swarm-pi-code-plugin CLAUDE.md

Repository instructions for a coding project where documentation is treated as part of every product change. They define checks for documentation, configuration, screenshots, version changes, and releases.

In plain words
What is it for?
Use them when changing functional code, configuration, screenshots, or release versions in this repository. They specify the checks to run and the files or review notes to update.
Why use it?
They help keep code, documentation, screenshots, and installed versions consistent. Required checks also make it easier to catch incomplete changes before delivery.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/jiaweixie/swarm-pi-code-plugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/JiaWeiXie/swarm-pi-code-plugin
Per session 447 This file is loaded in full into every session.
When invoked 447 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00447 $0.00447
Opus 5 $0.00224 $0.00224
Sonnet 5 $0.00089 $0.00089
Haiku 4.5 $0.00045 $0.00045

Measured 3d ago against content hash 4f42c19c39f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

swarm-pi-code-plugin CLAUDE.md 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.

CLAUDE.md · 18 lines

What it actually says

Repository instructions for AI coding agents

This repository treats documentation as part of the product change. Preserve unrelated dirty worktree changes and do not reset, stash, discard, commit, push, or install external tooling without explicit scope.

After changing functional code, run mise run docs-check. A failure means the work is incomplete: update both README.md and README.zh-TW.md, then update the focused reference required by the report.

For Configuration changes, inspect the Web implementation and docs/configuration.md together. Changes to src/web/ui.ts require updating one of the six current setup screenshots, unless a deliberate Screenshot-Impact: reviewed-current declaration with a meaningful reason is recorded.

Before delivery, stage only the intended files and run mise run docs-check-staged. In the final summary, report the checker command and result, documentation files changed, screenshot files changed or reviewed-current, and the relevant targeted verification.

Before and after any release version bump, use mise run version-check-installed. Run releases through mise run version-bump -- <patch|minor|major|X.Y.Z>; it reinstalls the local Codex plugin before and after synchronization so the installed manifest receives the new version value. Keep both Claude and Codex manifests free of a hooks field because Claude Code automatically loads hooks/hooks.json.

The repository pre-commit hook is advisory for humans. Treat its documentation-impact failure report as required work even though the hook exits successfully.

Use the Conventional Commits format for every commit. Start messages with a valid type such as feat:, fix:, docs:, test:, refactor:, build:, ci:, chore:, or revert:; add a scope when useful (for example, docs(configuration): ...). Keep the subject imperative and concise, and use a breaking-change marker (! or a BREAKING CHANGE: footer) when applicable.

When a command may build, compile, run a full test suite, launch a browser, or recurse through a task runner, inspect its scripts first and run the smallest relevant verification sequentially. Do not invent concurrency flags.

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. 3d ago First seen · 18 lines · 447 tokens per session scan A 4f42c19c39f9

Subscribe to this mod's changes

swarm-pi-code-plugin CLAUDE.md is an instructions file published in the GitHub repository JiaWeiXie/swarm-pi-code-plugin (2 stars, last pushed 10d ago), licensed MIT. It adds 447 tokens to every session, about $0.0022 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 2026-08-31.

Related

Other instructions, from other repositories