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 agentmods add instructions/jiaweixie/swarm-pi-code-plugin/claude-mdgit clone --depth 1 https://github.com/JiaWeiXie/swarm-pi-code-pluginWhat 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 | $0.00447 | $0.00447 |
| Opus 5 | $0.00224 | $0.00224 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00045 | $0.00045 |
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.
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.
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 First seen · 18 lines · 447 tokens per session scan A 4f42c19c39f9
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.
Other instructions, from other repositories
agent-framework copilot-instructions.md
Instructions for microsoft/agent-framework, covering github copilot instructions, repository structure and architectural decision records (adrs).
dark-factory AGENTS.md
Instructions for DUBSOpenHub/dark-factory, covering agents.md — working guide for ai agents, architecture, file ownership map, before you change anything and agent prompt rules.
paperclip-plugin-company-wizard CLAUDE.md
Instructions for Yesterday-AI/paperclip-plugin-company-wizard, covering claude.md, what this is, commands, architecture and source layout.
dark-factory copilot-instructions.md
Instructions for DUBSOpenHub/dark-factory, covering copilot instructions — dark factory, file map, non-negotiables, prohibited actions and pr requirements.
team-shinchan AGENTS.md
Instructions for seokan-jeong/team-shinchan, covering agents.md - team-shinchan agent map, layer architecture, agent registry, call flow and quick reference.
AssemblyZero CLAUDE.md
Claude Code instructions for martymcenroe/AssemblyZero, covering claude.md - assemblyzero, running workflows (critical), lld workflow (write an lld for an issue), implementation workflow (implement code from an lld) and common gotchas.