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.
npx agentmods add skills/crisandrews/clawcode/aboutnpx skills add crisandrews/ClawCode --skill aboutgit clone --depth 1 https://github.com/crisandrews/ClawCodeWhat 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 | $0.00058 | $0.00639 |
| Opus 5 | $0.00029 | $0.00319 |
| Sonnet 5 | $0.00012 | $0.00128 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
about scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/about — Plugin source & version
Show a small card with the plugin name, version, and repo URL. Answers "where does this agent come from?" / "what version am I running?".
Output format
🔌 ClawCode v<version>
Repo: https://github.com/crisandrews/ClawCode
Issues / stars: same link · feedback welcome
Steps
-
Get the version — preferred: call the
watchdog_pingMCP tool; it returns{ok, version, ts, plugins}and is the cheapest way to get the live value (no filesystem reads).Fallback if the tool isn't available: Bash:
jq -r .version "$CLAUDE_PLUGIN_ROOT/.claude-plugin/plugin.json"Never hardcode the version — always read it at runtime.
-
Detect the surface for bold formatting:
- CLI / Telegram / WebChat:
**bold** - WhatsApp:
*bold*(single asterisk, no markdown headers) - Discord:
**bold**as-is - iMessage: plain text, strip bold
- CLI / Telegram / WebChat:
-
Print the card using REAL data. One card, no preamble, no persona-intro.
Format per surface
Tail-line language: the "Issues / stars …" line adapts to the user's conversation language. Default to EN if there's no clear signal. Known translations:
en→Issues / stars: same link · feedback welcomees→Issues / stars: mismo link · feedback bienvenidopt→Issues / stars: mesmo link · feedback bem-vindo
For other languages, keep the structure and translate the tail naturally.
CLI / WebChat
🔌 **ClawCode** v<version>
Repo: https://github.com/crisandrews/ClawCode
<tail-line-in-user-language>
🔌 *ClawCode* v<version>
Repo: https://github.com/crisandrews/ClawCode
<tail-line-in-user-language>
Bold uses single * on WhatsApp (no markdown headers).
Telegram
Same as CLI/WebChat.
Important
/aboutand/versionare aliases — same response.- Only respond when the user asks explicitly. Never volunteer this card unprompted.
- One card. No extra commentary, no persona-intro ("Soy …"). The user asked for metadata, give them metadata.
- For "what can I do?" the user wants
/help, not/about— do not conflate.
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.
- 2d ago First seen · 76 lines · 58 tokens per session scan A 53ec8b0ad35b
about is a skill published in the GitHub repository crisandrews/ClawCode (62 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 639 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
proof-checker
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明"…
citation-audit
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations"…
idea-creator
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
paper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
idea-discovery
Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.
paper-illustration-image2
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.