Borrowing it
Nothing to install: this file belongs to receptron/mulmoterminal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/receptron/mulmoterminal/main/CLAUDE.mdgit clone --depth 1 https://github.com/receptron/mulmoterminalWrote 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/receptron/mulmoterminal/claude-md)<a href="https://agentmods.dev/instructions/receptron/mulmoterminal/claude-md"><img src="https://agentmods.dev/badge/instructions/receptron/mulmoterminal/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/receptron/mulmoterminal/claude-md"><img src="https://agentmods.dev/badge/instructions/receptron/mulmoterminal/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.08098 | $0.08098 |
| Opus 5.5 | $0.03239 | $0.03239 |
| Sonnet 5.5 | $0.01620 | $0.01620 |
| Haiku 4.5 | $0.00810 | $0.00810 |
Grade A, and why
mulmoterminal 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.
How it starts
The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — mulmoterminal
Working notes for AI coding agents in this repo. Human-facing docs (what it is, install, features, full API/architecture) live in README.md — read it for anything not covered here.
Stack & package manager
- TypeScript. Web UI: Vue 3 (Composition API) + Vite (
src/). Backend: Express + node-pty, run via tsx (server/). Shared code incommon/. - Package manager: yarn (yarn.lock). Use
yarn add; don't hand-edit package.json.
Run after changes
yarn format— Prettier..prettierignoreexcludes*.md, so Markdown is not reformatted.yarn lint— ESLint. There are two scripts and they are not interchangeable:lintpairs--cache-strategy metadatawith--concurrency auto, which is what makes an unchanged run cost 0 workers (auto counts only the files whose cached result is stale, and it can only do that undermetadata).lint:ciusescontentand no workers, becauseactions/checkoutrewrites every mtime — andcontentmakes auto count ALL files, so the two together spawn workers that find nothing to do. Numbers inplans/perf-lint-ci-local-split.md.yarn typecheck—vue-tsc -b, and it covers the whole repo: the roottsconfig.jsonreferences all five projects (app, node, server, and the two spec ones — including the specs colocated underserver/rather than intest/). Adding a project means adding it there too, or nothing type-checks it and CI will not tell you.yarn build—vue-tsc -b && vite build.yarn test— Vitest (test/**/*.spec.ts). Mock external APIs; tests must run without API keys.yarn dev— server + Vite together (local development).
Import a component at module scope, never inside a test
await import("…/Foo.vue") inside an it (or a helper an it awaits) pulls the component's
whole module graph through the transform, and the first test to reach it is billed that time
against testTimeout. On this repo that was 2132ms of loading against an 18ms mount — so the
file's first test looked 100x slower than its siblings, and on a loaded runner it was the one
that crossed 15s and went red (#1314). The test was never the slow part.
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.
- 3d ago Changed · +46 tokens per session 0d09c4bd0695
- 4d ago Changed · +19 lines · +346 tokens per session c60008087cf6
- 6d ago Changed · +15 tokens per session ded3846767ed
- 9d ago Changed · +2 lines · +53 tokens per session 31df1875f744
- 12d ago Changed · +2 lines · +51 tokens per session 38a081c81e11
- 14d ago Changed · +5 lines · +101 tokens per session f2882cc00c1a
- 16d ago Changed · +16 tokens per session 436b43d9ee3d
- 23d ago Changed · +7 lines · +155 tokens per session 839576697dd3
- 24d ago Changed · +12 lines · +277 tokens per session 0d1c38cf4322
- 26d ago First seen · 384 lines · 7,038 tokens per session scan A a87d7d8b2b50
mulmoterminal CLAUDE.md is an instructions file published in the GitHub repository receptron/mulmoterminal (245 stars, last pushed yesterday), licensed MIT. It adds 8,098 tokens to every session, about $0.0324 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.