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/firstp1ck/pi-coding-agent-forge/agents-mdgit clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forgeWhat 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 | $0.02075 | $0.02075 |
| Opus 5 | $0.01038 | $0.01038 |
| Sonnet 5 | $0.00415 | $0.00415 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
pi-coding-agent-forge 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.
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository documentation rules
This file applies to the whole repository. A more specific AGENTS.md in a package directory may add package-specific rules, but it must not weaken the documentation layers defined here.
Documentation goal
Write documentation for the person reading it:
README.mdis the friendly starting point for users.TECHNICAL.mdis an advanced user reference.DEVELOPMENT.mdis for contributors and implementation details.
Do not put every fact in the README. Do not hide essential usage or safety information in a developer document. Move information between layers instead of deleting it.
Required documentation layers
README.md — human guide
The README answers:
- What is this package or skill?
- Why would I use it?
- What can it do?
- How do I install it?
- How do I use it for the first time?
- Is there anything important to configure or keep safe?
- Where can I learn more?
Use plain language, short sections, and realistic examples. Keep exact command names, but explain what each important command does.
The README may contain:
- a one-sentence purpose;
- user-facing features;
- installation instructions;
- a practical first-use flow;
- common commands or example requests;
- essential requirements;
- prominent safety and privacy warnings;
- links to
TECHNICAL.mdwhen advanced user information exists.
The README must not contain:
- internal API endpoints;
- request or response payloads;
- schemas or protocol details;
- internal algorithms or architecture;
- source-file maps;
- contributor test commands and fixtures (user-facing health checks are allowed);
- benchmark implementation methods;
- repository contribution or package-publication internals. User-facing release steps remain allowed when release management is the package’s purpose.
TECHNICAL.md — advanced user reference
TECHNICAL.md is still user documentation. It is not a developer dump.
It may contain:
- complete user commands and options;
- user-editable settings and environment variables;
- runtime requirements and supported platforms;
- storage and configuration locations users may need;
- compatibility and operational limitations;
- security and privacy behavior;
- safe update, migration, and rollback behavior;
- troubleshooting guidance;
- links to
DEVELOPMENT.mdfor implementation details.
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.
- 2d ago First seen · 280 lines · 2,075 tokens per session scan A bf5d722d718a
pi-coding-agent-forge AGENTS.md is an instructions file published in the GitHub repository Firstp1ck/pi-coding-agent-forge (74 stars, last pushed 2d ago), licensed MIT. It adds 2,075 tokens to every session, about $0.0104 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
cldcde CLAUDE.md
Instructions for aegntic/cldcde, covering claude.md, commands, development, database and architecture.
kkRepo java-server.instructions.md
Instructions for klboke/kkRepo, a project described as: kkRepo is a Nexus-compatible, self-hosted artifact repository for Maven, npm, PyPI, Go, Helm, NuGet, Cargo/Rust, Dart/Pub, Docker/OCI, RubyGems, and Yum artifacts. It supports one-click migration from Nexus to kkRepo.
rosetta AGENTS.md
Instructions for tikoci/rosetta, covering codex instructions for rosetta, first reads, development defaults and mcp and client config.
rosetta llm-instruction-files-excluded-from-mdlint.instructions.md
LLM-targeted instruction files are excluded from markdownlint so authoring rules for human docs do not distort agent-facing guidance.
sandy CLAUDE.md
Instructions for jamestelfer/sandy, covering claude.md, voice, what is sandy, project layout and dev commands.
cctop AGENTS.md
Instructions for stefanprodan/cctop, covering agents.md, what this is, bun docs mcp server, commands and layout.