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/newnpx skills add crisandrews/ClawCode --skill newgit 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 | $0.00054 | $0.00866 |
| Opus 5 | $0.00027 | $0.00433 |
| Sonnet 5 | $0.00011 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
new scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/new — Start a new session
Save the current session to memory, then mark it as "reset pending" so the next message triggers a fresh greeting (like OpenClaw).
How this works (architecture)
OpenClaw's /new generates a new session ID and runs a greeting prompt on the next turn. In Claude Code, skills CANNOT invoke native /clear. Instead, we:
- Save the current session to
memory/YYYY-MM-DD.md - Write a marker
.session-reset-pendingwith the greeting prompt - Respond with a brief "new session" acknowledgement
- On the next message, the agent detects the marker, delivers the greeting, deletes the marker
This is the honest simulation of a session reset when native /clear is not invokable.
Steps
-
Detect surface (CLI vs messaging).
-
Summarize the current session to memory:
DATE=$(date +%Y-%m-%d) TIME=$(date +%H:%M)Append to
memory/$DATE.md:## Session summary (<TIME>) — before /new - <key point> - <key point> ### Open items - <pending>If the session was trivial, skip this step but still do the next one.
-
Write the reset marker:
cat > .session-reset-pending << 'EOF' A new session was started via /new or /reset. Greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning. EOF(This is the EXACT prompt from OpenClaw's session-reset-prompt.ts)
-
Respond briefly per surface:
CLI
🔄 New session started. Summary saved to memory/<DATE>.md.
Send a message to receive the welcome greeting.
(Or if you also want to clear the REPL context, run /clear afterward.)
🔄 *Session reset*. Send a message and I'll greet you again 👋
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 · 96 lines · 54 tokens per session scan A 93151f54f960
new is a skill published in the GitHub repository crisandrews/ClawCode (62 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 866 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.