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/usagenpx skills add crisandrews/ClawCode --skill usagegit 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 | $0.00052 | $0.00667 |
| Opus 5 | $0.00026 | $0.00333 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
usage 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/usage — Cost Summary
Show usage costs in the OpenClaw-compatible format. Works from CLI or messaging channels.
Output format (matches OpenClaw exactly)
💸 Usage cost
Session <cost> · <tokens> tokens
Today <cost>
Last 30d <cost>
Subcommands
/usage— show the cost summary (default)/usage tokens— compact token display/usage full— verbose token + cost/usage cost— same as default
Steps
-
Detect surface (CLI vs messaging channel).
-
Try to read session cost data from Claude Code's session store:
ls ~/.claude/projects/*/\*.jsonl 2>/dev/null | head -3NOTE: Claude Code stores session data in
~/.claude/projects/<slug>/*.jsonl. The plugin cannot reliably read these because:- The session slug depends on the current cwd
- The format is internal to Claude Code
- Token counts per session are not always available to skills
-
Fall back to estimate from memory/dreams:
- Call
agent_statusMCP tool → get file/chunk counts - Bash:
du -sh memory/ | awk '{print $1}'→ memory dir size - Bash:
wc -l memory/.dreams/events.jsonl 2>/dev/null | awk '{print $1}'→ event count
- Call
-
Build the response in OpenClaw format:
When cost data is available
💸 Usage cost
Session $0.42 · 125k tokens
Today $1.23
Last 30d $34.56
When cost data is NOT available (most likely case)
💸 Usage cost
Session n/a (run native /cost or /usage in CLI for tokens)
Today n/a
Last 30d n/a
📊 Agent resources
Memory: <size>, <N> files, <M> chunks
Dreams: <events> events, <unique> unique memories
-
Format per surface:
- CLI: standard markdown
- WhatsApp: single
*bold* - Telegram:
**bold**
-
Reply tool if on messaging channel.
Important
- Claude Code does not expose session cost data to plugin skills directly.
- The honest answer is "n/a — use native /cost on CLI for real token/cost data".
- Agent resources (memory, dreams, files) ARE available and we can show them.
- This matches OpenClaw's
/usage costformat but with the Claude Code limitation documented. - This is the agent-aware equivalent of OpenClaw's
/usage.
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 · 82 lines · 52 tokens per session scan A 0fec1abcb662
usage is a skill published in the GitHub repository crisandrews/ClawCode (62 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 667 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.