agentfootprint

agentfootprint is a skill for Claude Code, Codex from footprintjs/agentfootprint. It costs 72 tokens per session (4,045 once invoked), scanned A, a copy of agentfootprint, MIT.

A guide and toolkit for building AI agents with agentfootprint, a framework that represents an agent run as a flow of context, decisions, and tool calls. It supports interchangeable language-model providers and records evidence as the run proceeds.

In plain words
What is it for?
Use it when developing or explaining agentfootprint features such as agents, skills, retrieval, memory, tools, streaming, provider adapters, resilience, recorders, and swarm-style flows.
Why use it?
It helps developers understand the framework's actual APIs and avoid inventing functions or concepts that do not exist. It also supports deterministic testing with mock providers before using a real model.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/footprintjs/agentfootprint/claude-code
Any agent
npx skills add footprintjs/agentfootprint --skill claude-code
Clone the repo
git clone --depth 1 https://github.com/footprintjs/agentfootprint

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/footprintjs/agentfootprint/claude-code.svg)](https://agentmods.dev/skills/footprintjs/agentfootprint/claude-code)
Your own site
<a href="https://agentmods.dev/skills/footprintjs/agentfootprint/claude-code"><img src="https://agentmods.dev/badge/skills/footprintjs/agentfootprint/claude-code.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,045 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00072 $0.04045
Opus 5 $0.00036 $0.02022
Sonnet 5 $0.00014 $0.00809
Haiku 4.5 $0.00007 $0.00404

Measured 3d ago against content hash cd4d9d991248, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentfootprint 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 3d 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.

Origin

This is a copy

100% identical to agentfootprint — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

ai-instructions/claude-code/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentfootprint — The Explainable Agent Framework

agentfootprint structures AI agents as composable flowcharts, so every injection, read, write, decision and tool call becomes connected evidence as the run happens. Every concept takes an LLMProvider — swap mock({...}) for anthropic({...}) with zero code changes.

Core principles:

  • Adapter-swap testing ($0 test runs, deterministic assertions)
  • The ladder: mockollama (free, local, real model) → a paid provider
  • Declare context (facts, steering, skills); the framework decides WHEN it fires and WHICH slot it lands in
  • Collect during traversal, never post-process (inherited from footprintjs)
npm install agentfootprint footprintjs

Read this first — what does NOT exist

These are not hypothetical. A capable author, working from a correct mental model of this library, invented all four in one document. Treat them as the things you are most likely to get wrong here.

You will reach for The reality
startRun(...) No such function. The door is agent.run(input, options?), where AgentInput = { message: string; identity?; continueFrom? } and AgentOutput = string. run() returns AgentOutput | RunnerPauseOutcome — a run paused for a human returns a checkpoint; discriminate with isPaused(result).
RunStep as skill/route history RunStep is real and it is something else — the footprintjs flowchart TOPOLOGY slider, exported from agentfootprint/observe. Its kind is 'sequential' | 'fork' | 'merge' | 'decide' | 'iteration' | 'iteration-exit' | 'react'. Nothing in it concerns skills. Importing it succeeds, which is exactly why it is dangerous. For route history use routeRecorder() from the same door.
the LLM classifier as routing "tier 3" It is a tier-2 strategy. Tier 1 = declared start rules. Tier 2 = the configured scorer — llmClassifier(provider) OR keywordScorer() OR embeddingScorer(e) OR the entry scorer; near-ties fall through rather than argmax. Tier 3 = a menu the model resolves in-band through read_skill's own description, reached only when tier 2 was NOT decisive.
a skill's tools being gated to that skill automatically They are not, by default. defineSkill({ tools }) puts them in the agent's static tool list at build time — visible from iteration 1 whether the skill ever activates or not. Ask for the gate: .toolsFromActiveSkill() (agent-wide), skillGraph({ scopeTools: true }) (graph-wide), or autoActivate: 'currentSkill' (per skill). .tree() leaves are the one shape scoped by default.

Read the full file on GitHub · 317 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. 3d ago First seen · 317 lines · 72 tokens per session scan A cd4d9d991248

Subscribe to this mod's changes

agentfootprint is a skill published in the GitHub repository footprintjs/agentfootprint (20 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 4,045 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agentfootprint, differing in 0 lines, and is treated as a copy.