Borrowing it
Nothing to install: this file belongs to mpsuesser/pi-effect-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mpsuesser/pi-effect-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/mpsuesser/pi-effect-harnessWrote 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/mpsuesser/pi-effect-harness/agents-md)<a href="https://agentmods.dev/instructions/mpsuesser/pi-effect-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/mpsuesser/pi-effect-harness/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/mpsuesser/pi-effect-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/mpsuesser/pi-effect-harness/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01252 | $0.01252 |
| Opus 5.5 | $0.00501 | $0.00501 |
| Sonnet 5.5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
pi-effect-harness 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 2mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — pi-effect-harness
A bun workspace that publishes pi-effect-harness: a Pi extension turning the Pi coding agent into an Effect v4–aware harness. See README.md for the user-facing description.
Layout
packages/
harness-kit/ Internal kernel — Effect services for rules, hooks,
decisions, write projection, pattern matching.
Wraps Pi's ExtensionAPI in an Effect runtime.
agentsmd-undriftable/ CLI (`amdu`) for keeping AGENTS.md sections
deterministically generated from TypeScript source
via ts-morph. Independent utility, lives here for now.
harnesses/
effect/ The published artifact (`pi-effect-harness`).
src/ Extension entrypoint, services, rules, hooks, atoms.
patterns/ 46 ast-grep / regex pattern detectors (md + YAML).
skills/ 41 effect-* skills loaded into Pi's /skill: namespace.
guidance/ Markdown docs merged into the system-prompt header.
test/ One file per source module + a few cross-cutting
tests (all-patterns-covered, skill-gate-projection,
guidance-docs-injection, comment-string-false-positives).
sandboxes/
amdu-demo/ Throwaway projects for trying things out.
Treat as ephemeral.
The split between harness-kit and harnesses/effect is not load-bearing. Code migrates between the two as the kernel firms up. If something feels miscategorized, it probably is — move it.
Verification
bun run check # dprint format + oxlint + tsgo typecheck
bun run test # vitest run
bun run check && bun run test # what CI runs
Single tests:
bunx vitest run harnesses/effect/test/avoid-any.test.ts
bunx vitest run -t "blocks Effect writes"
bun install runs effect-tsgo patch in prepare to patch tsgo for Effect's type-level encoding. Expected; not a problem.
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.
- 2mo ago First seen · 91 lines · 1,252 tokens per session scan A 4c4751d7e990
pi-effect-harness AGENTS.md is an instructions file published in the GitHub repository mpsuesser/pi-effect-harness (25 stars, last pushed 4mo ago), licensed MIT. It adds 1,252 tokens to every session, about $0.0050 per session on Opus 5.5. 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.
pi-effect-harness AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pi-effect-harness AGENTS.mdmpsuesser/pi-effect-harness | Instructions file | 25 | 4mo ago | MIT | A | 1,252 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |