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 spences10/my-pi --skill pi-release-workflowgit clone --depth 1 https://github.com/spences10/my-piWrote 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/spences10/my-pi/pi-release-workflow)<a href="https://agentmods.dev/skills/spences10/my-pi/pi-release-workflow"><img src="https://agentmods.dev/badge/skills/spences10/my-pi/pi-release-workflow/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/spences10/my-pi/pi-release-workflow"><img src="https://agentmods.dev/badge/skills/spences10/my-pi/pi-release-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.00598 |
| Opus 5.5 | $0.00015 | $0.00239 |
| Sonnet 5.5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
pi-release-workflow 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pi Release Workflow
Use this when preparing, validating, or debugging package releases from this repo.
Workflow
- Check current package changes and Changesets before editing versions.
- Classify each affected package by its public behavior; do not infer the release level from the commit label alone.
- Respect pnpm
minimumReleaseAge; do not blindly bypass it for fresh registry packages. - For catalog/version updates, edit
pnpm-workspace.yamlor package manifests intentionally, then runpnpm installto refresh the lockfile. - Regenerate release artifacts when required, especially startup/package preview assets.
- Validate locally, then test published-package installability with the sandbox skill when applicable.
Version classification
- Patch: bug fixes, documentation, dependency maintenance, and internal refactors that preserve public behavior.
- Minor: new commands, tools, configuration, APIs, or other backward-compatible user-visible capabilities.
- Breaking: use major releases for stable
1.xpackages. While a package intentionally remains pre-1.0, use a minor release and call out the breaking behavior explicitly. - Treat
0.0.xas genuinely experimental. Move a package to0.1.0when it gains a meaningful public feature or is ready for a more stable pre-1.0 contract; do not keep shipping features as patches merely because the package started at0.0.x. - Classify packages independently in batch releases. A root
my-pibump does not require every affected workspace package to use the same release level. - Do not rewrite published versions to correct historical release classification; apply the policy to the next release.
Commands and checks
pnpm changeset statusfor pending release intent.pnpm install --frozen-lockfileto verify committed lockfile state.pnpm run preview:generatewhen preview image output should change.pnpm run checkbefore release PRs or publishing.- Use
pi-package-sandbox-testfor normal-user install/load validation of published Pi packages.
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 · 66 lines · 38 tokens per session scan A eafe91d4cbee
pi-release-workflow is a skill published in the GitHub repository spences10/my-pi (137 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 598 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 2026-08-30.
Other skills, from other repositories
changelog
Create engaging changelogs for recent merges to main branch.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-credit-harvest
Harvest one community PR into a release branch with authorship and credit preserved, verified green, and a warm thank-you.
github
Skill "github" from Hmbown/Codewhale, covering github, when to use, setup, workflow and non-goals.
release
Skill "release" from Hmbown/Codewhale, covering release, invocation, non-goals and workflow.
release-notes
Write release notes for a tagged release — a business-impact summary of what changed for the user, plus a thanks section naming every contributor whose commits are in the release. Short by construction.