A command-line lookup tool for finding a project's subscribed business rules and conventions in a knowledge base. It can search, display, or list rules, and some Claude sessions automatically include strongly matching rules.

It is for looking up rules before implementing or changing behaviour, when a convention is unclear, and before reviewing a change. If a project has no rule database, it reports that instead of inventing guidance.

It reduces the risk of guessing how a project expects behaviour, names, or workflows to work. It also gives reviewers a way to check changes against the rules that apply to them.

rules-ops — Skill for Claude Code by tu11aa/squadrant

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.

Any agent

npx skills add tu11aa/squadrant --skill rules-ops

Clone the repo

git clone --depth 1 https://github.com/tu11aa/squadrant

Made for: Claude Code.

Or install squadrant, the plugin that ships this one along with the rest of its 27 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tu11aa/squadrant/rules-ops/github.svg)](https://agentmods.dev/skills/tu11aa/squadrant/rules-ops)

Your own site

<a href="https://agentmods.dev/skills/tu11aa/squadrant/rules-ops"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/rules-ops/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tu11aa/squadrant/rules-ops"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/rules-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,010 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.01010
Opus 5.5	$0.00016	$0.00404
Sonnet 5.5	$0.00008	$0.00202
Haiku 4.5	$0.00004	$0.00101

Measured 28d ago against content hash feab887a67e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rules-ops 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 28d 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.

plugin/skills/rules-ops/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rules Operations

A project can subscribe to a knowledge base (KB) of rules: short statements with a modality, a source, and a status. squadrant rules is the lookup. It is plain CLI, so it works the same from any agent (Claude, Codex, opencode, Gemini).

When to Look Up Rules

Before implementing or changing behaviour in a project that subscribes to a KB.
When unsure about a convention, naming, workflow, or business rule. Search before guessing.
Before review — check the change against the rules that touch the area.

If the project has no KB, the commands say so (or return nothing). Move on; do not invent rules.

Claude sessions get rules auto-injected (<squadrant-project-rules> blocks): every must/must-not rule at session start, and up to 3 strongly matching rules per prompt. That covers the hard rules, not every rule; still search for the task at hand. Disable with SQUADRANT_RULES_INJECT=0.

How

squadrant rules search <terms...>   # ranked keyword search, e.g. squadrant rules search invoice approval
squadrant rules show <id>           # full rule by id
squadrant rules list                # browse every rule in scope

The project comes from your working directory or SQUADRANT_CREW_PROJECT (set automatically for crews). Pass --project <name> to override.
By default only active and stale rules are returned. --all adds proposed and retired (works on search and list).
Prefer --brief to save context. It prints one line per rule: [score] MODALITY id: statement (list --brief omits the score). Scan those, then squadrant rules show <id> only for the rules that matter.
--ids-only prints just the matching rule ids.
search shows the top 5 by default. When more matched it ends with (+N more; use --limit); raise it with --limit <n>.
Ranking weighs the id and keywords above the statement, and the statement above the rationale. A query of 2+ terms needs at least 2 matched terms (or a hit on a curated keyword), so add a second distinctive term to narrow rather than reading everything. The best match is usually in the top 3.
(no matching rules) means none matched. Try a synonym before concluding there is no rule.

Read the full file on GitHub · 59 lines

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.

28d ago First seen · 59 lines · 40 tokens per session scan A feab887a67e0

Subscribe to this mod's changes

rules-ops is a skill published in the GitHub repository tu11aa/squadrant (2 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,010 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-09.

Code review Project management

rules-ops next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rules-opstu11aa/squadrant	Skill	2	yesterday	MIT	A	40	Claude Code
autoreviewopenclaw/clawhub	Skill	9.5k	yesterday	MIT	A	17	Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills	Skill	2.2k	6d ago	MIT	A	115	Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermes	Skill	5.2k	yesterday	MIT	A	48	Claude Code, Codex
revdiff-planumputun/revdiff	Skill	945	yesterday	MIT	A	84	Claude Code
explore-unknownsdzhng/skills	Skill	1.4k	2d ago	MIT	A	162	Claude Code, Codex
re0-mergeLilMGenius/paperthin	Skill	1.4k	4d ago	MIT	A	70	Claude Code