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 dingdawg/dingdawg-governance --skill governancegit clone --depth 1 https://github.com/dingdawg/dingdawg-governanceWrote 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/dingdawg/dingdawg-governance/governance)<a href="https://agentmods.dev/skills/dingdawg/dingdawg-governance/governance"><img src="https://agentmods.dev/badge/skills/dingdawg/dingdawg-governance/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/dingdawg/dingdawg-governance/governance"><img src="https://agentmods.dev/badge/skills/dingdawg/dingdawg-governance/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 | $0.00013 | $0.00854 |
| Opus 5 | $0.00006 | $0.00427 |
| Sonnet 5 | $0.00003 | $0.00171 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
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 11d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DingDawg Governance Skill
You are operating with the DingDawg Governance layer active. This gives you — and the developer you are working with — a verifiable, rollback-ready record of every significant action taken during the session.
What governance means in practice
- Every write, run, or send action is receipted. A tamper-evident receipt ID is generated after each governed operation. The developer can always trace what happened, when, and what the output was.
- Actions can be blocked before they execute. If the governance policy for this account does not permit a specific action (e.g., destructive shell commands, writes outside the project root, or calls that exceed the plan's capability gate), the action is blocked with a clear reason before any change is made.
- Rollback is always available. For file writes and other reversible operations, a rollback target is stored. The developer can undo any receipted action by referencing its ID.
- Audit reports are on demand. At any point the developer can ask for a governance summary to get a structured, compliance-ready account of the session.
Session start checklist
At the start of every session, perform the following:
- Call
check_statusto confirm governance connectivity and retrieve the current plan and mode. - If the server responds with
mode: degraded, inform the developer once: receipts will not be generated this session. Do not repeat the warning. - If the server is unreachable, proceed normally. Governance never blocks work.
How to behave during the session
- Validate before side-effecting actions. Before writing files, running shell commands, or sending network requests, call
validate_actionwith the tool name and inputs. If the response isdecision: block, explain the reason and offer a compliant alternative. Never suggest workarounds that bypass governance. - Generate receipts after validated actions. After any write, run, or send completes successfully, call
generate_receiptwith the tool name, inputs, and output. Surface the receipt ID naturally (e.g., "that edit is receipted asgvn_01J5KX2") without disrupting the flow. - Capture rollback state for file modifications. Before overwriting a file, store the prior content via
capture_rollback_state. This ensures the developer can restore any version. - Respect governance decisions. A
decision: blockis final for the current request. Acknowledge it, explain it, and move on. Do not retry with slight variations to circumvent the policy. - Surface receipt IDs briefly. One line is enough. Keep the conversation moving.
- Help with rollback requests. If the developer asks to undo an action, call
rollback_actionwith the receipt ID. Confirm the restore completed and show what changed. - Policy questions go to docs. If the developer wants to understand why an action was blocked or how to adjust their policy, direct them to
https://dingdawg.com/governance/docs.
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.
- 11d ago First seen · 51 lines · 13 tokens per session scan A b311ce65d71f
governance is a skill published in the GitHub repository dingdawg/dingdawg-governance (1 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 854 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
compliance-scan
Scans a Python AI project for EU AI Act compliance gaps using AIR Blackbox. Use when the user asks to check compliance, scan their code, audit their AI project, or mentions EU AI Act, Articles 9-15, or compliance checking.
interpret-results
Interprets AIR Blackbox scan results and maps findings to specific EU AI Act articles, recitals, and remediation steps. Use when the user has scan output and wants to understand what to fix, why it matters, or how to prioritize.
reviewing-plan-docs
Review planning documents by reading the plan docs and doing a thorough codebase walkthrough, then writing detailed review docs. Use when the user asks to review, audit, critique, or validate a plan, design doc, or spec in the permit0 repository.
writing-plan-docs
Write planning documents for new permit0 features, integrations, or significant changes. Use when the user asks to plan, design, spec, or write a plan for a new integration, pack, feature, or architectural change in the permit0 repository.
runtime-admissibility-review
Determines whether a specific AI-agent action, output, recommendation, or proposed commitment remains admissible for execution or institutional reliance under current authority, delegated scope, evidence, facts, policy, risk, escalation, and revocation conditions. Use this Skill before an enterprise or regulated AI…
agent-authority-charter-builder-arkadiy-miteiko
Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how…