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 alexei-led/cc-thingz --skill releasing-codegit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/alexei-led/cc-thingz/releasing-code)<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/releasing-code"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/releasing-code/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/alexei-led/cc-thingz/releasing-code"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/releasing-code.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 | $0.00053 | $0.00920 |
| Opus 5.5 | $0.00021 | $0.00368 |
| Sonnet 5.5 | $0.00011 | $0.00184 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
releasing-code 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 17d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releasing Code
Prepare a release, route its publication, write its notes, or repair notes on a published release. Read notes.md when writing or checking release content. Follow the project's own release instructions where they are more specific.
Safety rules
- Publishing and repair change external state. Before any external mutation, get explicit user authorization for the exact repository, tag, and action. Skill routing, a tool approval, a passing check, or workflow ownership is not authorization.
- When a workflow owns the GitHub release, use that workflow's supported trigger. Do not publish around it with the CLI.
- Never overwrite package versions, move an existing local or published tag, force-push, or add
--clobber. - If the publisher, repository policy, a multi-step publication path, or the prior publication state is unclear, stop and ask.
Prepare
Done when the notes pass the checker, the full staged release diff is reviewed, and the project's release validation passes. Commit, tag, or publish only after the notes are reviewed.
- Identify the project, the intended version and tag, the last published release, and the publisher. Read the working tree, tags, recent commits, diffs, and release configuration; do not infer policy from a workflow filename.
- Take changes since the verified previous release from commit bodies and diffs. Keep only user-visible changes that shipped in this release.
- Use the committed changelog or other established release source as the single notes source. Do not write a separate body for the hosting service.
- For each declared breaking change, write an
Upgradesection with the required action, when to take it (before or after upgrading), and the consequence of skipping it.
Determine who publishes
Read the workflow steps and scripts for the operation that actually creates or updates the GitHub release. A tag workflow that only builds or uploads package artifacts does not own the GitHub release.
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.
- 17d ago Changed · +1 lines 6d87c0f852d0
- 21d ago First seen · 53 lines · 53 tokens per session scan A 2564568bfdd3
releasing-code is a skill published in the GitHub repository alexei-led/cc-thingz (37 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 920 once invoked, about $0.0002 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 2026-09-25.
Other skills, from other repositories
explain-pr
Explain a PR: the background problem and the proposed solution.
release
Release gentle-pi through GitHub and npm. Trigger: release, publish, npm publish, GitHub release, version bump.
ship
Use when code is ready to ship — creates PRs, merges, deploys, and verifies. Handles the full PR-to-production pipeline. Triggers on /ship.
release-readiness
Use after review/qa/security/license-audit/privacy-check to compose a release decision before /ship. Returns OK only when all required upstream evidence is present and clean. Triggers on /release-readiness.
upload
Pre-upload gate for track handoff. Verifies review status, HLD approvals, deploy checklist, and validator chain before git upload or PR submission.
plate
Turn finished local work into a commit, an ordinary pull request, or a pull request stack. Use this skill to commit changes or to publish a branch. Use it to open or update a pull request. Use it to create, sync, restack, or submit a pull request stack. You can also run /plate. This skill owns all staging, commits…