patrol-keywords

patrol-keywords is a command for Claude Code from cukas/patrol. It costs 18 tokens per session (504 once invoked), scanned A, original, MIT.

A command for managing the words that trigger Patrol’s bug-fix mode. It can list the built-in and custom words, add new ones, remove a word, or reset the custom list.

In plain words
What is it for?
Use it to configure trigger words such as terms for bugs, errors, crashes, or non-working features.
Why use it?
It lets the workflow recognize the language your team uses when reporting problems. This helps Patrol apply bug-investigation checks to the prompts you consider bug-related.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it to configure trigger words such as terms for bugs, errors…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/cukas/patrol/patrol-keywords
View source ↗ cukas/patrol
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.

Clone the repo
git clone --depth 1 https://github.com/cukas/patrol

Made for: Claude Code.

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-keywords

README.md
[![agentmods](https://agentmods.dev/badge/commands/cukas/patrol/patrol-keywords.svg)](https://agentmods.dev/commands/cukas/patrol/patrol-keywords)
Your own site
<a href="https://agentmods.dev/commands/cukas/patrol/patrol-keywords"><img src="https://agentmods.dev/badge/commands/cukas/patrol/patrol-keywords.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.00504
Opus 5 $0.00009 $0.00252
Sonnet 5 $0.00004 $0.00101
Haiku 4.5 $0.00002 $0.00050

Measured 6d ago against content hash 02f57e17dfe2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

patrol-keywords 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 6d 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-keywords.md · 52 lines

What it actually says

Patrol Keywords

Manage the keywords that trigger bug-fix mode. Custom keywords extend the built-in defaults.

Instructions

  1. Parse the user's arguments (text after /patrol-keywords):

    • No arguments → list all keywords
    • add "word1" "word2" ... → add to custom_keywords
    • remove "word" → remove from custom_keywords
    • reset → clear all custom keywords
  2. Read current config:

cat ~/.patrol/config.json 2>/dev/null || echo '{}'
  1. For list: show defaults and custom separately:

Default keywords (built-in, always active): fix, bug, broken, error, crash, doesn't work, not working, Fehler, kaputt, Absturz, funktioniert nicht, erreur, plantage, cassé, ne marche pas

Custom keywords (from config): [list from custom_keywords array, or "none" if empty]

  1. For add: read current custom_keywords array, append new words, write back:
# Read current
CURRENT=$(jq -r '.custom_keywords // []' ~/.patrol/config.json 2>/dev/null || echo '[]')
# Add new words (replace WORDS with actual words)
NEW=$(echo "$CURRENT" | jq --arg w "WORD" '. + [$w] | unique')
# Write back
jq --argjson kw "$NEW" '.custom_keywords = $kw' ~/.patrol/config.json > /tmp/patrol-config-tmp.json && mv /tmp/patrol-config-tmp.json ~/.patrol/config.json
  1. For remove: filter out the word:
jq --arg w "WORD" '.custom_keywords = (.custom_keywords // [] | map(select(. != $w)))' ~/.patrol/config.json > /tmp/patrol-config-tmp.json && mv /tmp/patrol-config-tmp.json ~/.patrol/config.json
  1. For reset: remove custom_keywords key:
jq 'del(.custom_keywords)' ~/.patrol/config.json > /tmp/patrol-config-tmp.json && mv /tmp/patrol-config-tmp.json ~/.patrol/config.json
  1. Show confirmation with the updated keyword list.
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. 6d ago First seen · 52 lines · 18 tokens per session scan A 02f57e17dfe2

Subscribe to this mod's changes

patrol-keywords is a command published in the GitHub repository cukas/patrol (3 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 504 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.