agentmods.dev

agentfootprint: Instructions file for Claude Code

CLAUDE.md

agentfootprint CLAUDE.md is an instructions file for Claude Code from footprintjs/agentfootprint. It costs 6,882 tokens per session, scanned A, original, MIT.

Repository instructions for agentfootprint, an agent framework built on footprintjs. They map existing features, internal flow, and places where the framework can be extended.

In plain words
What is it for?
Use them when planning agentfootprint changes, tracing how agents and language-model calls run, or identifying the likely files and code paths to modify.
Why use it?
They help developers avoid designing features that already exist and show which upstream framework parts are responsible for behavior.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions subagents.

This is footprintjs/agentfootprint's own configuration. It tells Claude Code how to work on agentfootprint itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentfootprint configures →

not rated 21repo changed yesterday A scan 6,882 tokens original MIT
View source ↗ footprintjs/agentfootprint agentfootprint.dev
Reuse

Borrowing it

Nothing to install: this file belongs to footprintjs/agentfootprint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/footprintjs/agentfootprint/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/footprintjs/agentfootprint

Made for: Claude Code.

Wrote 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.

agentmods badge for agentfootprint CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/footprintjs/agentfootprint/claude-md/github.svg)](https://agentmods.dev/instructions/footprintjs/agentfootprint/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/footprintjs/agentfootprint/claude-md"><img src="https://agentmods.dev/badge/instructions/footprintjs/agentfootprint/claude-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.

agentmods 80×15 button for agentfootprint CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/footprintjs/agentfootprint/claude-md"><img src="https://agentmods.dev/badge/instructions/footprintjs/agentfootprint/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,882 This file is loaded in full into every session.
When invoked 6,882 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06882 $0.06882
Opus 5.5 $0.02753 $0.02753
Sonnet 5.5 $0.01376 $0.01376
Haiku 4.5 $0.00688 $0.00688

Measured yesterday against content hash ff49f7a8faae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentfootprint CLAUDE.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.

CLAUDE.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentfootprint — feature-work map

Agent framework layered on footprintjs: every runner (Agent, LLMCall, compositions, patterns) is a footprintjs chart built ONCE at construction and executed through one native footprintjs run lifecycle per chart. Engine seams (stage kinds, $-methods, engine handlers) live UPSTREAM in footprintjs and are closed here. This file maps this repo's seams and blast radius — trust the code where any doc disagrees.

Definition of done — every change, every session

This repo is built mostly by coding agents. The rules below are what keep docs, examples and releases honest without anyone remembering anything.

  1. Before designing, grep CAPABILITIES.md — the thing may already exist (it has happened repeatedly). Then the nearest noun in src/index.ts.
  2. Code + tests. Run the area's tests while working (npx vitest run test/<area>); the full suite (npm test, ~5 min) before you finish.
  3. One change fragment in .changes/<slug>.md for anything touching src/ (type: fixed|added|changed|breaking|internal|… — see .changes/README.md). Never edit CHANGELOG.md, bump package.json's version, or write a version number anywhere — the release computes and writes it.
  4. A new public capability adds one row to CAPABILITIES.md with Since unreleased.
  5. A user-visible feature updates its page under docs-next/content/docs/ and has a runnable example under examples/ (npm run example -- examples/<dir>/<file>.ts). Docs pull code from the example (<CodeFile region>) rather than pasting it.
  6. npm run docs:regen, then commit everything it changed. CI's generated job fails when a generated file (API mirror, docs-truth report, examples README, AI-instruction copies) is stale.
  7. Fast gate: npm run lint && npm run format && npx tsc --noEmit.
  8. Releasing is not part of a change — merging is. A fragment reaching main makes the Release workflow (.github/workflows/publish.yml) open or update the release PR (release/next: version, CHANGELOG, regenerated docs). Merging THAT PR publishes the tree its CI passed — the gates run again only when the workflow cannot show CI passed them on that exact tree — then tags, publishes to npm with provenance and starts the docs site deploy, which never holds up npm. A red gate releases nothing. Never edit release/next by hand — the workflow rebuilds it.

Read the full file on GitHub · 144 lines

Changes

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.

  1. yesterday Changed · +5 tokens per session ff49f7a8faae
  2. 7d ago Changed · +2 lines · +32 tokens per session 8054c93cf797
  3. 14d ago Changed · -9 tokens per session 9f7a59ef6eb9
  4. 21d ago Changed · +146 tokens per session c99b86944484
  5. 22d ago Changed · +15 lines · +1,446 tokens per session d5f8cb5dc43f
  6. 1mo ago Changed · +14 tokens per session f55386e97b17
  7. 1mo ago Changed · +115 tokens per session 20cb6323313a
  8. 1mo ago Changed · +1 lines · +25 tokens per session b89563e0ef0a
  9. 1mo ago Changed · -92 lines · -18,027 tokens per session a61f96c275ae
  10. 1mo ago First seen · 218 lines · 23,135 tokens per session scan A 69768096016b

Subscribe to this mod's changes

agentfootprint CLAUDE.md is an instructions file published in the GitHub repository footprintjs/agentfootprint (21 stars, last pushed yesterday), licensed MIT. It adds 6,882 tokens to every session, about $0.0275 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.

AI SafetyBuilding agentsLLMagent-frameworkai-agentshuman-in-the-loopobservability
Related

agentfootprint CLAUDE.md compared with instructions from other repositories

agentfootprint CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agentfootprint CLAUDE.mdfootprintjs/agentfootprintInstructions file21yesterdayMITA6,882Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode