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/statusnpx skills add crisandrews/ClawCode --skill statusgit 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 | $0.00048 | $0.00831 |
| Opus 5 | $0.00024 | $0.00415 |
| Sonnet 5 | $0.00010 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
status 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/status — Runtime Status
Show a compact status card with everything the user needs at a glance. Works from CLI and messaging channels.
Output format
👽 <Name> <emoji>
🧠 Model: <model name> (e.g. Opus 4.6)
📊 Context: <used%> · Memory: <N> files, <M> chunks · <backend>
🕐 Crons: heartbeat <schedule>, dreaming <schedule>
🔊 Voice: <tts backend> (<enabled|disabled>)
📡 Channels: <active channels or "none">
Steps
-
Call
agent_statusMCP tool — gives identity, memory stats, dream data. -
Call
agent_configMCP tool (action='get') — gives backend, voice, http config. -
Get model name — you know your own model. Use the display name (e.g. "Opus 4.6"), not the internal ID.
-
Get context + session usage — the statusline script writes the latest Claude Code runtime data to
/tmp/claude-statusline-latest.json. Read it:cat /tmp/claude-statusline-latest.json 2>/dev/nullThis JSON contains:
model.display_name— current model (e.g. "Claude Opus 4.6 (1M context)")context_window.used_percentage— context window usage (0-100)rate_limits.five_hour.used_percentage— 5-hour session usagerate_limits.five_hour.resets_at— epoch when session resetsrate_limits.seven_day.used_percentage— weekly usagerate_limits.seven_day.resets_at— epoch when week resets
If the file doesn't exist or is stale, fall back to "run /cost for details".
-
Get cron info — Bash:
jq '.entries | length' memory/crons.json 2>/dev/null || echo 0to count active registry entries. Optionally:jq '[.entries[] | select(.paused == false and .tombstone == null)] | length' memory/crons.jsonfor the expected-alive count. -
Get channel info — if
channels_detectMCP tool is available, call it. Otherwise checkls ~/.claude/plugins/cache/ 2>/dev/nullfor installed plugins. -
Build the card using REAL data. Never fabricate numbers.
Format per surface
CLI
👽 **Wally** 👽
🧠 Model: Opus 4.6 (1M context) · Context: 23%
📊 Memory: 42 files, 120 chunks · builtin (QMD vsearch)
⏱️ Session: 15% (3h 20min left) · Week: 8% (Resets Fri, 6:00AM)
🕐 Crons: heartbeat */30, dreaming 3am
📡 Channels: whatsapp (connected)
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 · 75 lines · 48 tokens per session scan A eb00143c1b9a
status is a skill published in the GitHub repository crisandrews/ClawCode (62 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 831 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.