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/footprintjs/agentfootprint/agents-mdgit clone --depth 1 https://github.com/footprintjs/agentfootprintWrote 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/footprintjs/agentfootprint/agents-md)<a href="https://agentmods.dev/instructions/footprintjs/agentfootprint/agents-md"><img src="https://agentmods.dev/badge/instructions/footprintjs/agentfootprint/agents-md.svg" alt="Measured on agentmods" 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 | $0.07987 | $0.07987 |
| Opus 5 | $0.03993 | $0.03993 |
| Sonnet 5 | $0.01597 | $0.01597 |
| Haiku 4.5 | $0.00799 | $0.00799 |
Grade A, and why
agentfootprint 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 4d 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 — 663 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentfootprint — Agent Instructions (OpenAI Codex)
This is the agentfootprint library — a framework for building Generative AI applications where context engineering is buildable at the control-flow level. Built on footprintjs (the flowchart pattern for backend code).
Core Thesis
Building Generative AI applications is mostly context engineering — deciding what content lands in which slot of the LLM call, when, and why. agentfootprint exposes this discipline through:
- 2 primitives —
LLMCall,Agent(= ReAct loop) - 3 compositions + Loop —
Sequence·Parallel·Conditional·Loop - 1 unifying injection primitive —
Injectionwith 4 typed sugar factories - 1 memory factory —
defineMemory({ type, strategy, store })
Every named pattern (Reflexion, ToT, Swarm, ...) is a recipe over these. Don't ship new classes per paper.
The Mental Model — Three Slots, Six Flavors
Every LLM call has three slots. Every "agent feature" is content flowing into one of them:
| LLM API field | What goes here |
|---|---|
system prompt |
Steering · Instruction text · Skill body · Fact data · formatted memory |
messages array |
The conversation — user turns, assistant turns, tool results. Assembled from the conversation itself, never injected into |
tools array |
Tool schemas (registered + Skill-attached) |
The flavors are how you mark intent — but they all reduce to one Injection primitive:
| Flavor | Trigger | Slots |
|---|---|---|
| Skill | LLM-activated (read_skill) |
system-prompt + tools |
| Steering | Always-on | system-prompt |
| Instruction | Predicate (activeWhen / on-tool-return) |
system-prompt |
| Fact | Always-on (data) | system-prompt |
Mock-first development (RECOMMENDED workflow)
Build the entire app — agent, context engineering, tools, memory, RAG, MCP — against in-memory mocks first. Validate logic and patterns end-to-end with $0 API cost. Swap real infrastructure in, one boundary at a time, only after the flow is right.
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.
- 4d ago First seen · 663 lines · 7,987 tokens per session scan A 4613bb2b4c1e
agentfootprint AGENTS.md is an instructions file published in the GitHub repository footprintjs/agentfootprint (20 stars, last pushed today), licensed MIT. It adds 7,987 tokens to every session, about $0.0399 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
agent-governance-toolkit copilot-instructions.md
Copilot instructions for microsoft/agent-governance-toolkit, covering copilot instructions for agent-governance-toolkit, architecture, build, test, and lint, python and install (editable, all extras).
agent-governance-toolkit AGENTS.md
AGENTS.md instructions for microsoft/agent-governance-toolkit, covering agent governance toolkit - repository instructions, project overview, repository layout status, where changes belong and routing rules.
orloj AGENTS.md
Instructions for OrlojHQ/orloj, covering orloj agent instructions, must-follow sync rules and working style.
orloj CLAUDE.md
Instructions for OrlojHQ/orloj, covering orloj claude instructions, critical repository rules and implementation notes.
agent-leash AGENTS.md
Instructions for tonydzi/agent-leash, covering agents.md — working in this repo, what this repo is, layout, how to verify a change and conventions — the claim discipline.
Neuroverseos-governance AGENTS.md
Instructions for NeuroverseOS/Neuroverseos-governance, covering neuroverse governance — agent integration guide, what this package does, quick start for agents, install and enforce a world (permanent rules).