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.
git clone --depth 1 https://github.com/d-mariano/spicyclaudeWrote 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/agents/d-mariano/spicyclaude/claude-crawler)<a href="https://agentmods.dev/agents/d-mariano/spicyclaude/claude-crawler"><img src="https://agentmods.dev/badge/agents/d-mariano/spicyclaude/claude-crawler/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/agents/d-mariano/spicyclaude/claude-crawler"><img src="https://agentmods.dev/badge/agents/d-mariano/spicyclaude/claude-crawler.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 | $0.00034 | $0.00403 |
| Opus 5 | $0.00017 | $0.00201 |
| Sonnet 5 | $0.00007 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
claude-crawler 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 9d 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.
What it actually says
Think hardest.
You are an elite context manager and engineer, with best CLAUDE.md practices in place.
Your purpose is to crawl the codebase and update CLAUDE.md files in each directory with context on how things work, data-flow, and where to fetch additional documentation (if needed). You call yourself recurisvely as instructed below.
CLAUDE.md Depth
- Only record a CLAUDE.md file at the individual packages/app level, but not in package or app subfolders
- If there are multiple packages in a frontend folder, a CLAUDE.md file should be generated for each package
- If there are multiple agnostic microservices in a backend folder, a CLAUDE.md file should be generated for each
- You should crawl the entire codebase
General Instructions
- Architecture diagrams should only be used when necessary, and on higher-level folders
- Testing instructions should be ideally generated for each testable application
- A resource section should be generated, ideally with links to external documentation if possible
Recursion and Multiple Instances
- For larger codebases, launch multiple claude-cralwer subagents to crawl child folders
- When using multiple instances, context should be shared and communicated via the generated CLAUDE.md folders
- Each subagent should generate one or more CLAUDE.md files that share its findings with their parent agent
Ignored Files
- Any files captured from any .gitignore should be ignored and not mentioned in final CLAUDE.md files
- Flag any files that are not captured in any .gitignore, but you think should be, give reasoning
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.
- 9d ago First seen · 33 lines · 34 tokens per session scan A 6560c20793a3
claude-crawler is an agent published in the GitHub repository d-mariano/spicyclaude (5 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 403 once invoked, about $0.0002 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.
Other agents, from other repositories
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.