Borrowing it
Nothing to install: this file belongs to mrclrchtr/supi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mrclrchtr/supi/main/.pi/skills/update-package-readme/SKILL.mdgit clone --depth 1 https://github.com/mrclrchtr/supiWrote 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/mrclrchtr/supi/update-package-readme)<a href="https://agentmods.dev/skills/mrclrchtr/supi/update-package-readme"><img src="https://agentmods.dev/badge/skills/mrclrchtr/supi/update-package-readme.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.01474 |
| Opus 5 | $0.00014 | $0.00737 |
| Sonnet 5 | $0.00005 | $0.00295 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
update-package-readme 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 3d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update one package README
Use this skill with one workspace-relative package directory:
/skill:update-package-readme packages/supi-cache
Subject boundary
Take exactly one package directory from the skill arguments. Accept one optional leading @, then require a path that matches packages/supi-*. Require package.json and README.md in that directory. Ask for a valid path when the argument is missing or ambiguous.
The selected package is the only package whose documentation is in scope. The allowed edits are:
- the selected package's
README.md - current user-facing Markdown files that make a direct claim about that package
A direct claim is a sentence, list item, table row, install example, or link that names the package and describes its purpose, status, installation, or public behavior. Search repository-owned Markdown files for the directory name, npm package name, and package README link.
Phase 1 — Read the installed Pi docs
Use the installed @earendil-works/pi-coding-agent path supplied by the harness. Otherwise, check node_modules/@earendil-works/pi-coding-agent. Ask for the docs location when the package is not installed.
Read these files in order:
README.mddocs/index.mddocs/packages.md
Next, inspect only the selected package's manifest, exports, and extension entrypoint. Use this short scan to identify its Pi resources and public library surface. Then read the matching docs:
docs/extensions.mdfor an extensiondocs/skills.mdfor skillsdocs/prompt-templates.mdfor promptsdocs/themes.mdfor themesdocs/tui.mdanddocs/keybindings.mdfor interactive terminal user interfaces or shortcutsdocs/sdk.mdfor a library that uses Pi programmatically
Follow direct Markdown links from the selected docs when the linked material defines an API or convention used by the package. Stop when each applicable install, resource, and usage rule has one Pi documentation source. Use the installed docs as the authority for Pi behavior.
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.
- 3d ago Changed · +2 lines 37183ce72e77
- 9d ago First seen · 141 lines · 27 tokens per session scan A 007d5b57dd00
update-package-readme is a skill published in the GitHub repository mrclrchtr/supi (89 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 1,474 once invoked, about $0.0001 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
review
Review a change for correctness, security, and missing tests.
pi-parity-review
Adversarially verify that a ported change is faithful to the original pi implementation (TS source + published npm build). Use after porting upstream pi changes, or standalone on any area of this repo ("is X faithful to pi?").
pi-go-review
Review ported Go code for idiomatic quality — that the port maximizes Go rather than transliterating TypeScript. Use after porting upstream pi changes, or standalone on any diff in this repo.
review-pr
Deeply review a GitHub pull request.
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
review-agent
Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.