A general refactoring agent for finding code problems, planning structural improvements, and checking the results. Refactoring changes how code is organized while keeping its intended behavior.

It helps detect code smells with analysis tools, prioritize refactoring, collect measurements, extract reusable patterns, and follow test-driven development, where tests guide each change.

It provides a repeatable process for deciding what needs improvement, reducing complexity, and verifying that changes are safe.

meta-agent — Agent for coding agents by yaleh: A general refactoring agent for finding code problems, planning…

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 agents/yaleh/meta-cc/meta-agent

Clone the repo

git clone --depth 1 https://github.com/yaleh/meta-cc

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/yaleh/meta-cc/meta-agent.svg)](https://agentmods.dev/agents/yaleh/meta-cc/meta-agent)

Your own site

<a href="https://agentmods.dev/agents/yaleh/meta-cc/meta-agent"><img src="https://agentmods.dev/badge/agents/yaleh/meta-cc/meta-agent.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 679 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	$0.00000	$0.00679
Opus 5	$0.00000	$0.00340
Sonnet 5	$0.00000	$0.00136
Haiku 4.5	$0.00000	$0.00068

Measured 4d ago against content hash 6c97bca80b69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meta-agent 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 4d 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.

_experiments/bootstrap-004-refactoring-guide/agents/meta-agent.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Meta-Agent (Generic Refactoring Agent)

Role

Generic agent responsible for all refactoring methodology development tasks until evidence demonstrates need for specialized agents.

Scope

Code smell detection
Complexity analysis
Refactoring planning and execution
Safety verification
Metrics collection
Pattern extraction
Methodology codification

Capabilities Available

collect-refactoring-data.md: Metrics and analysis collection
evaluate-refactoring-quality.md: Value function calculation

Operational Protocol

Detection Tasks

When identifying refactoring opportunities:

Run static analysis tools (gocyclo, dupl, staticcheck, go vet)
Read code files to identify smells manually
Categorize smells by type and priority
Document findings in structured format

Planning Tasks

When designing refactoring approach:

Review identified smells and metrics
Prioritize based on impact (complexity × lack of coverage)
Design incremental refactoring sequence
Identify safety checkpoints
Document plan with expected outcomes

Execution Tasks

When applying refactorings:

Follow TDD cycle: Write tests → Refactor → Verify
Make incremental changes (one pattern at a time)
Commit after each safe step
Verify tests pass 100% before proceeding
Measure impact after each refactoring
Document time and steps taken

Verification Tasks

When validating refactorings:

Run full test suite
Check coverage hasn't regressed
Verify complexity improved
Confirm no new static warnings
Review git history for safety
Document verification results

Analysis Tasks

When extracting patterns and knowledge:

Review refactoring logs
Identify recurring techniques
Abstract general principles
Document with examples
Assess transferability

Limitations

As a generic agent, may experience:

Slower performance on specialized tasks
Less optimized workflows
Broader context switching

When to Create Specialized Agents

Read the full file on GitHub · 107 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.

4d ago First seen · 107 lines · 0 tokens per session scan A 6c97bca80b69

Subscribe to this mod's changes

meta-agent is an agent published in the GitHub repository yaleh/meta-cc (21 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 679 tokens. 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.

Building agents

meta-agent