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 agentmods add skills/liyana31811/codexless/codexless-release-supervisornpx skills add liyana31811/Codexless --skill codexless-release-supervisorgit clone --depth 1 https://github.com/liyana31811/CodexlessWrote 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/liyana31811/codexless/codexless-release-supervisor)<a href="https://agentmods.dev/skills/liyana31811/codexless/codexless-release-supervisor"><img src="https://agentmods.dev/badge/skills/liyana31811/codexless/codexless-release-supervisor.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.01846 |
| Opus 5 | $0.00044 | $0.00923 |
| Sonnet 5 | $0.00017 | $0.00369 |
| Haiku 4.5 | $0.00009 | $0.00185 |
Grade A, and why
codexless-release-supervisor 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 5d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codexless Release Supervisor
Run Codexless releases as a fail-closed state machine. The canonical Codexless source repository is the only editable implementation truth. Public candidate/official repositories are downstream release sinks and must not independently evolve release policy or implementation.
Prefer maintained scripts and observable receipts over memory or hand-written test lists. Keep the current release scope fixed; log non-blocking follow-ups instead of expanding the release.
Start
- Resolve the canonical repository and read its Git state, target version, and current acceptance suite version.
- Read references/release-gates.md before final release/hotfix gating.
- Freeze the canonical commit before deterministic public projection or candidate provenance is claimed.
- Materialize the public projection through the canonical R1 exporter before candidate work.
config/public-export-policy.jsonis the fail-closed file authority;release/public-overlay/is the only canonical public-only overlay source. The exporter reads canonical bytes from the exact Git source commit and reads the immutable public migration seed only from its pinned Git commit, never from a dirty public working tree. - Treat the R1 projection receipt and the older R0 candidate receipt as different evidence. R1 may truthfully report
fullDeterministicExporter=true; the R0 candidate gate remains historical candidate-provenance evidence withfullDeterministicExporter=falseand must not be rewritten or back-claimed. - Build or materialize a release candidate only after the R1 projection is reviewed. Candidate/native-install/publication work is a later gate and is not proven by the exporter.
- If the user asked only for preparation, stop before
git push, tag creation, or GitHub Release publication.
Canonical machine gates
Use the canonical repository's maintained entries:
npm run test:all
npm run test:acceptance:auto
npm run test:public-export
npm run release:public-export -- --base-repo <repo-containing-pinned-public-base> --dry-run
npm run release:candidate-gate -- --candidate <public-candidate-root>
What ships with it
1 file 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.
- 5d ago First seen · 83 lines · 87 tokens per session scan A 617f9973f8a3
codexless-release-supervisor is a skill published in the GitHub repository liyana31811/Codexless (74 stars, last pushed 6d ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,846 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
release-migration
Cut a @waniwani/sdk version bump that ships its own migration path so users can upgrade automatically. Use when bumping the SDK version, releasing a breaking change, editing the changelog for a release, or when the user says "cut a release", "version bump", "ship a breaking change", or "prepare a migration".
deploy-prod
Create a production deployment PR from main to deploy/prod with date-based auto-versioning (YYYY-MM-DD-rN). Use when the user runs /deploy-prod or asks to deploy to production, ship a release, cut a prod release, or open a production deployment pull request. Assumes a repo with a deploy/prod branch and a tag-on-merge…
publish-site
Versioned site deploys to GitHub/Cloudflare/Netlify Pages.
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
release-jetbrains
Use when releasing the Kilo JetBrains plugin -- resolve a version ("next rc" or explicit), run the prepare workflow, edit and commit a filtered human-readable changelog on the release PR, then watch publish to completion.