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/jayminwest/mulch/claude-mdgit clone --depth 1 https://github.com/jayminwest/mulchWrote 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/jayminwest/mulch/claude-md)<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>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 | $0.03557 | $0.03557 |
| Opus 5 | $0.01778 | $0.01778 |
| Sonnet 5 | $0.00711 | $0.00711 |
| Haiku 4.5 | $0.00356 | $0.00356 |
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.
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 primeoutputs 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).
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 · 210 lines · 3,557 tokens per session scan A 24314442aa8f
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.
Other instructions, from other repositories
wife AGENTS.md
Instructions for ma-nucho-pro/wife, covering if the user wants to install it, if the user wants to change something and rules that are not negotiable.
mnemo-mcp AGENTS.md
Instructions for sshisto/mnemo-mcp, covering agents.md - mnemo-mcp, build / lint / test commands, run a single test file, run a single test class and run a single test function.
SiftMarks CLAUDE.md
Instructions for Lling0000/SiftMarks, covering claude.md, commands, architecture, the four entry points share one database and package layering (lower depends on higher).
task-orchestrator CLAUDE.md
Instructions for jpicklyk/task-orchestrator, covering project: mcp task orchestrator, build commands, docker (most common), architecture and modes of operation.
Project-AMBER AGENTS.md
Instructions for JJHbrams/Project-AMBER, covering agent orchestration, roles and non-negotiable rules.
SiftMarks AGENTS.md
Instructions for Lling0000/SiftMarks, covering siftmarks agent notes, project shape, commands, current caveats and working rules.