meta-rules

meta-rules is a skill for Claude Code from brody-0125/my-claude-skills. It costs 33 tokens per session (876 once invoked), scanned A, original, MIT.

Writing rules for Claude Code agents, skills, and workflows, covering size limits, required details, and quality checks. They are intended for automatically generated plugin improvements.

In plain words
What is it for?
Use them when creating or reviewing agent descriptions, skills, examples, and hook scripts, especially when enforcing imperative wording, explicit inputs and outputs, and model assignments.
Why use it?
They prevent generated components from becoming too long, vague, inconsistent, or difficult to maintain.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code.

Part of the plugin-introspector plugin — 4 skills shipped together

Good fit Use them when creating or reviewing agent descriptions, skills, examples, and hook scripts, especially when enforcing imperative wording, explicit inputs and outputs, and model assignments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brody-0125/my-claude-skills/meta-rules
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 brody-0125/my-claude-skills --skill meta-rules
Clone the repo
git clone --depth 1 https://github.com/brody-0125/my-claude-skills

Made for: Claude Code.

Or install plugin-introspector, the plugin that ships this one along with the rest of its 4 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.

agentmods badge for meta-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/brody-0125/my-claude-skills/meta-rules/github.svg)](https://agentmods.dev/skills/brody-0125/my-claude-skills/meta-rules)
Your own site
<a href="https://agentmods.dev/skills/brody-0125/my-claude-skills/meta-rules"><img src="https://agentmods.dev/badge/skills/brody-0125/my-claude-skills/meta-rules/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.

agentmods 80×15 button for meta-rules

Your own site · 80×15
<a href="https://agentmods.dev/skills/brody-0125/my-claude-skills/meta-rules"><img src="https://agentmods.dev/badge/skills/brody-0125/my-claude-skills/meta-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 876 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00876
Opus 5 $0.00016 $0.00438
Sonnet 5 $0.00007 $0.00175
Haiku 4.5 $0.00003 $0.00088

Measured 11d ago against content hash 22ffa2a3917d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

meta-rules 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 11d 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.

plugins/plugin-introspector/skills/meta-rules/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta-Rules — Plugin Component Quality Gates

Rules that govern how agents, skills, and workflows should be written. All auto-generated improvements MUST pass these rules before application.

Token Limits

These limits apply to auto-generated improvements (output of improvement-generator and auto-optimizer). They constrain individual components, not the main orchestrating SKILL.md which serves as a command router.

Component Max Tokens Measurement Scope
Agent description (.md) 1000 chars/4 Per agent file
Knowledge skill (SKILL.md) 500 chars/4 Per knowledge skill (meta-rules, analysis-patterns, cost-tracking)
Main skill (SKILL.md) No hard limit Orchestrating skill — uses lazy-load via resources/
Single example 200 chars/4 Per example block
Hook script 100 lines line count Per standalone script

Writing Rules

Agents

  1. ALWAYS use imperative voice in instructions ("Analyze the traces" not "You should analyze the traces")
  2. ALWAYS specify input and output formats explicitly
  3. NEVER exceed 1000 tokens in the agent description
  4. ALWAYS include model assignment (haiku/sonnet/opus) with justification
  5. Include 1-2 examples maximum — more examples waste context
  6. NEVER use vague instructions ("do your best", "try to", "if possible")
  7. ALWAYS specify exit conditions — when is the agent done?

Skills

  1. ALWAYS keep SKILL.md under 500 tokens — use resources/ for details
  2. ALWAYS use the 2-layer structure: SKILL.md (core) + resources/ (on-demand)
  3. NEVER load all resources at once — lazy-load per phase/command
  4. ALWAYS declare allowed-tools explicitly — minimal permissions
  5. ALWAYS include trigger conditions in the description

Hooks

  1. ALWAYS complete within 50ms — hooks block execution
  2. ALWAYS use || true fallback — hook failures must not break workflow
  3. NEVER read large files in hooks — use append-only writes
  4. ALWAYS use set -euo pipefail in scripts
  5. NEVER install external dependencies — bash + jq only

Read the full file on GitHub · 83 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.

  1. 11d ago First seen · 83 lines · 33 tokens per session scan A 22ffa2a3917d

Subscribe to this mod's changes

meta-rules is a skill published in the GitHub repository brody-0125/my-claude-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 876 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

self-audit

Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.

SpaiR/task-pipeline · 52 tokens

grill

Interrogate a plan or decision one question at a time before capture, keeping a decision-plus-rationale ledger, then route to the right capture skill.

SpaiR/task-pipeline · 33 tokens

architect

Answer build-or-adopt honestly, then design one committed architecture from your own understanding of the problem — driven by ranked quality attributes, stress-tested against the field and against change, proven by a walking skeleton, its consequences confirmed by the user, committed to ARCHITECTURE.md. A command the…

donald-ada/workinggenius · 80 tokens

designer

Settle the look before the pixels — audience and context first, then the base and the delta, taste settled by looking at real states, accessibility as the floor, one design language committed to DESIGN.md as tokens with roles. A command the user types, for work with an interface someone will see; standalone, no other…

donald-ada/workinggenius · 69 tokens

daily-working

End-to-end pipeline: pull a task from the project's task tracker by ID (Redmine or GitHub Issues today, more addable via a new adapter), sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension…

tms-tungnguyen3/daily_working · 98 tokens

compact

Put the compaction question to a snapshot that drifted — route what no longer constrains unfinished work, and say what moves before moving it. In flight or done; the log is appended to, never edited or trimmed.

donald-ada/workinggenius · 47 tokens