mulch CLAUDE.md

mulch CLAUDE.md is an instructions file for coding agents from jayminwest/mulch. It costs 3,557 tokens per session, scanned A, original, MIT.

Repository instructions for the Mulch command-line tool, including its build and test commands, architecture, storage model, and record types. A command-line tool is software operated through a terminal.

In plain words
What is it for?
They help run tests, linting, type checks, and quality gates, while explaining how Mulch stores structured expertise files and how its architecture works.
Why use it?
They give coding agents consistent project-specific rules for building, checking, and changing the repository.

Instructions file

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/jayminwest/mulch/claude-md
Clone the repo
git clone --depth 1 https://github.com/jayminwest/mulch

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 mulch CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jayminwest/mulch/claude-md.svg)](https://agentmods.dev/instructions/jayminwest/mulch/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jayminwest/mulch/claude-md"><img src="https://agentmods.dev/badge/instructions/jayminwest/mulch/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,557 This file is loaded in full into every session.
When invoked 3,557 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 $0.03557 $0.03557
Opus 5 $0.01778 $0.01778
Sonnet 5 $0.00711 $0.00711
Haiku 4.5 $0.00356 $0.00356

Measured 4d ago against content hash 24314442aa8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mulch 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 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.

CLAUDE.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 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.

Build & Test Commands

bun test              # bun test (all tests)
bun test --watch      # bun test --watch
bun test test/commands/record.test.ts  # single test file
bun run lint          # biome check --error-on-warnings src/ test/
bun run typecheck     # tsc --noEmit
bun run check:all     # canonical quiet runner — all nine quality gates
bun run verify        # alias for check:all (agent-facing entry point)

check:all follows the os-eco fleet standard (docs/check-all-standard.md at the os-eco root): scripts/check-all.ts resolves the ordered gate manifest (lint → typecheck → check:agents → check:dups → check:deps → check:size → check:debt → check:coverage → check:ci-parity) from package.json. The runner and scripts/check-ci-parity.ts are byte-identical fleet-wide — never edit them in place; per-repo CI-parity escape hatches (aliases / ciOnly) live in scripts/ci-parity-config.json.

Architecture

Mulch is a passive CLI tool (@os-eco/mulch-cli) that manages structured expertise files for coding agents. It has no LLM dependency — agents call ml record / ml query, and Mulch handles storage and retrieval. Bun is the runtime — source .ts files are executed directly with no build step.

Storage Model

  • Expertise entries: JSONL files in .mulch/expertise/<domain>.jsonl (one record per line, append-only)
  • Config: YAML at .mulch/mulch.config.yaml
  • Storage ≠ delivery: JSONL on disk is machine-optimized; ml prime outputs agent-optimized markdown

Record Types & Classifications

Six built-in types: convention, pattern, failure, decision, reference, guide — each with type-specific required fields defined in src/schemas/record.ts. Projects can declare additional types under custom_types: in mulch.config.yaml; the registry layer (src/registry/) treats them identically (CLI flags, validation, dedup, formatters).

Read the full file on GitHub · 210 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. 4d ago First seen · 210 lines · 3,557 tokens per session scan A 24314442aa8f

Subscribe to this mod's changes

mulch CLAUDE.md is an instructions file published in the GitHub repository jayminwest/mulch (336 stars, last pushed 2d ago), licensed MIT. It adds 3,557 tokens to every session, about $0.0178 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.