Borrowing it
Nothing to install: this file belongs to monotykamary/pi-fabric. 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/monotykamary/pi-fabric/main/AGENTS.mdgit clone --depth 1 https://github.com/monotykamary/pi-fabricWrote 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/monotykamary/pi-fabric/agents-md)<a href="https://agentmods.dev/instructions/monotykamary/pi-fabric/agents-md"><img src="https://agentmods.dev/badge/instructions/monotykamary/pi-fabric/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/monotykamary/pi-fabric/agents-md"><img src="https://agentmods.dev/badge/instructions/monotykamary/pi-fabric/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 | $0.01296 | $0.01296 |
| Opus 5.5 | $0.00518 | $0.00518 |
| Sonnet 5.5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
pi-fabric 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 26d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Golden rule: build when done
Always finish a change with a fresh build before handing it back:
bun run build
Pi loads and publishes the compiled bundle in dist/ — not src/. Tests run
against src/, so green tests alone are not enough: without a build the
change is invisible in the TUI and unpublished. Rebuild so the user can
verify immediately.
Startup: budget the transitive graph, not just the entrypoint
A warm jiti filesystem cache avoids transpilation, not V8 compilation in a new Pi process. A small entrypoint can still import megabytes through barrels, shared chunks, schema builders, or supposedly cheap catalog metadata. Native ESM may bypass jiti's virtual host modules and compile another dependency copy. Do not assume that marking a package external makes startup free.
Keep registration and idle lifecycle hooks cheap. Load optional engines,
parsers, serializers, and UI catalogs at actual first use, not in
session_start, resources_discover, an immediately invoked async function,
or a zero-delay "background" import. Use import type for type-only edges.
For genuinely synchronous render APIs, memoized first-use createRequire
loads of optional third-party dependencies preserve behavior. Do not use
this escape hatch for Pi host APIs: lazy UI must use the supplied host interfaces.
Keep package-local dynamic entry paths stable across installed generations.
When touching startup, run bun run build (the artifact check guards the whole
static closure and optional dependencies), bun run assert:lazy-graph, and
cold-import/idle plus first-use tests. Review shared chunks too: code splitting
can pull a lazy module back into the eager graph. Do not raise a graph budget
just to make a regression pass.
Measure in fresh processes, with the host preloaded and warm transpile caches:
bun run benchmark:startup . ../pi-fovea ../pi-contour
This reports import and registration separately; it is not a full-session boot measurement. Same-process repeated imports measure the module cache, not boot. Compare before/after on the same machine. The probe interleaves extension order and reports CPU time as well as wall time; inspect sample spread on a busy host. Keep CI assertions structural rather than enforcing flaky millisecond thresholds.
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.
- 26d ago Changed 4ee22f218b90
- 27d ago Changed 17fe35fb215b
- 1mo ago Changed · +15 lines · +272 tokens per session 215efd012af8
- 1mo ago Changed · +35 lines · +401 tokens per session a09cbc7e2eef
- 1mo ago Changed · +9 lines · +229 tokens per session f8f5f9d0e4b2
- 1mo ago Changed · +25 lines · +220 tokens per session 1004259b18bd
- 1mo ago First seen · 29 lines · 174 tokens per session scan A 9866887c3ca2
pi-fabric AGENTS.md is an instructions file published in the GitHub repository monotykamary/pi-fabric (278 stars, last pushed 24d ago), licensed MIT. It adds 1,296 tokens to every session, about $0.0052 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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.