What is rule-manager?

A tool that reviews .claude/rules/ files and applies one token-saving improvement at a time. It also records each change in a memory log.

Use it to audit rule files, find issues such as excessive size or missing path scope, inspect prior optimization logs, and apply the highest-priority single improvement.

It helps keep the rules that guide an agent concise and focused, so they use less context and remain easier to maintain. The input does not specify the exact optimization chosen in each run.

rule-manager — Skill by aigentive

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 skills/aigentive/ralphx/rule-manager

Any agent

npx skills add aigentive/RalphX --skill rule-manager

Clone the repo

git clone --depth 1 https://github.com/aigentive/RalphX

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 774 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.

Model	Per session	Once invoked
Fable 5	$0.00070	$0.00774
Opus 5	$0.00035	$0.00387
Sonnet 5	$0.00014	$0.00155
Haiku 4.5	$0.00007	$0.00077

Measured 2d ago against content hash 75a17e8d84b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rule-manager 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 2d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/lib/common.sh, scripts/rule-apply-paths.sh, scripts/rule-audit.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/app/skills/rule-manager/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rule Manager

Iteratively optimizes .claude/rules/ for token efficiency. Each run: audit -> pick ONE optimization -> apply -> log.

Step 1: Read Framework Reference

Read the memory framework doc for context on priorities and standards: ${CLAUDE_PLUGIN_ROOT}/memory-framework.md

Also fetch/refresh the official Claude Code memory docs (cached locally):

"${CLAUDE_PLUGIN_ROOT}/skills/rule-manager/scripts/rule-fetch-docs.sh"

Step 2: Audit

Run the audit script to collect current state:

"${CLAUDE_PLUGIN_ROOT}/skills/rule-manager/scripts/rule-audit.sh" --json

Parse the JSON output. Report to user:

Total files, lines, estimated tokens
Files with/without paths: frontmatter
Files with @ references
Health indicators (oversized, unscoped, refs)

Also read the optimization log to see what's been done (per-day files): .claude/memory/ (read the latest file, or all files for full history)

Step 3: Identify ONE Optimization

Pick the HIGHEST priority that applies (do NOT do multiple):

Priority 1: @ References Between Rules

If any rule file has @ references to other rule files:

"${CLAUDE_PLUGIN_ROOT}/skills/rule-manager/scripts/rule-strip-refs.sh" <filename> --dry-run

Show the preview to user. If approved:

"${CLAUDE_PLUGIN_ROOT}/skills/rule-manager/scripts/rule-strip-refs.sh" <filename>

Priority 2: Unscoped Domain Rule

If a rule lacks paths: frontmatter but is domain-specific:

"${CLAUDE_PLUGIN_ROOT}/skills/rule-manager/scripts/rule-suggest-paths.sh" <filename>

Review the suggestions. For complex cases, use an Explore agent to grep the codebase for the rule's key terms. Show proposal to user. If approved:

"${CLAUDE_PLUGIN_ROOT}/skills/rule-manager/scripts/rule-apply-paths.sh" <filename> "pattern1" "pattern2"

Priority 3: Oversized Rule (>400 LOC)

If a rule exceeds 400 lines:

Read the file and identify distinct sections
Propose splitting into 2-3 focused files with paths: frontmatter
Create new files, delete original
This is a manual operation (no script -- requires judgment)

Read the full file on GitHub · 99 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2d ago First seen · 99 lines · 70 tokens per session scan A 75a17e8d84b3

Subscribe to this mod's changes

rule-manager is a skill published in the GitHub repository aigentive/RalphX (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 70 tokens to every session and 774 once invoked, about $0.0003 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.

Memory and context

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens