Systematic Code Refactoring
luongnv89/claude-howto
Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.
Audit code-health and technical-debt signals with evidence, rank proportionate interventions from focused cleanup to broad coordinated refactors, and draft implementation-ready plans without…
Install Code Health Audit
$ npx skills add holon-run/holon --skill code-health-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install holon-run/holon code-health-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/code-health-audit .claude/skills/code-health-audit && rm -rf skills-srcUse ~/.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/
Install the "code-health-audit" agent skill from https://github.com/holon-run/holon/tree/main/skills/code-health-audit into .claude/skills/code-health-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-health-audit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/holon-run/holon/tree/main/skills/code-health-auditType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add holon-run/holon --skill code-health-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install holon-run/holon code-health-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/code-health-audit .agents/skills/code-health-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "code-health-audit" agent skill from https://github.com/holon-run/holon/tree/main/skills/code-health-audit into .agents/skills/code-health-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-health-audit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add holon-run/holon --skill code-health-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install holon-run/holon code-health-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/code-health-audit .cursor/skills/code-health-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "code-health-audit" agent skill from https://github.com/holon-run/holon/tree/main/skills/code-health-audit into .cursor/skills/code-health-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-health-audit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/holon-run/holon.git --path skills/code-health-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add holon-run/holon --skill code-health-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install holon-run/holon code-health-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/code-health-audit .gemini/skills/code-health-audit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "code-health-audit" agent skill from https://github.com/holon-run/holon/tree/main/skills/code-health-audit into .gemini/skills/code-health-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-health-audit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install holon-run/holon code-health-auditInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add holon-run/holon --skill code-health-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/code-health-audit .github/skills/code-health-audit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "code-health-audit" agent skill from https://github.com/holon-run/holon/tree/main/skills/code-health-audit into .github/skills/code-health-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-health-audit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add holon-run/holon --skill code-health-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install holon-run/holon code-health-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/code-health-audit .opencode/skills/code-health-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "code-health-audit" agent skill from https://github.com/holon-run/holon/tree/main/skills/code-health-audit into .opencode/skills/code-health-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-health-audit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
code-health-audit- GitHub stars
- 154
- Token cost
- ~1.3k tokens
- SKILL.md length
- 564 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Audit code-health and technical-debt signals with evidence, rank proportionate interventions from focused cleanup to broad coordinated refactors, and draft implementation-ready plans without…
- Works in 6 steps: Name the scope. Record the repository,… → Prefer direct evidence. Cite a file and… → Separate certainty levels. Use… → …
- Tasks that involve Code quality
- SKILL.md covers Summary, When To Use, Do Not Use and Evidence Rules, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Code Health Audit is an agent skill from holon-run/holon. Audit code-health and technical-debt signals with evidence, rank proportionate interventions from focused cleanup to broad coordinated refactors, and draft implementation-ready plans without granting implementation permission.
Its SKILL.md is about 1.3k 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 Development, covering Code quality, Refactoring and Technical debt. The repository describes itself as: An agent workbench for ongoing work: preserve goals and progress, connect events and schedules, and resume when the next condition is met. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Code quality
- Tasks that involve Refactoring
- Tasks that involve Technical debt
Example prompts
- “/code-health-audit”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Name the scope. Record the repository, paths, time window, and
- Prefer direct evidence. Cite a file and symbol or line range, relevant
- Separate certainty levels. Use confirmed, signal, hypothesis, or
- Avoid metric theater. A large file, high churn count, or duplicated
- Record counter-evidence. Note stable interfaces, strong tests, low
- Keep findings atomic. One finding should have one primary location,
What it can do on your machine
Read from SKILL.md and the folder at commit c29bd95. 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
Code Health Audit loads about 1.3k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 564 words of instructions outside code blocks.
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 holon-run/holon at commit c29bd95, republished under its Apache-2.0 licence (© holon-run). 564 words, ~1,302 tokens.
Download SKILL.mdSave it as
.claude/skills/code-health-audit/SKILL.md (or your agent's skills folder).- name
- code-health-audit
- description
- Audit code-health and technical-debt signals with evidence, rank proportionate interventions from focused cleanup to broad coordinated refactors, and draft implementation-ready plans without granting implementation permission.
Code Health Audit Skill
Summary
Use this skill for a read-only repository health audit or for preparing an evidence-backed maintenance plan. Plans may cover a focused cleanup, a multi-phase refactor, or a broad coordinated change when that scale is justified by the repository's maintenance cost. It defines an evidence discipline and an output shape; it does not provide a static analyzer and it does not authorize code changes.
When To Use
- Finding maintainability hotspots across a repository
- Reviewing a technical-debt register for stale or duplicate entries
- Comparing refactoring candidates before implementation
- Drafting a proportionate, behavior-preserving maintenance or refactoring plan
- Preparing verification gates for an approved refactoring
Do Not Use
- As a substitute for reviewing a concrete change set or pull request
- To declare a smell a bug, vulnerability, or performance issue without evidence
- To run a broad rewrite, formatter sweep, or dependency upgrade as an unapproved side effect of an audit
- To infer permission to edit code, merge changes, or publish findings
Evidence Rules
- Name the scope. Record the repository, paths, time window, and read/write authorization.
- Prefer direct evidence. Cite a file and symbol or line range, relevant tests, history, configuration, or measured behavior.
- Separate certainty levels. Use
confirmed,signal,hypothesis, orunknown; explain what would raise confidence. - Avoid metric theater. A large file, high churn count, or duplicated string is a lead. Connect it to coupling, change friction, defect history, testability, or another observed impact before ranking it highly.
- Record counter-evidence. Note stable interfaces, strong tests, low churn, generated code, or other reasons not to refactor now.
- Keep findings atomic. One finding should have one primary location, impact statement, and next step. Link related findings instead of merging unrelated smells.
Show full SKILL.md (277 more words)Show less
Audit Taxonomy
Use only categories supported by evidence:
- Boundary: responsibilities, ownership, or module seams are unclear.
- Duplication: behavior or policy is repeated and changes must stay in sync.
- Complexity: control flow or state interactions make behavior difficult to understand or verify.
- Coupling: a local change requires broad knowledge or coordinated edits.
- Testability: important behavior lacks a stable, focused verification seam.
- Consistency: neighboring code follows materially different conventions that increase maintenance cost.
- Lifecycle: compatibility, migration, cleanup, or deprecation paths are incomplete or indefinitely retained.
- Observability: failures or state transitions cannot be diagnosed with the available evidence.
Do not use the category as proof. Explain the observed pattern and impact.
Candidate Ranking
Rank candidates using a short qualitative score:
| Dimension | Question |
|---|---|
| Impact | What maintenance cost or risk is reduced? |
| Confidence | How directly is the claim supported? |
| Surface | How many files, interfaces, and owners are involved? |
| Coupling | How many callers, integrations, or invariants can be affected? |
| Regression risk | What can silently change? |
| Verification readiness | Can behavior be checked before and after? |
Prefer candidates with meaningful impact, strong evidence, a justified intervention surface, manageable coupling, and a clear verification path. A large surface is not itself a reason to reject a candidate when leaving the problem in place has greater maintenance cost. A low-confidence high-impact item belongs in an investigation queue, not at the top of an implementation queue.
Report Shape
Produce:
Scope and baseline
Evidence matrix
- ID:
- Category:
- Location:
- Observation:
- Evidence:
- Impact:
- Confidence:
- Counter-evidence or gaps:
Priority order
- Candidate:
- Why now:
- Dependencies:
Maintenance or refactoring plan
1. Preserve these invariants:
2. Add or identify these verification gates:
3. Choose the right-sized intervention:
- use a focused seam change when it addresses the root cause;
- sequence a multi-phase change when that reduces risk;
- use a broad coordinated refactor when smaller changes would preserve the
maintenance problem or create temporary inconsistency.
4. Re-run focused checks, broader gates, and compare behavior as appropriate:
5. Stop or roll back if:
Authorization statePlans must distinguish inspection, test-only preparation, implementation, and cleanup. Each implementation phase should have an explicit boundary and a verification gate; the boundary may span many files when the change is coordinated and justified. If behavior cannot be characterized, recommend more investigation instead of inventing a safe refactoring sequence.
© holon-run, Apache-2.0. 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 skills/code-health-audit of holon-run/holon.
Open the folder on GitHubat commit c29bd95
Compare with similar skills
Code Health Audit 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Code Health Audit this skillholon-run/holon | 154 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Systematic Code Refactoringluongnv89/claude-howto | 42k | — | ~3k | Automated safety check: Pass | MIT | |
| Code Refactoring Workflowluongnv89/claude-howto | 42k | — | ~3.1k | Automated safety check: Pass | MIT | |
| FIXME Resolvertailcallhq/forgecode | 7.6k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| DesloppifyGit-on-my-level/codex-autorunner | 875 | — | ~3.4k | Automated safety check: Pass | MIT | |
| Tech Debt Analyzerailabs-393/ai-labs-claude-skills | 454 | 1 repos | ~3.9k | Automated safety check: Pass | MIT |
Similar skills
Code Refactoring Workflow
luongnv89/claude-howto
Guides systematic, test-backed refactoring in the style of Martin Fowler, moving through research, planning and small incremental changes with your approval at each phase.
FIXME Resolver
tailcallhq/forgecode
Finds every FIXME comment in a codebase, groups related ones across files into one task, implements the work they describe and removes the comments once it is done.
Desloppify
Git-on-my-level/codex-autorunner
Codebase health scanner and technical debt tracker. An agent skill from Git-on-my-level/codex-autorunner.
Tech Debt Analyzer
ailabs-393/ai-labs-claude-skills
This skill should be used when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability.
Code Quality Gate
fengshao1227/ccg-workflow
Scans code for complexity, long functions, duplicated blocks, naming problems and code smells with a Node script, then reports and suggests refactors.
More from holon-run/holon
All 14 skills in this repoVideo Production
holon-run/holon
Assemble existing local images, videos, audio and subtitles into preview/final videos with FFmpeg, technical QC and provenance.
GitHub Issue Solve
holon-run/holon
Solve a GitHub issue by collecting context, implementing a fix, and opening or updating a pull request.
GitHub PR Fix
holon-run/holon
Fix a GitHub pull request by addressing feedback or CI failures, pushing changes, and publishing replies.
Code Review
holon-run/holon
Review a set of code changes using evidence-backed findings, explicit confidence, and a clear coverage summary.
Ghx
holon-run/holon
Guidance for safe, reliable GitHub CLI workflows across issues, pull requests, and reviews.
GitHub Review
holon-run/holon
Review a GitHub pull request by collecting GitHub context, applying evidence-backed review rules, and optionally publishing one review.
Related
Categories
Questions about Code Health Audit
What does Code Health Audit do?
Audit code-health and technical-debt signals with evidence, rank proportionate interventions from focused cleanup to broad coordinated refactors, and draft implementation-ready plans without…. Code Health Audit is an agent skill from holon-run/holon. Audit code-health and technical-debt signals with evidence, rank proportionate interventions from focused cleanup to broad coordinated refactors, and draft implementation-ready plans without granting implementation permission.
When should I use Code Health Audit?
Code Health Audit fits situations like: tasks that involve Code quality; tasks that involve Refactoring; tasks that involve Technical debt.
How do I install Code Health Audit in Claude Code?
Run `npx skills add holon-run/holon --skill code-health-audit -a claude-code`. Or copy the skill folder (skills/code-health-audit in holon-run/holon) into .claude/skills/code-health-audit in your project. Claude Code loads it when a task matches its description.
How do I install Code Health Audit in Codex?
Run `npx skills add holon-run/holon --skill code-health-audit -a codex`. Or copy the skill folder (skills/code-health-audit in holon-run/holon) into .agents/skills/code-health-audit in your project. Codex loads it when a task matches its description.
Can I use Code Health Audit 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 holon-run/holon --skill code-health-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-health-audit, .gemini/skills/code-health-audit, .github/skills/code-health-audit and .opencode/skills/code-health-audit in your project.
What does Code Health Audit need to run?
SKILL.md names no scripts, command-line tools or credentials: Code Health Audit is instructions for the agent only.
Does Code Health Audit 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 Code Health Audit 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 Code Health Audit use?
Code Health Audit is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Code Health Audit use?
About 1.3k tokens (SKILL.md is roughly 5.2k 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 Code Health Audit?
Skills that share tags, products or a category with Code Health Audit: Systematic Code Refactoring (luongnv89/claude-howto, 42k stars), Code Refactoring Workflow (luongnv89/claude-howto, 42k stars), FIXME Resolver (tailcallhq/forgecode, 7.6k stars) and Desloppify (Git-on-my-level/codex-autorunner, 875 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Code Health Audit?
holon-run (a GitHub organization) maintains it in holon-run/holon, which has 154 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 9, 2026.
Source: holon-run/holon on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.