supi: Skill for Claude Code

.pi/skills/update-package-readme/SKILL.md

update-package-readme is a skill for Claude Code from mrclrchtr/supi. It costs 27 tokens per session (1,696 once invoked), scanned A, original, MIT.

A procedure for updating one SuPi package’s README and other Markdown files that directly describe it. It requires checking the installed Pi coding-agent documentation and evidence from the selected package.

In plain words
What is it for?
Use it when updating a package under `packages/supi-*`. It covers checking the package files, revising its README, and correcting direct user-facing references elsewhere in the repository.
Why use it?
It keeps package documentation aligned with the installed documentation and the package’s actual behavior. Its scope prevents unrelated packages or indirect references from being changed.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is mrclrchtr/supi's own configuration. It tells Claude Code how to work on supi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything supi configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/mrclrchtr/supi/main/.pi/skills/update-package-readme/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mrclrchtr/supi

Made for: Claude Code.

Wrote 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.

agentmods badge for update-package-readme

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrclrchtr/supi/update-package-readme/github.svg)](https://agentmods.dev/skills/mrclrchtr/supi/update-package-readme)
Your own site
<a href="https://agentmods.dev/skills/mrclrchtr/supi/update-package-readme"><img src="https://agentmods.dev/badge/skills/mrclrchtr/supi/update-package-readme/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.

agentmods 80×15 button for update-package-readme

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,696 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.01696
Opus 5.5 $0.00011 $0.00678
Sonnet 5.5 $0.00005 $0.00339
Haiku 4.5 $0.00003 $0.00170

Measured 1mo ago against content hash 8e07d416bebd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

.pi/skills/update-package-readme/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 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.

Audience and relevance

Extension READMEs serve end users. Public library READMEs serve API consumers. For internal packages and test utilities, identify the intended maintainer or developer audience.

Keep a detail only if it helps that audience install, use, configure, or troubleshoot the package, or understand its limits and risks. For libraries, this includes public API contracts and examples. Keep maintainer setup and source file lists in contributor documentation rather than extension user READMEs.

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:

  1. README.md
  2. docs/index.md
  3. docs/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.md for an extension
  • docs/skills.md for skills
  • docs/prompt-templates.md for prompts
  • docs/themes.md for themes
  • docs/tui.md and docs/keybindings.md for interactive terminal user interfaces or shortcuts
  • docs/sdk.md for a library that uses Pi programmatically

Read the full file on GitHub · 151 lines

Changes

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.

  1. 1mo ago Changed · +8 lines 8e07d416bebd
  2. 1mo ago Changed · +2 lines 37183ce72e77
  3. 2mo ago First seen · 141 lines · 27 tokens per session scan A 007d5b57dd00

Subscribe to this mod's changes

update-package-readme is a skill published in the GitHub repository mrclrchtr/supi (103 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,696 once invoked, about $0.0001 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.