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/cosmix/loom/claude-mdgit clone --depth 1 https://github.com/cosmix/loomWrote 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/cosmix/loom/claude-md)<a href="https://agentmods.dev/instructions/cosmix/loom/claude-md"><img src="https://agentmods.dev/badge/instructions/cosmix/loom/claude-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 | $0.01250 | $0.01250 |
| Opus 5 | $0.00625 | $0.00625 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
loom 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 today.
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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
⚠️ KNOWLEDGE-FIRST: Your Knowledge Brief already quotes what retrieval judged relevant. Pull more with loom knowledge context --query. Open a file under doc/loom/knowledge/ only when a pull comes back empty; then read the tier-1 summary for the area, and only the tier-2 topics you touch.
Project Overview
Loom is a self-propelling agent orchestration CLI written in Rust. It coordinates Claude Code sessions across git worktrees, enabling parallel task execution with automatic crash recovery and context handoffs.
This is an unreleased project under active development NO BACKWARDS COMPATIBILTY OR MIGRATION ROUTINES SHOULD BE ADDED AT THIS STAGE.
Build Commands
cd loom
cargo build # Development build
cargo build --release # Release build
cargo test # Run all tests
cargo test stage_transitions # Run single test file
cargo test --test e2e # Run end-to-end tests
cargo clippy -- -D warnings # Lint with warnings as errors
cargo fmt --check # Check formatting
Tests use serial_test for isolation - many tests cannot run in parallel.
Architecture
Source Layout (loom/src/)
main.rs CLI entry point (clap-based command definitions)
lib.rs Module exports
commands/ Command implementations (init, run, status, stage, etc.)
daemon/ Unix socket server for IPC (protocol.rs, server.rs)
orchestrator/
core/ Main orchestrator loop and state machine
terminal/ Terminal window spawning abstraction
monitor/ Session health monitoring and context tracking
signals/ Signal generation for agent communication
auto_merge.rs Git merge automation
retry.rs Failure retry with backoff
models/
stage/ Stage state machine (types.rs, transitions.rs)
session/ Session lifecycle tracking
plan/
parser.rs Markdown plan document parser
schema/ YAML metadata validation
graph/ Execution DAG building
fs/ File operations for the .loom/work/ state directory
git/ Git operations (worktrees, branches, merges)
verify/ Acceptance criteria execution
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.
- today Changed · -3 lines · -73 tokens per session 3cf7148c2752
- 4d ago First seen · 147 lines · 1,323 tokens per session scan A 1a2984cd9070
loom CLAUDE.md is an instructions file published in the GitHub repository cosmix/loom (54 stars, last pushed today), licensed MIT. It adds 1,250 tokens to every session, about $0.0063 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
skael CLAUDE.md
Claude Code instructions for skael-dev/skael, covering claude.md, what is skael, commands, architecture and package layout.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
lumen AGENTS.md
AGENTS.md instructions for ory/lumen, covering agents.md, repository expectations and commands.
SciCrucible CLAUDE.md
Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.
aligndev AGENTS.md
AGENTS.md instructions for razr001/aligndev: This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in nodemodules/next/dist/docs/ before writing any code. Heed deprecation notices.