What makes Refactor Agents Md notable?

1K downloads. Trust evidence available

How should Refactor Agents Md be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Refactor Agents Md

Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or revie...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.0.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.2release · observed Jun 9, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s178sk484g47vwcbvvfcjpftfx8461fz:refactor-agents-md

Install using `clawhub skill install s178sk484g47vwcbvvfcjpftfx8461fz:refactor-agents-md` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/clarezoe/refactor-agents-md before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-refactor-agents-md/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

32,742 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: "refactor-agents-md"
description: "Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or reviewing AGENTS.md / CLAUDE.md guidance — or when the file has grown into a \"ball of mud\" with contradictions, bloat, and stale instructions."
license: "MIT-0"
metadata: {"openclaw":{"emoji":"🧹","homepage":"https://github.com/Fei2-Labs/skill-genie"},"category":"developer-tools","author":"Skill Genie","tags":["agents-md","claude-md","refactoring","progressive-disclosure","ai-config"],"version":"1.0.2","license":"MIT-0","hermes":{"tags":["agents-md","claude-md","refactoring","progressive-disclosure","ai-config"]}}
---

<objective>
Refactor AGENTS.md files so the root file stays small, stable, and broadly useful while detailed guidance moves into focused follow-up docs. The skill helps identify contradictions, separate essentials from bloat, and produce a clearer instruction hierarchy that is easier for agents to follow.
</objective>

<quick_start>
1. Identify whether the user wants a review, a rewrite proposal, or an in-repo refactor.
2. Read the current AGENTS.md content and classify each instruction as root-essential, topic-specific, conflicting, redundant, vague, or stale.
3. Keep only universal instructions in the root file, move the rest into topic docs, and surface any contradictions before editing.
</quick_start>

<essential_principles>
<principle name="keep-root-minimal">
The root AGENTS.md should contain only what applies to every task: a one-line project description, package manager expectations if non-default, non-standard build or typecheck commands, and truly universal constraints.
</principle>

<principle name="resolve-conflicts-first">
If two instructions disagree, do not silently merge them. Surface the conflict, explain the tradeoff briefly, and ask the user which version to keep before rewriting.
</principle>

<principle name="group-by-purpose">
Move remaining guidance into separate files grouped by topic or behavior, not by author, chronology, or file location.
</principle>

<principle name="delete-bloat">
Flag redundant, vague, self-evident, or outdated instructions for deletion instead of preserving them in a new location.
</principle>

<principle name="prefer_progressive_disclosure">
Keep the root file as a router into narrower guidance. Detail belongs in follow-up docs that are only read when relevant.
</principle>
</essential_principles>

<intake>
Ask the user which mode they want:
1. Review only
2. Propose a rewrite
3. Apply the refactor in the repo

If the user already gave enough context, skip extra questions and go straight to the matching workflow.
</intake>

<routing>
<mode name="review-only">workflows/audit-agents-md.md</mode>
<mode name="propose-rewrite">workflows/audit-agents-md.md</mode>
<mode name="apply-refactor">workflows/refactor-agents-md.md</mode>
</routing>

<reference_index>
All shared guidance lives in refere

README.md

# refactor-agents-md

Refactor bloated AGENTS.md / CLAUDE.md into clean, topic-specific docs.

## What it does

`refactor-agents-md` takes a monolithic agent guidance file that has grown into a "ball of mud" and splits it into a minimal root file plus topic-specific follow-up documents using progressive disclosure.

## When to use

- Your AGENTS.md or CLAUDE.md has grown too large with contradictions and stale instructions
- User asks to clean up, split, or review agent guidance files

## How it works

1. Analyze the existing file for sections, contradictions, and bloat
2. Extract topic-specific content into separate focused documents
3. Create a minimal root file that routes to topic docs on demand
4. Remove contradictions and stale instructions

## Key features

- Progressive disclosure: agents only load what they need
- Detects contradictions and redundancy
- Preserves important rules while removing noise
- Works with any agent config format (AGENTS.md, CLAUDE.md, etc.)

---

**Source**: [github.com/Fei2-Labs/skill-genie](https://github.com/Fei2-Labs/skill-genie)
**Author**: [@clarezoe](https://x.com/clarezoe)

_meta.json

{
  "ownerId": "kn71ntcwxg33gv53ryabqt0vw981g9my",
  "slug": "refactor-agents-md",
  "version": "1.0.2",
  "publishedAt": 1781011308782
}

references/principles.md

<principles>
<rule name="root_scope">
Treat the root AGENTS.md as a universal contract, not a knowledge dump. Keep only instructions that should apply to every task in the repository.
</rule>

<rule name="universal_content">
Good root content is usually limited to:
- a one-sentence project description
- package manager or workspace expectations if non-default
- non-standard build, test, or typecheck commands
- repository-wide safety constraints that matter for every task
</rule>

<rule name="split_triggers">
Move content out of the root file when it is specific to one domain, one workflow, or one tool. If only some tasks need it, it belongs elsewhere.
</rule>

<rule name="contradiction_handling">
When instructions conflict, preserve neither by default. Identify the exact conflict, explain the consequence of each option, and ask the user to choose.
</rule>

<rule name="bloat_signals">
Treat these as deletion candidates unless there is a strong reason to keep them:
- obvious advice the agent already knows
- duplicated instructions with slightly different wording
- vague slogans that do not change behavior
- stale references to paths, commands, or project state
</rule>

<rule name="file_organization">
Prefer a small root file with direct links to topic-specific docs. Name follow-up files by purpose, such as testing, formatting, release, or platform-specific guidance.
</rule>

<rule name="output_goal">
A good refactor leaves the root file shorter, clearer, and easier to scan, while the total guidance stays available in focused follow-up docs.
</rule>
</principles>

skill-card.md

## Description:

Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure.

This skill is ready for commercial/non-commercial use.

## Publisher:

[clarezoe](https://clawhub.ai/user/clarezoe)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and engineers use this skill to review, split, or refactor oversized AGENTS.md or CLAUDE.md guidance into a minimal root file and focused topic documents.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Apply mode can intentionally change repository guidance files that future agents may read.

Mitigation: Use review or proposal mode first when instructions may conflict, and inspect proposed changes before applying them.

Risk: Conflicting AGENTS.md or CLAUDE.md instructions can lead to incorrect refactoring decisions.

Mitigation: Pause on conflicts, present the exact disagreement, and require the user to choose which instruction to keep before rewriting.

## Reference(s):

- [Skill Genie repository](https://github.com/Fei2-Labs/skill-genie)
- [Principles and heuristics](references/principles.md)
- [ClawHub skill page](https://clawhub.ai/clarezoe/skills/refactor-agents-md)

## Skill Output:

**Output Type(s):** [Text, Markdown, Code, Configuration, Guidance]

**Output Format:** [Markdown guidance, proposed file structures, and repository file edits when apply mode is requested]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May change AGENTS.md, CLAUDE.md, or related topic guidance files in apply mode.]

## Skill Version(s):

1.0.2 (source: SKILL.md frontmatter metadata and server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular