patrol-rules

patrol-rules is a command for coding agents from cukas/patrol. It costs 13 tokens per session (390 once invoked), scanned A, original, MIT.

A command for listing the rules currently active in Patrol and viewing their details or adding built-in rule templates.

In plain words
What is it for?
It is for inspecting rules such as reading files before editing, testing after changes, or preventing force-pushes to the main branch.
Why use it?
It makes it clear which checks are active, where they came from, and whether they warn or block work.

Command

Part of the patrol plugin — 4 skills, 7 commands, 3 hooks shipped together

Install

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.

agentmods
npx agentmods add commands/cukas/patrol/patrol-rules
Clone the repo
git clone --depth 1 https://github.com/cukas/patrol

Or install patrol, the plugin that ships this one along with the rest of its 4 skills, 7 commands, 3 hooks.

Wrote 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.

agentmods badge for patrol-rules

README.md
[![agentmods](https://agentmods.dev/badge/commands/cukas/patrol/patrol-rules.svg)](https://agentmods.dev/commands/cukas/patrol/patrol-rules)
Your own site
<a href="https://agentmods.dev/commands/cukas/patrol/patrol-rules"><img src="https://agentmods.dev/badge/commands/cukas/patrol/patrol-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 390 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00013 $0.00390
Opus 5 $0.00006 $0.00195
Sonnet 5 $0.00003 $0.00078
Haiku 4.5 $0.00001 $0.00039

Measured 4d ago against content hash 138f730910c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

patrol-rules 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 4d 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.

commands/patrol-rules.md · 48 lines

What it actually says

/patrol-rules

List all active rules with their source, level, and status.

When invoked with no arguments

Read the cached rules from /tmp/patrol-{session_id}/rules.json. Present as a table:

# Rule Level Source Status
1 test-before-push warn .patrol/rules.json active
2 read-before-edit warn built-in active
3 no-force-push-main block built-in (safety) active

Group by category: Safety → Workflow → Quality → Architecture → Custom

For each rule, determine source:

  • IDs starting with _safety- → "built-in (safety)"
  • IDs matching built-in investigation rules (read-before-edit, investigate-first, test-after-changes) → "built-in"
  • All others → the file path they were loaded from (show as relative path)

When invoked with explain <rule-id>

Show full rule details:

  • ID, name, category, level
  • Trigger type and match pattern
  • Require conditions (if any)
  • Message template
  • Source file
  • Tags (if any)

When invoked with add <template-id>

Show available built-in rule templates that are not currently active. If a specific template-id is given, add it to ~/.patrol/my-rules.json.

When invoked with disable <rule-id>

Disable a personal rule by setting "enabled": false in ~/.patrol/my-rules.json. Cannot disable repo or company rules — inform the user that they need to modify the source file. Cannot disable safety rules — inform the user that safety rules are always active.

Changes

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.

  1. 4d ago First seen · 48 lines · 13 tokens per session scan A 138f730910c4

Subscribe to this mod's changes

patrol-rules is a command published in the GitHub repository cukas/patrol (3 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 390 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.

Related

Other commands, from other repositories