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/channelsnpx skills add crisandrews/ClawCode --skill channelsgit 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 | $0.00081 | $0.01338 |
| Opus 5 | $0.00041 | $0.00669 |
| Sonnet 5 | $0.00016 | $0.00268 |
| Haiku 4.5 | $0.00008 | $0.00134 |
Grade B, and why
channels scanned grade B with 1 finding 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Key `runtime.status` values: `idle_other_instance` (lock held by another session — the main one), `logged_out` (re-link needed), `lock_error` (filesystem/PID-file problem). Never tell the user to run `/whatsapp:configure How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Channels — messaging status + launch
Diagnose messaging channel plugins and give the user the exact command to load them. This skill does NOT install channels (use /agent:messaging) or authenticate them (per-channel skills like /whatsapp:configure) — it reports state and hands back a launch command.
This is a CORE feature. See docs/channels.md for details.
Dispatch
| User says | Action |
|---|---|
/agent:channels or /agent:channels list |
Call channels_detect({ format: "table" }) and print card |
/agent:channels status [<name>] |
Call channels_detect({ format: "json" }), filter by name if given, format single channel |
/agent:channels launch |
Call channels_detect({ format: "launch" }) and print only the command |
/agent:channels launch --with-installed |
Call with includeInstalledOnly: true — includes installed-but-not-authenticated |
/agent:channels launch --skip-permissions |
Call with skipPermissions: true — adds the dangerous flag to the command (warn the user) |
List flow
- Call
channels_detect({ format: "table" }) - Print the returned text verbatim — it already has the table, next-steps hints, the launch command, and a ⚠️ Runtime block when a channel server is up but not delivering inbound (see Runtime warnings below)
- If any channels show
❌under Installed and the user is new, remind: "Install a channel with/agent:messaging <name>"
Status flow (single channel)
- Call
channels_detect({ format: "json" }) - Find the entry where
namematches (case-insensitive) - If not found, respond: "I don't track a channel called
<name>. Known channels: whatsapp, telegram, discord, imessage, slack, fakechat." - Otherwise print a compact block:
📡 <label>
kind: <development|official|integration>
installed: <✅ | ❌> (<detail>)
authenticated: <✅ | ❌ | ⏸️> (<detail>)
active: <❓ | ❌> (<detail>)
next: <setupHint>
- If the entry has a
runtimefield, surface it — see Runtime warnings.
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 · 88 lines · 81 tokens per session scan B 23d69fc00e20
channels is a skill published in the GitHub repository crisandrews/ClawCode (62 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 1,338 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). 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.
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
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.
paper-talk
End-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conference talks (NeurIPS / ICML / ICLR / VALSE / 投稿 talks). Trigger phrases: "做 talk", "做 PPT 全流程", "talk pipeline"…