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/ericchansen/aifmt/agents-mdgit clone --depth 1 https://github.com/ericchansen/aifmtWhat 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 | $0.01153 | $0.01153 |
| Opus 5 | $0.00576 | $0.00576 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
aifmt 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 yesterday.
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.
aifmt Agent Instructions
What is this project?
aifmt is an MCP server + Copilot CLI plugin that makes visual text content "just work" in AI coding assistants. It fixes, validates, and generates diagrams, tables, box-drawing art, and tree diagrams.
⚠️ CRITICAL: You Cannot Verify Rendering — Humans Must
This is the single most important rule for working on this project.
You (the AI) cannot see how text renders on GitHub, in terminals, or in any visual context. You can read source code and count characters, but you cannot verify that a box, table, or tree diagram actually looks correct when rendered.
Every visual output claim must be verified by a human looking at the rendered result. This means:
- Never say "this looks correct" or "this is fixed" — you don't know that. Say "this is what the fixer produces — please verify on GitHub."
- Never hand-write visual content (boxes, tables, trees) and claim it's correct. Always generate it by running the actual fixer code, then ask the human to verify.
- When writing tests, the expected output for visual content should be
human-verified, not assumed. Use
# FIXME: human-verifycomments for unverified expected values. - When fixing a visual bug, push to GitHub and ask the user to check the rendered result. A passing test does NOT mean the output renders correctly — the test might be checking the wrong thing.
- The fixer's math can be wrong even when tests pass. We discovered that emoji = 2.5 cols on GitHub (not 2.0) only because a human looked at screenshots. No amount of unit testing would have caught that.
The Development Loop
You write code → You run tests → Tests pass → You push →
Human checks rendered output → Human reports what's wrong →
You fix → repeat
Do NOT skip the human verification step. Do NOT claim work is done until the human confirms the rendered output is correct.
Key Discovery: GitHub Emoji = 2.5 Columns
Through empirical testing (human screenshots), we discovered:
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.
- yesterday First seen · 104 lines · 1,153 tokens per session scan A 6bdaca2cf8ec
aifmt AGENTS.md is an instructions file published in the GitHub repository ericchansen/aifmt (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,153 tokens to every session, about $0.0058 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.