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/updatenpx skills add crisandrews/ClawCode --skill updategit 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 | $0.00045 | $0.01607 |
| Opus 5 | $0.00023 | $0.00804 |
| Sonnet 5 | $0.00009 | $0.00321 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
update scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/agent:update — Check for new versions
Detect whether new versions of Claude Code (@anthropic-ai/claude-code) or ClawCode (this repo) are available, and surface the safe update procedure for each. Designed for users running ClawCode as a long-running daemon, where Claude Code's in-process auto-updater is disabled (see lib/service-generator.ts — Environment=DISABLE_AUTOUPDATER=1) and updates have to be applied explicitly.
When to use
- User asks
/agent:update,/update, "check for updates", "are there updates", etc. - Heartbeat skill calls in silent-check mode (see
templates/HEARTBEAT.md). - Before applying any change to the running service — knowing the upstream version helps decide whether to bundle with an update.
Steps
-
Detect current versions. Run all three in parallel (independent reads):
# Claude Code installed binary CC_INSTALLED=$(claude --version 2>/dev/null | awk '{print $1}') # ClawCode local repo HEAD PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(pwd)/ClawCode}" CW_LOCAL=$(git -C "$PLUGIN_ROOT" rev-parse --short HEAD 2>/dev/null) CW_LOCAL_TAG=$(git -C "$PLUGIN_ROOT" describe --tags --abbrev=0 2>/dev/null || echo "no-tag") -
Detect available versions. Network calls — be tolerant of failures (no network, npm flake, GitHub down):
# Claude Code latest on npm CC_LATEST=$(npm view @anthropic-ai/claude-code version 2>/dev/null) # ClawCode latest tag and HEAD on upstream git -C "$PLUGIN_ROOT" fetch upstream --tags 2>/dev/null CW_UPSTREAM_HEAD=$(git -C "$PLUGIN_ROOT" rev-parse --short upstream/main 2>/dev/null) CW_UPSTREAM_TAG=$(git -C "$PLUGIN_ROOT" describe --tags --abbrev=0 upstream/main 2>/dev/null || echo "no-tag")If any value is empty, treat that side as "unknown" rather than failing the whole check.
-
Compare and decide. Two boolean signals:
CC_UPDATE_AVAILABLEandCW_UPDATE_AVAILABLE.- Claude Code:
CC_UPDATE_AVAILABLE=1ifCC_INSTALLEDandCC_LATESTare both set and not equal. - ClawCode:
CW_UPDATE_AVAILABLE=1ifCW_LOCAL_TAGandCW_UPSTREAM_TAGare both set, neither isno-tag, and they differ (i.e. upstream has cut a newer release tag). Plain commits onupstream/main(docs, chore, ci) do NOT trigger an update notification; otherwise routine upstream activity would teach users to ignore the pings.
- Claude Code:
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 · 108 lines · 45 tokens per session scan A 32cecbdb1537
update is a skill published in the GitHub repository crisandrews/ClawCode (62 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 1,607 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.