agentmods.dev

lead-protocol CLAUDE.md

A set of repository instructions for coordinating multiple coding agents. It tells each session which rule, project, mapping, and handoff files to read before doing work.

In plain words
What is it for?
Starting coding sessions in a repository that uses the Lead Protocol. It helps agents load the right operating rules, understand active work, and continue from a previous handoff.
Why use it?
It prevents agents from missing project rules or duplicating work with other active sessions. It also makes the current agent's saved handoff state part of the startup process.

Instructions file

5 28d ago A scan 266 tokens original Apache-2.0
View the source file mmilanez/lead-protocol
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 instructions/mmilanez/lead-protocol/claude-md
Clone the repo
git clone --depth 1 https://github.com/mmilanez/lead-protocol
Per session 266 This file is loaded in full into every session.
When invoked 266 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00266 $0.00266
Opus 5 $0.00133 $0.00133
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00027 $0.00027

Measured 3d ago against content hash f8380f75d078, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lead-protocol 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 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.

CLAUDE.md · 19 lines

What it actually says

CLAUDE.md — Pointer for Claude Code

This repository uses the Lead Protocol for multi-agent coordination. Your comprehensive operational instructions are strictly located in .agents/.

MANDATORY BOOT PROCEDURE: At the start of every session, you MUST silently read the following files in order:

  1. .agents/CORE_RULES.md — index of operations and essential contracts
  2. .agents/PROJECT_RULES.md — business context; read §J8 Active modules first
  3. For each scope listed in §J8 Active modules (in declaration order): .agents/modules/<scope>.md
  4. .agents/AGENTS_MAP.md — tool-signature → agent-slug map (needed to resolve your own <agent> slug)
  5. .agents/sessions/active_sessions.md — concurrent-session awareness
  6. .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.

Never proceed with coding tasks without first verifying the state in your pair's handoff.md.

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 · 19 lines · 266 tokens per session scan A f8380f75d078

Subscribe to this mod's changes

lead-protocol CLAUDE.md is an instructions file published in the GitHub repository mmilanez/lead-protocol (5 stars, last pushed 28d ago), licensed Apache-2.0. It adds 266 tokens to every session, about $0.0013 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.

Building agentsProject managementagentic-aiagentsaiai-agentsaudit-trailhandoff
Related

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.

vectorize-io/hindsight · 4,846 tokens

agent-framework copilot-instructions.md

Instructions for microsoft/agent-framework, covering github copilot instructions, repository structure and architectural decision records (adrs).

microsoft/agent-framework · 211 tokens

hindsight AGENTS.md

Instructions for vectorize-io/hindsight: See CLAUDE.md for project documentation and coding conventions.

vectorize-io/hindsight · 25 tokens

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.

justrach/codedb · 509 tokens

agentrq AGENTS.md

Instructions for agentrq/agentrq, covering agentrq codebase notes, project layout, running tests, mcp server (backend/internal/controller/mcp/) and events (experimental).

agentrq/agentrq · 826 tokens

claude-code-settings copilot-instructions.md

Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.

feiskyer/claude-code-settings · 649 tokens