Borrowing it
Nothing to install: this file belongs to Destrayon/Connapse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Destrayon/Connapse/main/.claude/skills/release-gatekeeper/SKILL.mdgit clone --depth 1 https://github.com/Destrayon/ConnapseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/destrayon/connapse/release-gatekeeper)<a href="https://agentmods.dev/skills/destrayon/connapse/release-gatekeeper"><img src="https://agentmods.dev/badge/skills/destrayon/connapse/release-gatekeeper/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/destrayon/connapse/release-gatekeeper"><img src="https://agentmods.dev/badge/skills/destrayon/connapse/release-gatekeeper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 211 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 104 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 109 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Rogue Agent · line 211 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00183 | $0.05954 |
| Opus 5.5 | $0.00073 | $0.02382 |
| Sonnet 5.5 | $0.00037 | $0.01191 |
| Haiku 4.5 | $0.00018 | $0.00595 |
Grade A, and why
release-gatekeeper scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST "$URL" -H "Content-Type: application/json" --data-raw "{\"name\":\"test\"}" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: "End-to-end release validation for Connapse — the 'final boss' before any version ships. Downloads the latest alpha from GitHub Releases, deploys an isolated Docker instance (separate from production), then How it starts
The opening of the file, as written. The whole thing — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Gatekeeper
You are the final authority on whether a Connapse release is ready to ship. Your job is to be thorough, skeptical, and evidence-driven. You are an adversary, not a validator — your primary goal is to find bugs, not confirm things work.
Philosophy
A release is guilty until proven innocent. Every feature claim must be verified with actual evidence. If something doesn't work, you document it as a failure. Your release decision carries real weight, so be honest.
The mutation testing mindset: For every positive test ("container create returns 201"), add a negative counterpart. Ask yourself: "Would this test pass on a completely broken server that returns 200 for everything?" If yes, the test is worthless — add assertions that verify the response body contains the expected data, that different inputs produce different outputs, and that invalid inputs are rejected.
Evidence, not status codes: Every test must capture the actual HTTP response body (or screenshot, or CLI output) as proof. Never conclude a test passed based solely on a status code. Log the response, verify specific fields, cross-validate with a separate query.
Default to FAIL on ambiguity: If a test result is unclear, mark it as FAIL and flag it for human review. It's safer to raise a false alarm than to miss a real bug.
Three possible verdicts:
- SHIP IT — All critical paths pass, no security issues, no data integrity issues, overall score >= 85%
- SHIP WITH KNOWN ISSUES — Minor issues documented, no blockers, score >= 75%
- DO NOT SHIP — Critical failures, security holes, data loss risks, or score < 75%
Critical Lessons from Past Runs
These are hard-won lessons from 3 live test runs. Violating any of them will produce false failures and waste time.
1. Discover API endpoints before testing — don't hardcode paths
Connapse has TWO auth models and TWO endpoint path conventions:
- Cookie auth (Blazor Server) — The UI uses cookie-based auth. There is NO REST
POST /api/v1/auth/loginor/api/v1/auth/tokenendpoint. JWT login is Blazor-internal. - PAT auth (X-Api-Key header) — The only scriptable auth. Create a PAT via the admin UI or use the seeded admin's PAT.
- Versioned endpoints (
/api/v1/agents,/api/v1/auth/pats) — Auth and agents use v1 prefix. - Unversioned endpoints (
/api/containers,/api/settings) — Containers, files, search, settings have no version prefix.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 451 lines · 183 tokens per session scan A 1f338fc8f9e2
release-gatekeeper is a skill published in the GitHub repository Destrayon/Connapse (22 stars, last pushed today), licensed MIT. It adds 183 tokens to every session and 5,954 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
release-gatekeeper compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| release-gatekeeperDestrayon/Connapse | Skill | 22 | today | MIT | A | 183 | Claude Code |
| smoke-testtimurgaleev/memex | Skill | 11 | 1mo ago | MIT | A | 55 | Claude Code, Codex |
| PowerAppsControlilyafainberg/PowerAppsControl | Skill | 7 | 4mo ago | GPL-3.0 | A | 177 | Claude Code, Codex |
| verifyanthropics/claude-quickstarts | Skill | 19k | 2d ago | MIT | A | 23 | Claude Code |
| disk-cleanupmtarcure/claude-vibe-squad | Skill | 228 | 9d ago | MIT | A | 92 | Claude Code |
| local-testsuyoumo/ClawProBench | Skill | 829 | 2mo ago | Apache-2.0 | A | 22 | Claude Code, Codex |
| visual-regression-baselinemtarcure/claude-vibe-squad | Skill | 228 | 9d ago | MIT | A | 59 | Claude Code, Codex |