Borrowing it
Nothing to install: this file belongs to fo0/clawstash. 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/fo0/clawstash/main/CLAUDE.mdgit clone --depth 1 https://github.com/fo0/clawstashWrote 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/fo0/clawstash/claude-md)<a href="https://agentmods.dev/instructions/fo0/clawstash/claude-md"><img src="https://agentmods.dev/badge/instructions/fo0/clawstash/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/fo0/clawstash/claude-md"><img src="https://agentmods.dev/badge/instructions/fo0/clawstash/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 | $0.02913 | $0.02913 |
| Opus 5.5 | $0.01165 | $0.01165 |
| Sonnet 5.5 | $0.00583 | $0.00583 |
| Haiku 4.5 | $0.00291 | $0.00291 |
Grade A, and why
clawstash 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md -- Project Guide
Session Start -- Read Order
MEMORY.md -> SCRATCHPAD.md; BACKLOG.md only when prior findings come up; skip what is missing. agent_docs/* and skills load on demand, never up front.
Workflow Triggers
Skills (.claude/skills/<name>/SKILL.md): done ("done" / "fertig"; never auto-runs a review, and does not push unless asked) · pr · basic-review · basic-sec-review · rollback · ci (which workflows actually run: agent_docs/development-notes.md -> CI/CD) · stuck · beacon · verify (browser UI check) · scheduler (bare /loop: .claude/loop.md) · orca (/orca <objective>). Diagram -> agent_docs/diagram_prompt.md. Findings -> BACKLOG.md, knowledge -> MEMORY.md / SCRATCHPAD.md (agent_docs/backlog_process.md, memory_process.md).
Output Languages
Chat to the user: the user's language (default German) -- skill report shapes fix the structure, not the language -- technical terms English and never translated. Everything else English -- code, comments, log output, UI strings, commits (Conventional Commits), PRs, issues, every generated file. Term list: agent_docs/autonomy.md -> Never-translate term list.
Performance / Modes
Model: the session's, never pinned. Plan mode for non-trivial strategy only. Reference: agent_docs/autonomy.md -> Mode reference.
Caveman Mode -- chat compression (default full)
Chat, status and confirmations only -- never files, code, commits, PR bodies, issue comments. At full: drop filler, pleasantries, hedging and articles; fragments are fine for status lines. Shorten by selection, not compression: cut what would not change the reader's next move; no abbreviations, arrow chains or invented shorthand in any mode; code and error strings verbatim. Never compressed: the closing summary, security warnings, irreversible-action confirmations, the Handoff Prompt. caveman lite|full|ultra switches, stop caveman turns it off for the session. Full wording: agent_docs/autonomy.md -> Caveman Mode.
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 Changed · +12 tokens per session e6107eecf120
- 18d ago Changed · -2 tokens per session 19562dd2b244
- 19d ago Changed 064af9baf035
- 26d ago Changed · -13 lines · -531 tokens per session c6e4ca4e46eb
- 1mo ago Changed fa94a6668ca3
- 1mo ago Changed · -11 lines · -69 tokens per session e8587f60b26e
- 1mo ago Changed · -54 lines · -1,326 tokens per session 9e3ed6fafccb
- 1mo ago Changed · -10 tokens per session d4c477d7d568
- 1mo ago Changed · +23 tokens per session 295b3caf36ca
- 1mo ago First seen · 236 lines · 4,816 tokens per session scan A 5cc7f602d41d
clawstash CLAUDE.md is an instructions file published in the GitHub repository fo0/clawstash (1 stars, last pushed today), licensed MIT. It adds 2,913 tokens to every session, about $0.0117 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 2026-08-31.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.