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/feniix/pi-extensions/agents-mdgit clone --depth 1 https://github.com/feniix/pi-extensionsWrote 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/feniix/pi-extensions/agents-md)<a href="https://agentmods.dev/instructions/feniix/pi-extensions/agents-md"><img src="https://agentmods.dev/badge/instructions/feniix/pi-extensions/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 | $0.01516 | $0.01516 |
| Opus 5 | $0.00758 | $0.00758 |
| Sonnet 5 | $0.00303 | $0.00303 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
pi-extensions 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 4d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
- This repo is an npm workspace with independent packages in
packages/*. - Each package follows a consistent layout:
extensions/index.tsfor the pi extension entry point.__tests__/for Vitest tests (e.g.,index.test.ts,helpers.test.ts).README.md,package.json, andLICENSEper package.
- Root-level configs live in
biome.json,tsconfig.json, andvitest.config.ts. docs/solutions/contains documented solutions to past problems (bugs, best practices, workflow patterns), organized by category with YAML frontmatter fields such asmodule,tags, andproblem_type; relevant when implementing or debugging in documented areas.CONCEPTS.mddefines shared domain vocabulary (entities, named processes, status concepts) with project-specific meaning; relevant when orienting to the codebase or discussing domain concepts.
Build, Test, and Development Commands
Run these from the repo root unless noted:
npm run lint— Biome lint/format checks.npm run lint:fix— auto-fixable Biome issues.npm run typecheck— TypeScript type checking only.npm run test— Vitest test suite.npm run test:coverage— Vitest coverage run with repo-wide thresholds.npm run check— lint + typecheck.npm run check:ci— CI-friendly Biome + typecheck.npm run ci:detect -- <base> <head>— show which packages the CI workflow will check for a given diff.
Local package testing:
cd packages/<package-name>pi -e .— run the package in pi without installing.npx biome ci packages/<package-name>— lint a single package.npx tsc --noEmit --project packages/<package-name>/tsconfig.json— typecheck a single package using the shared root TS config via the package wrapper tsconfig.npx vitest run packages/<package-name>/__tests__— run tests for a single package.
Workspace version bumps:
- Use npm workspace versioning from the repo root:
npm version [<newversion> | major | minor | patch | premajor | preminor | prepatch | prerelease | from-git] - Prefer targeting a single package with
--workspace/-w, for example:npm version --workspace packages/pi-devtools minor -w, --workspaceruns the command in the context of the configured workspace(s).
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.
- 4d ago First seen · 104 lines · 1,516 tokens per session scan A e54bda4a1869
pi-extensions AGENTS.md is an instructions file published in the GitHub repository feniix/pi-extensions (23 stars, last pushed 11d ago), licensed MIT. It adds 1,516 tokens to every session, about $0.0076 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
matt-skills-with-to-goal CLAUDE.md
Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
pixir CLAUDE.md
Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.
codeTree CLAUDE.md
Instructions for ThinkyMiner/codeTree, covering claude.md, what this is, structural analysis tools (13), graph & onboarding tools (10) and supported languages.
symphony AGENTS.md
Instructions for broomva/symphony, covering agents.md - symphony, repository purpose, architecture, key design decisions and gathering context from the knowledge graph.