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/cukas/patrolWrote 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/commands/cukas/patrol/patrol-keywords)<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>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 | $0.00018 | $0.00504 |
| Opus 5 | $0.00009 | $0.00252 |
| Sonnet 5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
patrol-keywords scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Patrol Keywords
Manage the keywords that trigger bug-fix mode. Custom keywords extend the built-in defaults.
Instructions
-
Parse the user's arguments (text after
/patrol-keywords):- No arguments → list all keywords
add "word1" "word2" ...→ add to custom_keywordsremove "word"→ remove from custom_keywordsreset→ clear all custom keywords
-
Read current config:
cat ~/.patrol/config.json 2>/dev/null || echo '{}'
- For list: show defaults and custom separately:
Default keywords (built-in, always active): fix, bug, broken, error, crash, doesn't work, not working, Fehler, kaputt, Absturz, funktioniert nicht, erreur, plantage, cassé, ne marche pas
Custom keywords (from config): [list from custom_keywords array, or "none" if empty]
- For add: read current
custom_keywordsarray, append new words, write back:
# Read current
CURRENT=$(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
- 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
- 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
- Show confirmation with the updated keyword list.
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.
- 6d ago First seen · 52 lines · 18 tokens per session scan A 02f57e17dfe2
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.
Other commands, from other repositories
merge
Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
spec
Spec-first design: a gap-closing interview that produces a complete spec, with a quality controller that blocks until every section is answered and every question resolved.
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
copilot-leak
Copilot's auto-review escapes: find them since the last look, sanitise them, and turn each one into a lesson.
debug
Systematic debugging: root cause before any fix, one hypothesis at a time, and a three-strikes rule that questions the architecture instead of stacking patches.