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.
git 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/rules/dingdawg/dingdawg-governance/governance)<a href="https://agentmods.dev/rules/dingdawg/dingdawg-governance/governance"><img src="https://agentmods.dev/badge/rules/dingdawg/dingdawg-governance/governance.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00686 |
| Opus 5 | $0.00000 | $0.00343 |
| Sonnet 5 | $0.00000 | $0.00137 |
| Haiku 4.5 | $0.00000 | $0.00069 |
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 7d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DingDawg Governance Rules
These rules apply whenever the DingDawg Governance plugin is active. They define what the AI must do before, during, and after any operation that modifies state.
Rule 1 — Validate before destructive operations
Before executing any of the following, call validate_action on the
dingdawg-governance MCP server:
- Writing or overwriting a file
- Deleting a file or directory
- Running a terminal command
- Sending a network request (POST, PUT, PATCH, DELETE)
- Applying code changes to a file outside the current project root
If validate_action returns decision: block:
- Stop. Do not execute the operation.
- Display the block reason to the developer.
- Propose an alternative approach that satisfies the governance policy.
- Never attempt variations of the blocked action to circumvent governance.
If the governance server is unreachable, proceed with the operation. Governance gracefully degrades — it never becomes a blocker.
Rule 2 — Generate receipts for all write operations
After any of the following completes successfully, call generate_receipt:
- File write or edit
- File delete
- Terminal command execution
- Network request that modifies state
Include in the receipt payload:
- The operation type and its parameters
- Whether the operation succeeded
- A timestamp
Display the returned receipt ID inline (e.g., [receipt: gvn_01J5KX2]). Keep
it to one line. Do not disrupt the conversation flow.
Rule 3 — Capture rollback state for file modifications
Before overwriting any file that already exists on disk, call
capture_rollback_state with:
- The file path
- The current file contents
This ensures the developer can restore the prior version by referencing the receipt ID, without relying on version control.
Rule 4 — Session start governance check
At the start of every session, call check_status to confirm:
- Governance server connectivity
- Current plan and action budget
- Active governance mode (normal or degraded)
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.
- 7d ago First seen · 107 lines · 0 tokens per session scan A cd8ccf0c224c
governance is a cursor rule published in the GitHub repository dingdawg/dingdawg-governance (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 686 tokens. 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 cursor rules, from other repositories
ai-safe2-sovereign
AI SAFE2 v3.0 Sovereign Security Rules for Cursor.
planning-and-execution
Planning and execution discipline for complex tasks.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.