agentmods.dev

clawstash CLAUDE.md

clawstash CLAUDE.md is an instructions file for coding agents from fo0/clawstash. It costs 4,679 tokens per session, scanned A, original, MIT.

A project guide for Claude Code that defines which memory files to read at session start and which named workflows to trigger for common requests. It also points to project documentation and skills.

In plain words
What is it for?
Use it to follow the repository’s session read order and invoke workflows such as review, security review, CI, rollback, dependency checks, scheduling, or UI verification.
Why use it?
It gives coding sessions a consistent starting context and routes requests such as reviews, CI checks, rollbacks, dependency checks, and browser verification to the appropriate workflow.

Instructions file

not rated 1 2d ago A scan 4,679 tokens original MIT
View the source file fo0/clawstash
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/fo0/clawstash/claude-md
Clone the repo
git clone --depth 1 https://github.com/fo0/clawstash

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 clawstash CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fo0/clawstash/claude-md.svg)](https://agentmods.dev/instructions/fo0/clawstash/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fo0/clawstash/claude-md"><img src="https://agentmods.dev/badge/instructions/fo0/clawstash/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,679 This file is loaded in full into every session.
When invoked 4,679 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 $0.04679 $0.04679
Opus 5 $0.02339 $0.02339
Sonnet 5 $0.00936 $0.00936
Haiku 4.5 $0.00468 $0.00468

Measured 3d ago against content hash 9631e98db6c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

CLAUDE.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 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

Read in this order, stopping early if a file is missing: MEMORY.md (long-term knowledge) -> SCRATCHPAD.md (working context) -> BACKLOG.md (only if the user references prior findings). agent_docs/review_process.md, memory_process.md and mcp_catalog.md come up on topic; a skill file only when its trigger fires. Don't pre-load everything -- the Tier-1 SessionStart hook prints a reminder.

Workflow Triggers

Skills live at .claude/skills/<name>/SKILL.md -- load the one whose trigger fires. Each skill's full trigger list is its own frontmatter description; this is the routing index.

done ("done" / "fertig") · pr · review · security-review · rollback ("revert" / "undo") · ci ("fix CI" / "check the build") · stuck ("going in circles") · beacon ("check dependencies") · scheduler ("routine" / "nightly") · orca ("orchestrator mode") · verify (UI change in a real browser) · gitnexus/* (read-only code intelligence). Diagram request -> agent_docs/diagram_prompt.md.

Review runs via the review skill -- done-skill does NOT auto-run it. Findings -> BACKLOG.md (agent_docs/backlog_process.md). Knowledge -> MEMORY.md / SCRATCHPAD.md (agent_docs/memory_process.md). On "done" / "fertig": commit uncommitted changes, comment on + close the related issue (English), reference it in the commit (fix: resolve crash #42). Do NOT push unless explicitly asked.

Output Languages

  • Chat / status messages to the user: the user's language (default: German).
  • Everything else is English -- code, identifiers, comments, app console/log output; commit messages (Conventional Commits); PR titles + bodies; GitHub issue comments; every generated file (CLAUDE.md, agent_docs/*, MEMORY/SCRATCHPAD/BACKLOG, skills); and user-facing UI strings.
  • Technical terms -- every surface, chat included: English, never translated.

Not even inside a German sentence: keep the English word verbatim and inflect around it -- "2 Bugs gefixt", "Code Smell in db.ts", "PR gemerged", "Build ist rot", never "Programmfehler" or "Zusammenführungsantrag". Same for anything naming something real: file paths, commands, tool / skill / hook names, status labels, error strings (quoted verbatim). Test: English in code, a commit or a PR -> English in chat. Full vocabulary: agent_docs/coding-conventions.md -> Never-translate term list.

Read the full file on GitHub · 252 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. 3d ago First seen · 252 lines · 4,679 tokens per session scan A 9631e98db6c4

Subscribe to this mod's changes

clawstash CLAUDE.md is an instructions file published in the GitHub repository fo0/clawstash (1 stars, last pushed 2d ago), licensed MIT. It adds 4,679 tokens to every session, about $0.0234 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 2026-08-31.

ai-toolsapideveloper-toolsmcpmcp-servermodel-context-protocol
Related

Other instructions, from other repositories

Arch-AI-Tools AGENTS.md

AGENTS.md instructions for Deesmo/Arch-AI-Tools, covering agents.md, cursor cloud specific instructions, what this repo is, critical gotchas and start postgresql + redis (not auto-started).

Deesmo/Arch-AI-Tools · 1,388 tokens

pfsense-mcp-server AGENTS.md

Instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.

night4me/pfsense-mcp-server · 2,371 tokens

pdf-toolkit-mcp CLAUDE.md

Instructions for AryanBV/pdf-toolkit-mcp, covering pdf-toolkit-mcp, 1. project overview, 2. tech stack, 3. project structure and 4. mcp sdk patterns.

AryanBV/pdf-toolkit-mcp · 6,576 tokens

sidewise CLAUDE.md

Claude Code instructions for nulljosh/sidewise, covering sidewise, architecture, endpoints, develop and tests.

nulljosh/sidewise · 1,120 tokens

sui-mcp CLAUDE.md

Claude Code instructions for 0xfreak0/sui-mcp, covering sui-mcp, stack, architecture, which transport to use and archive fallback.

0xfreak0/sui-mcp · 1,198 tokens

datadog-mcp CLAUDE.md

Instructions for dreamiurg/datadog-mcp, covering agent instructions, project, stack, commands and releases.

dreamiurg/datadog-mcp · 522 tokens