patrol-help

patrol-help is a command for coding agents from cukas/patrol. It costs 14 tokens per session (514 once invoked), scanned A, original, MIT.

A reference command that lists Patrol’s available commands, skills, and configuration options. Patrol is a coding workflow that watches investigation, reading, editing, and verification activity.

In plain words
What is it for?
Use it to view commands for changing Patrol mode, checking status, managing trigger words, investigating bugs, and reviewing the workflow.
Why use it?
It gives you one place to see how Patrol is configured and which commands are available. This avoids having to remember command names or behavior.

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-help
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-help

README.md
[![agentmods](https://agentmods.dev/badge/commands/cukas/patrol/patrol-help.svg)](https://agentmods.dev/commands/cukas/patrol/patrol-help)
Your own site
<a href="https://agentmods.dev/commands/cukas/patrol/patrol-help"><img src="https://agentmods.dev/badge/commands/cukas/patrol/patrol-help.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 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 $0.00014 $0.00514
Opus 5 $0.00007 $0.00257
Sonnet 5 $0.00003 $0.00103
Haiku 4.5 $0.00001 $0.00051

Measured 4d ago against content hash f52fae2d55bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

patrol-help 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-help.md · 59 lines

What it actually says

Patrol Help

Show the user this reference:

Commands

Command Description
/patrol-on Force full patrol mode on for this session
/patrol-off Disable patrol mode for this session
/patrol-status Dashboard — mode, tier, health, verification, config
/patrol-keywords Manage custom trigger keywords (list/add/remove/reset)
/patrol-config Show/edit configuration
/patrol-help This help

Skills

Skill Description
/diagnose Structured root-cause investigation — trace, hypothesize, verify, then fix

How It Works

Two-tier enforcement:

  Light mode (always-on)           → read-before-edit nudge + build/test reminder
  Full mode (bugfix keyword/manual) → full escalation + band-aid detection + STOP gate

  Status line (real-time):
    🛡️                              → watching, no activity
    🛡️ 📖4 ✏️2                      → healthy: 4 files read, 2 edited
    🛡️ bugfix · 📖4 ✏️2             → bugfix mode, healthy
    🟡 2 unread                     → warning: edits without reads
    🚨 STOP                         → hard stop: investigate now
    ✅                              → build/test verified

Config

Global: ~/.patrol/config.json Per-project: .patrol/config.json (overrides global)

Setting Default Description
enabled true Enable/disable patrol
always_on true Light mode active even without bugfix keywords
auto_detect_bugfix true Auto-detect bug-fix sessions from keywords
custom_keywords [] Additional trigger keywords (extend defaults)
band_aid_threshold 3 Edits before warning in full mode
verify_commands "auto" Build/test commands (or auto-detect)
easter_eggs false Yoda-themed messages
debug false Debug logging to ~/.patrol/debug.log
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 · 59 lines · 14 tokens per session scan A f52fae2d55bd

Subscribe to this mod's changes

patrol-help is a command published in the GitHub repository cukas/patrol (3 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 514 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