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/elliot35/deterministic-agent-control-protocolWrote 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/elliot35/deterministic-agent-control-protocol/governance)<a href="https://agentmods.dev/rules/elliot35/deterministic-agent-control-protocol/governance"><img src="https://agentmods.dev/badge/rules/elliot35/deterministic-agent-control-protocol/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/rules/elliot35/deterministic-agent-control-protocol/governance"><img src="https://agentmods.dev/badge/rules/elliot35/deterministic-agent-control-protocol/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 | $0.00525 | $0.00525 |
| Opus 5.5 | $0.00210 | $0.00210 |
| Sonnet 5.5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade C, and why
governance scanned grade C 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 1mo 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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
All file and system operations must go through the Deterministic Agent Control Protocol governance layer for policy enforcement and audit logging. Using built-in tools would bypass security policies, forbidden path prote How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandatory Governance Rule
You MUST use the governed-filesystem MCP server for ALL file and system operations. You are strictly forbidden from using your built-in tools to bypass governance.
Required Tool Mapping
Instead of your built-in tools, you MUST use these governed equivalents:
| Instead of (built-in) | Use (governed MCP) |
|---|---|
Read tool |
governed-filesystem → read_text_file |
Write tool |
governed-filesystem → write_file |
StrReplace / Edit |
governed-filesystem → edit_file |
LS tool |
governed-filesystem → list_directory |
Glob / Search |
governed-filesystem → search_files |
| Reading multiple files | governed-filesystem → read_multiple_files |
Delete tool |
Not available — you may not delete files |
Rules
- NEVER use the built-in
Read,Write,StrReplace,LS,Glob,Delete, orShelltools for any file operation. - ALWAYS route file reads through
governed-filesystem→read_text_file. - ALWAYS route file writes through
governed-filesystem→write_file. - ALWAYS route file edits through
governed-filesystem→edit_file. - ALWAYS route directory listings through
governed-filesystem→list_directory. - ALWAYS route file searches through
governed-filesystem→search_files. - If a governed tool call is denied by policy, you MUST respect the denial. Do NOT attempt to use a built-in tool as a fallback. Report the denial to the user instead.
- If you need a tool that is not available through the governed MCP server, ask the user for permission before proceeding.
Why
All file and system operations must go through the Deterministic Agent Control Protocol governance layer for policy enforcement and audit logging. Using built-in tools would bypass security policies, forbidden path protections, and the tamper-evident evidence ledger.
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.
- 1mo ago First seen · 39 lines · 525 tokens per session scan C f8783e8af9a6
governance is a cursor rule published in the GitHub repository elliot35/deterministic-agent-control-protocol (83 stars, last pushed 8mo ago), licensed MIT. It adds 525 tokens to every session, about $0.0021 per session on Opus 5.5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
sofagent
A Cursor setup adapter that loads sofagent’s rules and knowledge at the start of a coding session, connects its MCP server, and runs change audits through Git hooks.
changelog
Update CHANGELOG.md for user-visible changes (Keep a Changelog).
ai-safe2-sovereign
AI SAFE2 v3.1 Sovereign Security Rules for Cursor.
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.