agentmods.dev

pi-subagents AGENTS.md

Repository instructions for a Pi package extension, which adds subagent features to the Pi coding environment. They define where agent, launch, runtime, session, and tool code belongs.

In plain words
What is it for?
Planning changes to subagents, child-process launching, session files, runtime state, tools, tests, and extension wiring.
Why use it?
They help agents understand the project’s ownership boundaries and avoid putting unrelated code into catch-all folders. They also identify the expected test setup.

Instructions file for CodexOpenCode

112 7d ago A scan 1,304 tokens original MIT
View the source file edxeth/pi-subagents
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/edxeth/pi-subagents/agents-md
Clone the repo
git clone --depth 1 https://github.com/edxeth/pi-subagents

Made for: Codex, OpenCode.

Per session 1,304 This file is loaded in full into every session.
When invoked 1,304 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 $0.01304 $0.01304
Opus 5 $0.00652 $0.00652
Sonnet 5 $0.00261 $0.00261
Haiku 4.5 $0.00130 $0.00130

Measured 2d ago against content hash a53c68c4517b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

AGENTS.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Read README.md before doing anything. It documents the model, frontmatter, placement policies, and env vars this package exposes.

Package facts

  • This is a Pi package extension. Extension entrypoint is src/index.ts.
  • Tests run on plain node --test (see package.json scripts). npm test and bun test both work.
  • One-off checks (tsc, biome, knip) run via bunx so no extra deps are declared.

Project structure contract

Keep the repository organized by ownership. Do not recreate a catch-all src/subagents/ or generic test/parts/ directory.

Source layout:

  • src/subagents.ts is extension wiring only: event hooks, tool registration, and thin glue.
  • src/agents/ owns agent definitions, catalog messaging, and titles.
  • src/launch/ owns child launch preparation, launch policy, child command construction, resume args, prompt artifacts, runtime path resolution, and session seeding.
  • src/runtime/ owns running state, wait/join, shutdown, background/interactive watchers, result routing, and widgets.
  • src/session/ owns JSONL session helpers and trimmed fork-session logic.
  • src/tools/ owns Pi tool/command implementations and tool policy.
  • src/mux/ owns multiplexer internals; src/mux.ts is the public barrel.
  • src/artifact-storage.ts owns artifact storage roots/paths. src/launch/prompt-artifacts.ts owns writing launch prompt/task artifact files. Do not blur these names.
  • src/types.ts is shared runtime type surface only; do not turn it into a junk drawer.

Test layout:

  • Use test/, not tests/; node --test scripts already target test/.
  • Mirror source ownership in tests. Each domain suite must be imported by test/test.ts, or npm test will not run it.
  • test/support/ is split by ownership; do not recreate a fat test/support.ts. Check the current files with ls rather than assuming.
  • Never name split files part-*, chunk-*, or similar. File names must describe the behavior/domain they test.

File size and split rules

Read the full file on GitHub · 120 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. 2d ago First seen · 120 lines · 1,304 tokens per session scan A a53c68c4517b

Subscribe to this mod's changes

pi-subagents AGENTS.md is an instructions file published in the GitHub repository edxeth/pi-subagents (112 stars, last pushed 7d ago), licensed MIT. It adds 1,304 tokens to every session, about $0.0065 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.

Building agentsPlanningTesting
Related

Other instructions, from other repositories

shuohao-skills CLAUDE.md

Instructions for eternityspring/shuohao-skills, covering claude.md and 行为规则.

eternityspring/shuohao-skills · 398 tokens

postgres-skills AGENTS.md

Instructions for neondatabase/postgres-skills, covering agents.md, repository overview, creating a new skill, directory structure and naming conventions.

neondatabase/postgres-skills · 1,105 tokens

redthread AGENTS.md

AGENTS.md instructions for matheusht/redthread, covering redthread agent architecture, 1. core operating guidelines, 2. the orchestration workflow (principal vs subagents), the principal agent must and subagent usage.

matheusht/redthread · 1,929 tokens

skills AGENTS.md

Instructions for CometWorks/skills: You are an experienced developer of Space Engineers in-game scripts, mods, and plugins.

CometWorks/skills · 197 tokens

OpenSwarm CLAUDE.md

Instructions for VRSEN/OpenSwarm, covering agency builder, background, a note on communication flow patterns, available sub-agents and orchestration responsibilities.

VRSEN/OpenSwarm · 1,865 tokens

AiDAPrivate AGENTS.md

AGENTS.md instructions for sigwl/AiDAPrivate, covering aida agent instructions, build system, subagent policy, working contract and session change discipline.

sigwl/AiDAPrivate · 6,240 tokens