Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nirecom/agents --skill get-release-approvalgit clone --depth 1 https://github.com/nirecom/agentsWrote 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/nirecom/agents/get-release-approval)<a href="https://agentmods.dev/skills/nirecom/agents/get-release-approval"><img src="https://agentmods.dev/badge/skills/nirecom/agents/get-release-approval/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/nirecom/agents/get-release-approval"><img src="https://agentmods.dev/badge/skills/nirecom/agents/get-release-approval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.00916 |
| Opus 5.5 | $0.00011 | $0.00366 |
| Sonnet 5.5 | $0.00006 | $0.00183 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
get-release-approval scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obtain the user's final release approval for the user_verification step.
This skill is the only issuer of <<WORKFLOW_USER_VERIFIED: reason>>; protocol and preflight branches: skills/_shared/user-verified.md.
Procedure
When a hook blocks a sanctioned command, a fallback path is taken, or any unexpected outcome occurs, report via /supervisor-report (trigger conditions: rules/supervisor-reporting.md).
GA-1. Confirm the step: run node "$AGENTS_MAIN_ROOT/bin/workflow/next-step" --session "<session-id>".
REASON= web-merge-pending or web-merge-not-ready → continue to GA-2; its preflight decides the wait.
Any other REASON= than user_verification → do not emit; follow its ACTION instead.
GA-2. Preflight: run bash "$AGENTS_MAIN_ROOT/skills/get-release-approval/scripts/preflight.sh" --session "<session-id>" as one standalone call.
Handle RUN_TL4=, GATE_RC=, and the CATEGORY: lines per skills/_shared/user-verified.md "Preflight".
PREFLIGHT=web_merge_* → raise no AskUserQuestion; follow that file's "Web-merge channel" (the web merge is the only approval).
PREFLIGHT=blocked → show PREFLIGHT_REASON and its recovery (rebase or update the branch, resolve conflicts, wait for CI or reviews, mark the PR ready), then stop without the sentinel.
PREFLIGHT=merged_on_web → the PR was merged outside this session; continue to GA-3 with a reason that says so.
PREFLIGHT=ok → continue to GA-3.
PREFLIGHT=web_merge_done → the human merged on the web; no sentinel; go to GA-4.
PREFLIGHT=web_merge_closed or web_merge_blocked → show PREFLIGHT_REASON, then stop without the sentinel.
PREFLIGHT=web_merge_pending → no sentinel; show PR_URL as the PR the human merges on the web, then GA-2b.
GA-3. Emit the sentinel per skills/_shared/user-verified.md "Protocol", as its own Bash call.
Reason on the pull_request path: PR #<PR_NUMBER> — approving merge to main (or PR #<PR_NUMBER> merged via web UI for merged_on_web).
Reason on the direct path: a one-line summary of what will be committed and pushed.
Deny → stop; do not retry.
What ships with it
2 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.
- 7d ago First seen · 49 lines · 28 tokens per session scan A cc94d42127f2
get-release-approval is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 916 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Fully automate a release with version-bump and childhood.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.