Agent skill

Manage Rules

by Eigenwise in Eigenwise/eigenwise-toolshed

Inspect, audit, enable, or disable project live-rules. An agent skill from Eigenwise/eigenwise-toolshed.

MITAuto-check passedDevOps & Cloud

Install Manage Rules

skills CLI
$ npx skills add Eigenwise/eigenwise-toolshed --skill manage-rules -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Eigenwise/eigenwise-toolshed manage-rules --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Eigenwise/eigenwise-toolshed.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/live-rules/skills/manage-rules .claude/skills/manage-rules && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
manage-rules
GitHub stars
277
Token cost
~2k tokens
SKILL.md length
1,128 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Inspect, audit, enable, or disable project live-rules. An agent skill from Eigenwise/eigenwise-toolshed.

  • Works in 4 steps: If .claude/live-rules/rules/ exists,… → If the directory exists but… → If the manifest is parseable but hashes… → …
  • Check active instructions
  • SKILL.md covers Find the rules and manifest, How to read the files, Tasks and Guidelines, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Manage Rules is an agent skill from Eigenwise/eigenwise-toolshed. Inspect, audit, enable, or disable project live-rules. Use to list rules, check active instructions, explain an injected rule, or recover an atomic manifest.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud. The repository describes itself as: Six Claude Code plugins for the work that keeps coming back: repo maps, conditional rules, ticketed parallel work, extra subscription models, local usage metrics, and guided setup. The licence is MIT.

When your agent uses it

  • Check active instructions
  • Explain an injected rule
  • Recover an atomic manifest

Example prompts

  • “/manage-rules”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. If .claude/live-rules/rules/ exists, inspect its .md files and the generated manifest.
  2. If the directory exists but manifest.json is missing, malformed JSON, or has the wrong schema,
  3. If the manifest is parseable but hashes or metadata do not match the rule files, report a stale
  4. If the atomic directory is absent, resolve the legacy file from LIVE_RULES_PATH or the default

What it can do on your machine

Read from SKILL.md and the folder at commit 92c16cd. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Manage Rules loads about 2k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 1,128 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Eigenwise/eigenwise-toolshed at commit 92c16cd, republished under its MIT licence (© Eigenwise). 1,128 words, ~1,978 tokens.

Download SKILL.mdSave it as .claude/skills/manage-rules/SKILL.md (or your agent's skills folder).
name
manage-rules
description
Inspect, audit, enable, or disable project live-rules. Use to list rules, check active instructions, explain an injected rule, or recover an atomic manifest.

Manage Rules

Read, audit, and toggle live rules without changing what a rule says. For authoring or editing rule content, use the add-rule skill. The full format is documented in ../add-rule/references/rule-format.md.

New workspaces use one rule per Markdown file under .claude/live-rules/rules/ and a generated .claude/live-rules/manifest.json. Never edit the manifest directly. After every rule-file change, run:

text
node "${CLAUDE_PLUGIN_ROOT}/scripts/sync-atomic-rules.js" --project "${CLAUDE_PROJECT_DIR}"

Existing projects may still use a legacy file. The default is .claude/live-rules.md; an explicit LIVE_RULES_PATH may point to another project-relative, absolute, or ~-relative file. The legacy format is for migration or an explicit override only. SessionStart automatically migrates the default legacy file, verifies the atomic result, and removes the old file. An explicit path is preserved, and a failed verification keeps the legacy file.

Find the rules and manifest

Check the atomic directory first:

  1. If .claude/live-rules/rules/ exists, inspect its .md files and the generated manifest.
  2. If the directory exists but manifest.json is missing, malformed JSON, or has the wrong schema, report an atomic manifest recovery problem, not "no rules". Run the sync command above to rebuild the manifest from the rule files, then audit again.
  3. If the manifest is parseable but hashes or metadata do not match the rule files, report a stale manifest. The runtime reads the rule files directly and marks the mismatch; run sync to resync it.
  4. If the atomic directory is absent, resolve the legacy file from LIVE_RULES_PATH or the default path. If that file exists, report legacy storage and explain that SessionStart can migrate it. If no atomic directory and no legacy file exist, report that no rules are configured and point the user to add-rule.

A missing or malformed manifest with atomic rule files is never a clean no-rules result. Preserve the rule files while recovering it. If sync names a malformed rule file, repair that file and run sync again.

How to read the files

For atomic storage, inspect every .md rule under .claude/live-rules/rules/. Each file must contain exactly one rule. Compare its parsed metadata and content hash with the corresponding manifest entry. For legacy storage, parse the file as a sequence of frontmatter sections. Anything before the first fence is an intro; a bare file with no complete frontmatter block is one global rule.

Tasks

List the rules

Parse every section or atomic file and present a compact table. Use the description as the rule name, fallback to the filename or position:

RuleStorageScopeFires whenPriorityEnabled
House styleatomicglobalmatching prompt when unseen or changed0yes
React component conventionsatomicglobediting **/*.tsx when unseen or changed0yes
API layer rulesatomicdirediting under packages/api, or matching cwd0yes
Deploy checklistatomicpromptprompt matches deploy when unseen or changed0yes
Strict lint gateatomicglobmatching edit0no

Derive scope the same way as the hooks: no globs, dirs, or prompt means global; otherwise list whichever are present. A rule with only include: is still global. Note the include payload and whether its target exists.

Audit the rules

Check the storage and manifest before checking individual rules. Report concrete issues and the exact recovery:

  • Missing or malformed atomic manifest: .claude/live-rules/rules/ exists but manifest.json is absent, invalid JSON, or has an unsupported shape. Run the owned sync command; do not report no rules.
  • Stale atomic manifest: a rule hash, path, or metadata field differs from the generated value. The rule files are the authority; run sync to resync the manifest.
  • Dropped atomic rule: a manifest entry points to a missing or unsafe path, or a file contains more than one rule. Name the file, repair it, and run sync.
  • Broken or empty frontmatter that the parser would skip, such as an unterminated array, missing closing ---, or no body.
  • A stray --- inside a body, which the parser reads as the next rule's fence. Suggest *** or ___ instead.
  • Globs that match nothing in the repo. Compile the glob and test it against tracked files before reporting it.
  • Invalid prompt regexes written as /.../flags.
  • An include: target that does not exist. A rule whose includes are all missing is dropped and injects nothing.
  • Duplicates or conflicts: contradictory instructions or near-identical rules that should be merged.
  • Oversized rules: a body long enough to crowd the roughly 10k-character injection budget.
  • Over-broad global rules that should be scoped to a file, directory, or prompt.
  • Unexpected legacy storage: explain the migration or explicit LIVE_RULES_PATH exception and check whether SessionStart can migrate it.

Summarize findings as a short list of "rule or manifest: problem, suggested fix". Only change content if the user asks. add-rule is the right tool for content rewrites; manifest recovery uses the sync command.

Show full SKILL.md (353 more words)Show less
Enable or disable a rule

Toggle a rule without deleting it: find its atomic file or legacy section, set enabled: true or enabled: false in its frontmatter, and save. For atomic storage, run sync after saving so the manifest records the new metadata. Leave other files and sections untouched. Confirm which rule you toggled and its new state.

Explain what is active

Given a situation such as "for a normal prompt", "when I edit src/app/page.tsx", or "when I say 'tdeploy'", walk the rules and report which ones are eligible and why, mirroring the hook logic:

  • At SessionStart: applicable startup rules are injected and the session ledger is reset.
  • On a prompt: global rules, matching prompt rules, and directory rules whose directory contains the session cwd are selected; only new or changed unseen hashes are emitted after SessionStart.
  • Before an edit: glob rules matching that file and directory rules containing it are selected; only new or changed unseen hashes are emitted.

A rule carrying include: fires only if at least one included file exists. If all are missing it is dropped. Explain whether a selected rule was already seen unchanged in this session or is newly matching, so "why did Claude follow this?" and "why didn't it?" have a concrete answer.

Guidelines

  • Read and toggle, not rewrite. Send content changes to add-rule.
  • Recover manifests from source files. Never hand-edit generated JSON.
  • Verify before claiming. Test a glob against the repo file list and inspect include targets.
  • Never touch CLAUDE.md or CLAUDE.local.md.
  • After a change, remind the user to review and commit the atomic rule files and generated manifest so the team stays in sync.

Success criteria

  • Atomic directory, rule files, manifest, and legacy fallback are distinguished
  • Missing or malformed manifests are reported as recovery problems, never as clean no-rules
  • Existing resync command is run or clearly directed when the manifest is missing or stale
  • Rules are listed with storage, scope, trigger, priority, and enabled state
  • Audit reports real, rule-specific issues and tests globs against actual files
  • Any enable/disable change applies to the right file or section and is synced when atomic
  • CLAUDE.md is untouched

© Eigenwise, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/live-rules/skills/manage-rules of Eigenwise/eigenwise-toolshed.

Open the folder on GitHubat commit 92c16cd

Compare with similar skills

Manage Rules next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Manage Rules compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Manage Rules this skillEigenwise/eigenwise-toolshed277—~2kAutomated safety check: PassMIT
Monitor CInrwl/nx29k6 repos~4.7kAutomated safety check: PassMIT
Terraform and OpenTofu Guideagentscope-ai/QwenPaw35k6 repos~4.2kAutomated safety check: PassApache-2.0
Vercel Optimize Auditvercel-labs/agent-skills32k9 repos~4.3kAutomated safety check: PassNone
Openclaw Live Updateropenclaw/openclaw392k—~3.7kAutomated safety check: PassMIT
Analyze GitHub Action Logswithastro/astro63k1 repos~1.3kAutomated safety check: PassCustom licence

Similar skills

  • Monitor CI

    nrwl/nx

    Monitor Nx Cloud CI pipeline and handle self-healing fixes. An agent skill from nrwl/nx.

    29k GitHub starsUsed in 6 repos~4.7k tokens
    DevOps & CloudAuto-check passed
  • Terraform and OpenTofu Guide

    agentscope-ai/QwenPaw

    Guidance for writing and testing Terraform and OpenTofu code: module structure, naming, test approaches, CI/CD workflows, state handling and security scanning.

    35k GitHub starsUsed in 6 repos~4.2k tokens
    DevOps & CloudAuto-check passed
  • Vercel Optimize Audit

    vercel-labs/agent-skills

    Official

    Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.

    32k GitHub starsUsed in 9 repos~4.3k tokens
    DevOps & CloudAuto-check passed
  • Openclaw Live Updater

    openclaw/openclaw

    Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation.

    392k GitHub stars~3.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Official

    Analyze recent GitHub Actions workflow runs to identify patterns, mistakes, and improvements.

    63k GitHub starsUsed in 1 repo~1.3k tokens
    DevOps & CloudAuto-check passed
  • Creates and queries KubeSphere users, workspaces and projects and assigns built-in roles, defaulting to least privilege and never deleting anything.

    17k GitHub starsUsed in 1 repo~3.1k tokens
    DevOps & CloudAuto-check passed

More from Eigenwise/eigenwise-toolshed

All 14 skills in this repo
  • Add Rule

    Eigenwise/eigenwise-toolshed

    Create or edit a live-rules instruction in the project's atomic rule set.

    277 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Map Codebase

    Eigenwise/eigenwise-toolshed

    Create a self-maintaining codebase map in .claude/.codebase-info/.

    277 GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Setup

    Eigenwise/eigenwise-toolshed

    Set up a Claude Code workspace for a new or existing project, informed by hindsight from the user's whole session history.

    277 GitHub stars~4.5k tokensUpdated today
    Auto-check passed
  • Groom

    Eigenwise/eigenwise-toolshed

    Audit a Sidequest board for completed, stale, duplicate, or superseded tickets, then safely close clear cases.

    277 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Toolshed Doctor

    Eigenwise/eigenwise-toolshed

    Run a read-only health check for Quartermaster and installed Toolshed plugins.

    277 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Enable Project Telemetry

    Eigenwise/eigenwise-toolshed

    Opt the current project into local Claude Code usage telemetry, or verify its setup.

    277 GitHub stars~2.9k tokensUpdated today
    Auto-check: warnings

Categories

Questions about Manage Rules

What does Manage Rules do?

Inspect, audit, enable, or disable project live-rules. An agent skill from Eigenwise/eigenwise-toolshed. Manage Rules is an agent skill from Eigenwise/eigenwise-toolshed. Inspect, audit, enable, or disable project live-rules.

When should I use Manage Rules?

Manage Rules fits situations like: check active instructions; explain an injected rule; recover an atomic manifest.

How do I install Manage Rules in Claude Code?

Run `npx skills add Eigenwise/eigenwise-toolshed --skill manage-rules -a claude-code`. Or copy the skill folder (plugins/live-rules/skills/manage-rules in Eigenwise/eigenwise-toolshed) into .claude/skills/manage-rules in your project. Claude Code loads it when a task matches its description.

How do I install Manage Rules in Codex?

Run `npx skills add Eigenwise/eigenwise-toolshed --skill manage-rules -a codex`. Or copy the skill folder (plugins/live-rules/skills/manage-rules in Eigenwise/eigenwise-toolshed) into .agents/skills/manage-rules in your project. Codex loads it when a task matches its description.

Can I use Manage Rules in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Eigenwise/eigenwise-toolshed --skill manage-rules -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/manage-rules, .gemini/skills/manage-rules, .github/skills/manage-rules and .opencode/skills/manage-rules in your project.

What does Manage Rules need to run?

SKILL.md names no scripts, command-line tools or credentials: Manage Rules is instructions for the agent only.

Does Manage Rules access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Manage Rules safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Manage Rules use?

Manage Rules is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Manage Rules use?

About 2k tokens (SKILL.md is roughly 7.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Manage Rules?

Skills that share tags, products or a category with Manage Rules: Monitor CI (nrwl/nx, 29k stars), Terraform and OpenTofu Guide (agentscope-ai/QwenPaw, 35k stars), Vercel Optimize Audit (vercel-labs/agent-skills, 32k stars) and Openclaw Live Updater (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Manage Rules?

Eigenwise (a GitHub user) maintains it in Eigenwise/eigenwise-toolshed, which has 277 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.

Source: Eigenwise/eigenwise-toolshed on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.