(req) do |res|
res.read_body do |chunk|
chunk.each_line do |line|
line = line.strip
if line.start_with?("event:")
event = line.delete_prefix("event:").strip
elsif line.start_with?("data:")
data = JSON.parse(line.delete_prefix("data:").strip)
case event
when "delta" then print "." # live progress
when "done" then done = data
when "error" then raise (data["message"] || "run failed")
end
end
end
end
end
end
review = JSON.parse(done["output"]["output"])
puts "\n#{done["charged_credits"]} credits - #{review["review_name"]} [#{review["posture"]}]"
review["findings"].each { |f| puts " [#{f["priority"]}] #{f["id"]} #{f["location"]}" }
File.write("review.json", JSON.pretty_generate(review))
$event = null;
$done = null;
$ch = curl_init(API . "/run-stream");
curl_setopt_array($ch, [
CURLOPT_POST => true,
CURLOPT_HTTPHEADER => [
"Authorization: Bearer $TOKEN",
"Content-Type: application/json",
"Idempotency-Key: sc-001",
],
CURLOPT_POSTFIELDS => json_encode($payload),
CURLOPT_WRITEFUNCTION => function ($ch, $chunk) use (&$event, &$done) {
foreach (explode("\n", $chunk) as $line) {
$line = trim($line);
if (str_starts_with($line, "event:")) {
$event = trim(substr($line, 6));
} elseif (str_starts_with($line, "data:")) {
$data = json_decode(trim(substr($line, 5)), true);
if ($event === "delta") { echo "."; } // live progress
elseif ($event === "done") { $done = $data; }
elseif ($event === "error") { throw new Exception($data["message"] ?? "run failed"); }
}
}
return strlen($chunk);
},
]);
curl_exec($ch);
curl_close($ch);
$review = json_decode($done["output"]["output"], true);
echo "\n{$done['charged_credits']} credits - {$review['review_name']} [{$review['posture']}]\n";
foreach ($review["findings"] as $f) {
echo " [{$f['priority']}] {$f['id']} {$f['location']}\n";
}
file_put_contents("review.json", json_encode($review, JSON_PRETTY_PRINT));
var req = new HttpRequestMessage(HttpMethod.Post, Api + "/run-stream") {
Content = JsonContent.Create(payload),
};
req.Headers.Add("Idempotency-Key", "sc-001");
using var res = await Http.SendAsync(req, HttpCompletionOption.ResponseHeadersRead);
using var reader = new StreamReader(await res.Content.ReadAsStreamAsync());
string? evt = null, done = null;
while (await reader.ReadLineAsync() is { } line)
{
if (line.StartsWith("event:")) evt = line[6..].Trim();
else if (line.StartsWith("data:"))
{
var data = line[5..].Trim();
if (evt == "delta") Console.Write("."); // live progress
else if (evt == "done") done = data;
else if (evt == "error") throw new Exception(data);
}
}
using var final = JsonDocument.Parse(done!);
var text = final.RootElement.GetProperty("output").GetProperty("output").GetString();
using var reviewDoc = JsonDocument.Parse(text!);
var review = reviewDoc.RootElement;
Console.WriteLine($"{review.GetProperty("review_name")} [{review.GetProperty("posture")}]");
foreach (var f in review.GetProperty("findings").EnumerateArray())
Console.WriteLine($" [{f.GetProperty("priority")}] {f.GetProperty("id")} {f.GetProperty("location")}");
await File.WriteAllTextAsync("review.json", text!);
In a browser, the native EventSource only speaks GET, and this endpoint is a
POST — read the fetch response body incrementally, as the JavaScript
sample above does. On an idempotent replay the server may answer with a plain JSON
envelope instead of an event stream; check the Content-Type before you start
parsing frames.