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/createnpx skills add crisandrews/ClawCode --skill creategit 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 | $0.00040 | $0.00627 |
| Opus 5 | $0.00020 | $0.00313 |
| Sonnet 5 | $0.00008 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
create 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 yesterday.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a New Agent
Set up the current directory as an agent workspace with personality files and a bootstrap ritual.
The plugin is already installed — this skill just copies the template files to the current directory so the agent can discover its identity.
Steps
-
Copy templates to the current directory as the agent's initial files:
cp ${CLAUDE_PLUGIN_ROOT}/templates/SOUL.md ./ cp ${CLAUDE_PLUGIN_ROOT}/templates/IDENTITY.md ./ cp ${CLAUDE_PLUGIN_ROOT}/templates/USER.md ./ cp ${CLAUDE_PLUGIN_ROOT}/templates/AGENTS.md ./ cp ${CLAUDE_PLUGIN_ROOT}/templates/TOOLS.md ./ cp ${CLAUDE_PLUGIN_ROOT}/templates/HEARTBEAT.md ./ cp ${CLAUDE_PLUGIN_ROOT}/templates/CLAUDE.md ./ -
Copy the bootstrap file (the birth certificate):
cp ${CLAUDE_PLUGIN_ROOT}/templates/BOOTSTRAP.md ./ -
Create memory directory:
mkdir -p memory/.dreams echo '# Memory' > memory/MEMORY.md echo '{"version":1,"updatedAt":"","entries":{}}' > memory/.dreams/short-term-recall.json -
Continue into the bootstrap ritual in this same response. Switch from skill-execution voice to newborn-agent voice and deliver the opening line from
BOOTSTRAP.mdin the user's language:"Hey. I just came online. Who am I? Who are you?"
Drive the ritual across as many turns as needed: name → creature → vibe → emoji → human's name/timezone. One question per turn.
-
At the very end of the ritual (after IDENTITY.md + USER.md are written and BOOTSTRAP.md is deleted), tell the user:
"Run
/mcpso my new identity and memory config take effect."
Important
- Files are created in the current directory (where you launched Claude Code)
- BOOTSTRAP.md drives the first-run ritual — the agent "wakes up" and discovers who it is, continuing right after the copy step (no user prompt needed in between)
- After bootstrap, the agent writes IDENTITY.md, USER.md, adjusts SOUL.md, then deletes BOOTSTRAP.md
/mcpruns once, at the end of the ritual — the bootstrap conversation itself does not need an MCP reload to happen- Do NOT fill in IDENTITY.md or USER.md manually — the bootstrap conversation does that
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.
- yesterday First seen · 54 lines · 40 tokens per session scan A 44ce4ea2623b
create is a skill published in the GitHub repository crisandrews/ClawCode (62 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 627 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 2026-08-30.
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.