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/baphuongna/pi-crew/agents-mdgit clone --depth 1 https://github.com/baphuongna/pi-crewWrote 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/baphuongna/pi-crew/agents-md)<a href="https://agentmods.dev/instructions/baphuongna/pi-crew/agents-md"><img src="https://agentmods.dev/badge/instructions/baphuongna/pi-crew/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 | $0.00931 | $0.00931 |
| Opus 5 | $0.00465 | $0.00465 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
pi-crew 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 5d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-crew Development Notes
This package is a Pi extension for team orchestration.
Source of Truth
Read in this order:
- This file (
AGENTS.md) for operating rules and paths. docs/HARNESS.mdfor the human-agent collaboration model.docs/FEATURE_INTAKE.mdbefore turning any request into work.docs/product/for current product contracts.docs/architecture.mdfor implementation shape.docs/stories/for story packets and backlog.docs/TEST_MATRIX.mdfor proof status.docs/decisions/for why important choices were made.
Task Loop
For every task:
- Classify the request with
docs/FEATURE_INTAKE.md. - Identify affected modules and risk level.
- Choose lane: tiny, normal, or high-risk.
- Implement the change.
- Run validation:
npm test+npm run typecheck. - Update docs, stories, test matrix, decisions as needed.
- Report what changed and what was not attempted.
Rules
- Keep
index.tsminimal; register functionality fromsrc/extension/register.ts. - Prefer small modules over large orchestrator files.
- Do not copy source from SUL-licensed projects.
oh-my-openagentis concept-only inspiration. - MIT sources such as
pi-subagentsandoh-my-claudecodemay be adapted with attribution inNOTICE.md. - Avoid
any; useunknownplus validation for tool/config inputs. - Avoid dynamic inline imports, EXCEPT at documented lazy-load boundaries to defer heavy runtime cost (mark with
// LAZY: <reason>). - Do not hardcode global keybindings without user configurability.
- Default execution uses child Pi workers. Keep it safe through runtime limits, depth guards, and explicit disable controls (
executeWorkers=false,runtime.mode=scaffold,PI_CREW_EXECUTE_WORKERS=0, orPI_TEAMS_EXECUTE_WORKERS=0). - Worktree cleanup must preserve dirty worktrees unless
forceis explicitly set. - Management deletes must require
confirm: true; referenced resources should be blocked unlessforce: true. - After code changes, run
npm testfrompi-crew/unless explicitly told not to.
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.
- 5d ago First seen · 76 lines · 931 tokens per session scan A de933c1a9feb
pi-crew AGENTS.md is an instructions file published in the GitHub repository baphuongna/pi-crew (51 stars, last pushed yesterday), licensed MIT. It adds 931 tokens to every session, about $0.0047 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.