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 sidiangongyuan/codex-skills-library --skill github-project-releasegit clone --depth 1 https://github.com/sidiangongyuan/codex-skills-libraryWrote 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/sidiangongyuan/codex-skills-library/github-project-release)<a href="https://agentmods.dev/skills/sidiangongyuan/codex-skills-library/github-project-release"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/github-project-release/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/sidiangongyuan/codex-skills-library/github-project-release"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/github-project-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 23 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00052 | $0.00950 |
| Opus 5.5 | $0.00021 | $0.00380 |
| Sonnet 5.5 | $0.00010 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
github-project-release 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 1mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Project Release
Turn a local project into a clean GitHub repository that is safe to make public later. Default to research-code release behavior: clean copy first, private GitHub repo first, audit before push.
Workflow
-
Inspect the source project before copying.
- Identify the runnable entrypoints, key configs, curated figures/tables, license, citation files, and upstream dependencies.
- Treat the codebase as source of truth. Do not preserve stale upstream README language as the release front page.
-
Check credentials.
- Run
scripts/github_project_release.py auth-check. - Use the active
ghaccount as the default owner. - Never ask the user to paste a GitHub token into chat. If auth is missing, ask them to run
gh auth loginor provide credentials through a secure non-chat channel.
- Run
-
Prepare a clean release copy.
- Run
scripts/github_project_release.py prepare --source <project> --dest <release-dir>. - Keep only what a new user needs to understand and run the project.
- Exclude datasets, checkpoints, logs, generated outputs, raw experiment dumps, paper PDFs, local submission material, and exploratory files unless the user explicitly overrides the default.
- Run
-
Write or rewrite the README.
- Read
references/readme_playbook.mdbefore drafting README content. - Use English by default.
- Write for external readers, not for the project owner.
- For research code, cover Context + Run + Cite: what it is, what problem it solves, what is included, how to install/run the minimal path, and how to cite current and upstream work.
- Read
-
Audit before publishing.
- Run
scripts/github_project_release.py audit --path <release-dir>. - Treat reported high-risk items as blockers unless the user explicitly accepts them.
- If a paper link is not public, use
Paper link: coming soon.and do not upload PDFs.
- Run
-
Publish privately.
- Run
scripts/github_project_release.py publish --release-dir <release-dir>. - If the repo does not exist, create a private repo.
- If it exists, push only safe non-rewriting updates.
- Do not force-push, delete, overwrite, or make the repo public unless explicitly requested.
- Run
What ships with it
4 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.
- 1mo ago First seen · 95 lines · 52 tokens per session scan A 52cc9d2d5fa5
github-project-release is a skill published in the GitHub repository sidiangongyuan/codex-skills-library (24 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 950 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 2026-08-31.
Other skills, from other repositories
release-skills
A release workflow for preparing and publishing a new version of a software project. A release is a named version that may include updated version files, release notes, tags, or a GitHub Release.
aiwg-pr
AIWG-specific pull request delivery workflow for AIWG product/workspace changes; not the generic repository PR process.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
git-mirror-audit
Verify configured secondary git mirrors are present and not drifting from the primary remote/default branch.
aiwg-delivery-pr
AIWG-specific delivery pull request workflow; explicit alias for aiwg-pr, not a generic repository PR guide.
git-workflow
A Git workflow guide for organizing commits, branches, pull requests, releases, and automated version-control tasks. Git is the system developers use to track code changes and collaborate.