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/tintinweb/pi-subagents/agents-mdgit clone --depth 1 https://github.com/tintinweb/pi-subagentsWrote 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/instructions/tintinweb/pi-subagents/agents-md)<a href="https://agentmods.dev/instructions/tintinweb/pi-subagents/agents-md"><img src="https://agentmods.dev/badge/instructions/tintinweb/pi-subagents/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02696 | $0.02696 |
| Opus 5 | $0.01348 | $0.01348 |
| Sonnet 5 | $0.00539 | $0.00539 |
| Haiku 4.5 | $0.00270 | $0.00270 |
Grade A, and why
pi-subagents AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Rules
Conversational Style
- Keep answers short and concise
- No emojis in issues, PR comments, or code
- No fluff or cheerful filler text (e.g., "Thanks @user" not "Thanks so much @user!")
- Technical prose only, be direct
- When the user asks a question, answer it first before making edits or running implementation commands.
- When responding to user feedback or an analysis, explicitly say whether you agree or disagree before saying what you changed.
Code Quality
- Read files in full before wide-ranging changes, before editing files you have not fully inspected, and when asked to investigate or audit. Do not rely on search snippets for broad changes.
- No
anyunless absolutely necessary. - Inline single-line helpers that have only one call site.
- Check
node_modulesfor external API types (@earendil-works/pi-*,@sinclair/typebox, etc.); don't guess. - No inline imports (
await import(),import("pkg").Type, dynamic type imports). Top-level imports only. - Never remove or downgrade code to fix type errors from outdated deps; upgrade the dep instead.
- Match the surrounding code style — it is enforced by biome (
biome.json). - Always ask before removing functionality or code that appears intentional.
- Do not preserve backward compatibility unless the user asks for it.
- This is a pi extension. Respect the Claude Code-compatible tool names, calling conventions, and UI patterns the extension deliberately mirrors; don't diverge from them without a stated reason.
- When reviewing a diff, favor solutions that are elegant, not overengineered — flag needless abstraction, layering, or defensive code that the change doesn't warrant.
Documentation
Read the file that covers a surface before changing its behavior; update it in the same change.
| File | Covers |
|---|---|
README.md |
User-facing reference: features, install, tool parameter tables, commands, settings and defaults, the event table, the RPC channel list, and the src/ file map (## Architecture). Source of truth for defaults and setting names. |
docs/workflows.md |
SubagentWorkflow in depth — how the model writes a script, editing and re-running it, saving a named workflow, agent() options, recipes, troubleshooting. Examples in examples/workflows/. |
docs/rpc.md |
Calling this extension from another pi extension — pi.events lifecycle events (subagents:completed, subagents:ready, …), the subagents:rpc:* channels (ping, spawn, stop, consume), spawn options, error strings, and the Symbol.for("pi-subagents:manager") registry. Source: src/cross-extension-rpc.ts. |
CONTRIBUTING.md |
Contributor guidelines and quality bar. |
SECURITY.md |
Vulnerability reporting. |
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 · 155 lines · 2,696 tokens per session scan A 153f8dd763d0
pi-subagents AGENTS.md is an instructions file published in the GitHub repository tintinweb/pi-subagents (1,047 stars, last pushed 6d ago), licensed MIT. It adds 2,696 tokens to every session, about $0.0135 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 instructions, from other repositories
pi-agent-browser-native AGENTS.md
Instructions for fitchmultz/pi-agent-browser-native, covering pi-agent-browser-native, product-specific guidance, documentation placement, upstream capability baseline and command reference and tool result categories.
pi-cursor-sdk AGENTS.md
Instructions for fitchmultz/pi-cursor-sdk, covering agents.md, purpose, repository map, operating rules and setup and commands.
pi-codex-goal AGENTS.md
Instructions for fitchmultz/pi-codex-goal, covering pi-codex-goal — agent notes, local pi install policy, verify before finishing and layout.
pi-commandcode-provider AGENTS.md
Instructions for patlux/pi-commandcode-provider, a project described as: pi custom provider for the Command Code API — 18 models including Claude, GPT, DeepSeek, Kimi, GLM, MiniMax, and Qwen.
pi-fancy-footer AGENTS.md
Instructions for mavam/pi-fancy-footer, covering pi-fancy-footer, setup, development and release engineering.
pi-plugin-signal-grep AGENTS.md
AGENTS.md instructions for xcjy8bao/pi-plugin-signal-grep, covering ai contributor instructions, engineering principles, search correctness invariants and required workflow.