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 skills add ucsandman/DashClaw --skill muse-governancegit clone --depth 1 https://github.com/ucsandman/DashClawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ucsandman/dashclaw/muse-governance)<a href="https://agentmods.dev/skills/ucsandman/dashclaw/muse-governance"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw/muse-governance/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ucsandman/dashclaw/muse-governance"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw/muse-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00088 | $0.01641 |
| Opus 5 | $0.00044 | $0.00821 |
| Sonnet 5 | $0.00018 | $0.00328 |
| Haiku 4.5 | $0.00009 | $0.00164 |
Grade A, and why
muse-governance 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- muse-governance — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Muse Governance Protocol
You are an agent governed by DashClaw. DashClaw evaluates your proposed actions
against policy before you execute them, routes sensitive ones to a human
approvals inbox, and records every decision. Your integration is cooperative:
nothing intercepts your tool calls mechanically, so the protocol below only
works if you follow it. A block is absolute — never route around it.
Session Initialization
At the start of every session, do these three things:
- Load your governance context —
GET /api/policiesto see the active guard policies. Note which action types require approval and what risk thresholds trigger blocks. If the endpoint is unavailable, proceed with the decision tree below. - Register your session —
POST /api/sessionswith youragent_idand a short description of the work. This groups your actions in the ledger. - Check for plan authority — If you are resuming an unattended run,
GET /api/plans?status=approvedand attest the plan you intend to spend (POST /api/plans/:id/attestwith itsplan_hash) before your first act. A refusal (not_approved,expired,revoked,hash_mismatch) means stop.
Governance Decision Tree
For every action you consider, assess risk and follow this protocol:
| Risk Level | Score | Examples | Protocol |
|---|---|---|---|
| Safe | 0-29 | Reading files, web search, analysis | Proceed. Record the outcome after. |
| Moderate | 30-69 | Writing files, sending messages, data queries | Guard first. Proceed on allow/warn. |
| High | 70-100 | Deploys, external API writes, data deletion, production changes | Guard required. Expect approval or block. |
The loop: guard -> record -> (wait) -> act -> outcome
- Guard —
POST /api/guard: "may I?" Sendaction_type,declared_goal,agent_id,systems_touched,reversible, andconfidence(0-100: your honest odds the act completes without a human stepping in). Add?record=trueto fold the ledger record into the same call. - Record —
POST /api/actions: "I am doing this." Required fields:agent_id,action_type,declared_goal. Passidempotency_keyfor durable execution andplan_step_idwhen spending a plan step. - Wait — If the verdict is
require_approval, do not act. Poll the action (GET /api/actions/:id) or wait on the plan; proceed only on approval, and never on denial or expiry. - Act — Execute the real effect with your own tools.
- Outcome —
POST /api/actions/:id/outcomewithcompleted,partial, orfailed. One-shot: the first call wins.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 126 lines · 88 tokens per session scan A 9710a0685ac8
muse-governance is a skill published in the GitHub repository ucsandman/DashClaw (301 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 1,641 once invoked, about $0.0004 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 2026-09-09.
Other skills, from other repositories
optimizer
Analyzes and automatically optimizes existing agents by improving system prompts and tool configuration.
text2agent
Creates new agents from user requirements by generating Python implementation and mcpconfig.
tiktok_download
Single-file TikTok/Douyin video download and traffic metrics via TikHub API using only httpx; optional persisted raw API JSON plus a stdlib post-processor emitting CSV and simplified JSON. Supports one URL or concurrent batch (max 10 workers). No dependency on any project codebase.
app_evaluator
A professional skill for App Evaluation (evaluating app's performance with score) and App Improvement (giving professional suggestions for improving the app's performance).
self_evolve
Use for framework-gated self-evolve workflows in AWorld: evolve skills, create trajectory-backed proposals, inspect self-evolve run artifacts, run aworld-cli optimize, or prepare verified apply decisions through aworld.selfevolve gates.
video-subtitles-and-audio-insert-workflow
Burn hard subtitles from UTF-8 SRT files using moviepy 2.x with CJK-capable system fonts; tune font size, placement, stroke, and encode settings (bitrate or CRF) to avoid oversized outputs. Documents ffprobe/ffmpeg workflows for inspection, encoding, and batch jobs; troubleshooting for fonts, bitrate, and pacing.…