agentmods.dev

claude-crawl CLAUDE.md

claude-crawl CLAUDE.md is an instructions file for coding agents from hex/claude-crawl. It costs 761 tokens per session, scanned A, original, MIT.

Instructions for documenting a Claude Code work session and restoring its context later.

In plain words
What is it for?
Resuming documented sessions, recording project findings and changes, and keeping scripts, configuration files, and other artifacts organised.
Why use it?
They tell the agent which session files to read and how to track changes, discoveries, summaries, and created files.

Instructions file

not rated 1 5mo ago A scan 761 tokens original MIT
View the source file hex/claude-crawl
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/hex/claude-crawl/claude-md
Clone the repo
git clone --depth 1 https://github.com/hex/claude-crawl

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 claude-crawl CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hex/claude-crawl/claude-md.svg)](https://agentmods.dev/instructions/hex/claude-crawl/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hex/claude-crawl/claude-md"><img src="https://agentmods.dev/badge/instructions/hex/claude-crawl/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 761 This file is loaded in full into every session.
When invoked 761 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 $0.00761 $0.00761
Opus 5 $0.00380 $0.00380
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 3d ago against content hash 29324e463762, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-crawl 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 · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Documentation Protocol

This is a Claude Code session managed by the cs tool. Session metadata lives in the .cs/ directory. The session root is your workspace for project files.

Session Files - READ THESE ON RESUME

When resuming this session, read the following files to restore context:

  1. .cs/summary.md - If exists, read first for previous session overview
  2. .cs/README.md - Session objective, environment, and outcome
  3. .cs/discoveries.md - Recent findings, observations, and ideas
  4. .cs/discoveries.compact.md - If exists, condensed historical findings
  5. .cs/changes.md - Modifications and fixes made
  6. .cs/artifacts/MANIFEST.json - List of tracked artifacts

Note: Historical discoveries are archived to .cs/discoveries.archive.md and condensed into .cs/discoveries.compact.md. Only read the archive if you need full detail on a specific past finding.

Artifact Auto-Tracking

Scripts and configuration files you create are automatically saved to .cs/artifacts/:

  • Scripts: .sh, .bash, .zsh, .py, .js, .ts, .rb, .pl
  • Configs: .conf, .config, .json, .yaml, .yml, .toml, .ini, .env

When you use the Write tool for these file types, they are automatically redirected to the .cs/artifacts/ directory and tracked in MANIFEST.json.

Documentation Discipline

Update the markdown documentation files throughout the session:

  1. Start of session: Fill in .cs/README.md objective and environment
  2. As you work: Update .cs/discoveries.md with findings and .cs/changes.md with modifications
  3. End of session: Complete the .cs/README.md outcome section

Treat these files as a lab notebook - document as you go, not just at the end.

Summary Command

When the session is complete, use the /summary command to generate an intelligent summary of the entire session. This will create a .cs/summary.md file synthesizing all documentation.

Secure Secrets Handling

Sensitive data is automatically detected and stored securely (macOS Keychain, Windows Credential Manager, or encrypted file):

Read the full file on GitHub · 76 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 · 76 lines · 761 tokens per session scan A 29324e463762

Subscribe to this mod's changes

claude-crawl CLAUDE.md is an instructions file published in the GitHub repository hex/claude-crawl (1 stars, last pushed 5mo ago), licensed MIT. It adds 761 tokens to every session, about $0.0038 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.

Memory and contextclaude-codeclaude-code-plugincloudflarefirecrawljinaweb-crawling
Related

Other instructions, from other repositories

agy-plugin-cc CLAUDE.md

Instructions for Vit129/agy-plugin-cc, covering agy-plugin-cc — claude code guide, agent memory, global-first rule, project context (auto-loaded every session) and project summary.

Vit129/agy-plugin-cc · 733 tokens

claudemd CLAUDE.md

Instructions for sdsrss/claudemd, covering code graph (repo-wide ast index) and claude-mem-lite — persistent memory.

sdsrss/claudemd · 691 tokens

claude-obsidian-chronicle CLAUDE.md

Claude Code instructions for takashito/claude-obsidian-chronicle, covering claude.md, what this is, architecture: three triggers → one writer, key mechanisms in session-summary.sh and transcript resolution in done-runner.sh.

takashito/claude-obsidian-chronicle · 1,896 tokens

BorisChernyClaudeMarkdown CLAUDE.md

Claude Code instructions for maximus0411/BorisChernyClaudeMarkdown, covering workflow orchestration, 1. plan mode default, 2. subagent strategy to keep main context window clean, 3. self-improvement loop and 4. verification before done.

maximus0411/BorisChernyClaudeMarkdown · 528 tokens

ai-handoff AGENTS.md

AGENTS.md instructions for Nazzero/ai-handoff, a project described as: Structured handoff documents for AI coding agents. Type /handoff to generate session summaries for seamless AI-to-AI continuity.

Nazzero/ai-handoff · 75 tokens

claude-neo4j-mem AGENTS.md

AGENTS.md instructions for troglodyte/claude-neo4j-mem, a project described as: Claude Neo4j memory plugin, in the manner of claude-mem.

troglodyte/claude-neo4j-mem · 9 tokens