What is rule-reviewer?

An internal reviewer for draft coding rules. It checks whether rules are specific, testable, broadly useful, duplicated, outdated, or in conflict with other rules.

Reviewing draft rules, finding similar or contradictory guidance, improving wording, promoting reliable rules, merging duplicates, and removing stale or weak rules.

It keeps a rule collection small and useful by deciding which rules to promote, combine, rewrite, or archive.

How codingagentsystem/cas configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to codingagentsystem/cas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/codingagentsystem/cas/main/.claude/agents/rule-reviewer.md

Clone the repo

git clone --depth 1 https://github.com/codingagentsystem/cas

Made for: Claude Code.

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/agents/codingagentsystem/cas/rule-reviewer/github.svg)](https://agentmods.dev/agents/codingagentsystem/cas/rule-reviewer)

Your own site

<a href="https://agentmods.dev/agents/codingagentsystem/cas/rule-reviewer"><img src="https://agentmods.dev/badge/agents/codingagentsystem/cas/rule-reviewer/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/agents/codingagentsystem/cas/rule-reviewer"><img src="https://agentmods.dev/badge/agents/codingagentsystem/cas/rule-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 634 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	$0.00034	$0.00634
Opus 5.5	$0.00014	$0.00254
Sonnet 5.5	$0.00007	$0.00127
Haiku 4.5	$0.00003	$0.00063

Measured 2mo ago against content hash dc57b68f2065, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rule-reviewer 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 2mo 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.

.claude/agents/rule-reviewer.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review draft rules: promote, merge, or archive. Keep the rule set lean and high-signal.

Process

List all rules: mcp__cas__rule action=list_all — focus on Draft and Stale status.
For each draft rule, assess quality:
- Is it specific and actionable? ("Set busy_timeout on SQLite connections" = good, "Be careful with databases" = bad)
- Is it testable? Could you verify compliance by reading code?
- Does it apply broadly or is it a one-off fix disguised as a rule?
Check for overlap: mcp__cas__rule action=check_similar content="<rule content>" — find near-duplicates before deciding.
Decide:
- Promote if clear, specific, actionable, marked helpful, no conflicts with proven rules
- Merge if two rules say the same thing or overlap significantly — keep the more specific one, incorporate unique details from the other
- Rewrite if the rule has a good idea but bad phrasing — update content to be specific and actionable before promoting
- Archive if too vague, unused 30+ days, conflicts with proven rules, or project is done
Check for conflicts — contradictory rules ("Always X" vs "Never X"), overlapping scope with different guidance.
Execute:
- Promote: mcp__cas__rule action=helpful id=<id>
- Merge: update the better rule mcp__cas__rule action=update id=<keep> content="<merged>", then delete mcp__cas__rule action=delete id=<dup>
- Rewrite: mcp__cas__rule action=update id=<id> content="<improved>"
- Archive: mcp__cas__rule action=delete id=<id>

Quality Bar for Promotion

A rule deserves proven status when it:

States a clear constraint or pattern (not just advice)
Would catch a real issue if checked during code review
Doesn't duplicate an existing proven rule
Has been marked helpful at least once, OR describes a pattern that caused a real rejection

Guidelines

Be conservative with promotion — rules should earn proven status
One clear rule > two similar ones
Rewrite vague rules before promoting — don't promote bad phrasing just because the idea is good
Archive aggressively — unused rules add noise, and they cost context tokens
Flag conflicts for human review, don't auto-resolve
Check helpful_count — helpful rules deserve promotion
Rules from verification rejections (from_verification tag) are high-signal — they caught real issues

Read the full file on GitHub · 47 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.

2mo ago First seen · 47 lines · 34 tokens per session scan A dc57b68f2065

Subscribe to this mod's changes

rule-reviewer is an agent published in the GitHub repository codingagentsystem/cas (177 stars, last pushed 7mo ago), licensed MIT. It adds 34 tokens to every session and 634 once invoked, about $0.0001 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 2026-08-30.

Code review ai ai-orchestration claude cli coding-assistant mcp

rule-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rule-reviewercodingagentsystem/cas	Agent	177	7mo ago	MIT	A	34	Claude Code
reviewercan1357/oh-my-pi	Agent	38k	yesterday	MIT	A	10	Claude Code
security-reviewercan1357/oh-my-pi	Agent	38k	yesterday	MIT	A	14	Claude Code
code-reviewerJSK9999/ai-nexus	Agent	19	8mo ago	Apache-2.0	A	38	Claude Code
code-revieweranrylu/soul-forge	Agent	1	7mo ago	none	A	9	Claude Code
security-reviewerJSK9999/ai-nexus	Agent	19	8mo ago	Apache-2.0	A	52	Claude Code
Smart Excludeagentgg-dev/agentgg	Agent	459	3d ago	Apache-2.0	A	36	Claude Code

cas: Agent for Claude Code