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/mmilanez/lead-protocol/agents-mdgit clone --depth 1 https://github.com/mmilanez/lead-protocolWhat 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 | $0.00321 | $0.00321 |
| Opus 5 | $0.00161 | $0.00161 |
| Sonnet 5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
lead-protocol 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.
What it actually says
AGENTS.md — Pointer for AI Agents
This file acts as a universal pointer for agents like Cursor, Windsurf, Antigravity, and Codex.
This repository operates under the Lead Protocol. All operational instructions, project context, and state definitions are stored in the .agents/ directory.
Before taking any action, read the rules and the current state in this order:
.agents/CORE_RULES.md— index + essential contracts.agents/PROJECT_RULES.md— identify the scopes listed in§J8 Active modules- For each scope listed in
§J8 Active modules(in declaration order):.agents/modules/<scope>.md .agents/AGENTS_MAP.md— tool-signature → agent-slug map; resolve your own<agent>slug here (needed to form the per-pair handoff path).agents/sessions/active_sessions.md— concurrent-session awareness.agents/local/<actor>/<agent>/handoff.md— state of THIS(actor, agent)pair
PROTOCOL_RULES.md is read on demand, not in the baseline — CORE_RULES.md points to it. See PROTOCOL_RULES.md §P-Access for the full load contract.
Do not bypass the protocol. Your work must be logged in your pair's handoff.md and, when applicable, in .agents/decisions.jsonl and .agents/JOURNAL.md at the end of your session.
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 · 19 lines · 321 tokens per session scan A 8983a36b50da
lead-protocol AGENTS.md is an instructions file published in the GitHub repository mmilanez/lead-protocol (5 stars, last pushed 27d ago), licensed Apache-2.0. It adds 321 tokens to every session, about $0.0016 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
hindsight CLAUDE.md
Instructions for vectorize-io/hindsight, covering claude.md, project overview, development commands, local development (api + ui) and start both api server and control plane ui.
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
relay AGENTS.md
Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
valuecell AGENTS.md
Instructions for ValueCell-ai/valuecell, covering guidelines, python programming, python environment, imports and runtime checks.
neosh AGENTS.md
Instructions for neoswarm/neosh, covering working on neosh, layout, rules that are not negotiable, verification and the command line.