Agent Setup Health Audit
tw93/Waza
Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.
Reads an agent environment's own traces, friction reports and logs across sessions, then proposes fixes on the surface that owns each one, only with your approval.
Install Refit Environment Retrospective
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill refit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Yeachan-Heo/oh-my-claudecode refit --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/Yeachan-Heo/oh-my-claudecode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/refit .claude/skills/refit && 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 "refit" agent skill from https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/refit into .claude/skills/refit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refit", 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/Yeachan-Heo/oh-my-claudecode/tree/main/skills/refitType 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 Yeachan-Heo/oh-my-claudecode --skill refit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Yeachan-Heo/oh-my-claudecode refit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yeachan-Heo/oh-my-claudecode.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/refit .agents/skills/refit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "refit" agent skill from https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/refit into .agents/skills/refit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refit", 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 Yeachan-Heo/oh-my-claudecode --skill refit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Yeachan-Heo/oh-my-claudecode refit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yeachan-Heo/oh-my-claudecode.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/refit .cursor/skills/refit && 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 "refit" agent skill from https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/refit into .cursor/skills/refit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refit", 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/Yeachan-Heo/oh-my-claudecode.git --path skills/refit--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 Yeachan-Heo/oh-my-claudecode --skill refit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Yeachan-Heo/oh-my-claudecode refit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yeachan-Heo/oh-my-claudecode.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/refit .gemini/skills/refit && 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 "refit" agent skill from https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/refit into .gemini/skills/refit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refit", 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 Yeachan-Heo/oh-my-claudecode refitInstalls 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 Yeachan-Heo/oh-my-claudecode --skill refit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Yeachan-Heo/oh-my-claudecode.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/refit .github/skills/refit && 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 "refit" agent skill from https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/refit into .github/skills/refit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refit", 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 Yeachan-Heo/oh-my-claudecode --skill refit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Yeachan-Heo/oh-my-claudecode refit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yeachan-Heo/oh-my-claudecode.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/refit .opencode/skills/refit && 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 "refit" agent skill from https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/refit into .opencode/skills/refit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "refit", 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
refit- GitHub stars
- 40k
- Token cost
- ~1.4k tokens
- SKILL.md length
- 794 words
- Files
- 1
- Skills in repo
- 47
- Repo updated
- First seen
- Licence
- MIT
At a glance
Reads an agent environment's own traces, friction reports and logs across sessions, then proposes fixes on the surface that owns each one, only with your approval.
- Works in 4 steps: Deterministic check — the failure was… → Steering surface — the failure was a… → Tool surface — the drag was tooling… → …
- After several sessions where the agent kept tripping on the same check
- SKILL.md covers Evidence first, Four fix-owner surfaces, Proposal and landing and Headless refit (unattended…, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Refit studies the environment the agent worked in rather than the code it produced. It starts from instruments, not a checklist: trace timelines and summaries, a session friction report, the .omc/logs folder, plan notepads such as issues.md and problems.md, and the repo's own checks in package.json scripts and CI workflows. An empty survey is a valid result, and an invented finding counts as a violation.
Every finding must name the surface that owns its fix. A deterministic check covers mechanical failures with a lint rule, hook or CI job. The steering surface covers judgment calls through docs/standards or CLAUDE.md and AGENTS.md. The tool surface covers slow or costly tooling in .mcp.json, scripts or hooks, and the fourth surface is information access. A finding that fits none is declined with a reason, and nothing is written without your approval.
When your agent uses it
- After several sessions where the agent kept tripping on the same check
- Turning recorded friction into lint rules, hooks or doc changes
- Auditing which of a repo's checks are unwired or silently broken
Example prompts
- “Review what slowed down the last few ralph runs and propose environment fixes.”
- “Read the friction report and tell me which repeated failures deserve a lint rule.”
- “Check whether our CI workflows actually run the checks listed in package.json.”
Requirements
- OMC instrumentation such as trace timelines and session friction reports
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Deterministic check — the failure was mechanical: a fixed syntactic pattern, a banned API, an import shape, a file-location rule. The fix…
- Steering surface — the failure was a judgement call no guardrail substitutes for: cross-file consistency, matches-surrounding-style. The…
- Tool surface — the drag was tooling itself: expensive or token-inefficient MCP calls, missing automation, checks too slow to be run when…
- Information surface — the agent needed a signal it could not reach: dev-server logs, service state, third-party readonly access. The fix…
What it can do on your machine
Read from SKILL.md and the folder at commit 454bae0. 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
Refit Environment Retrospective loads about 1.4k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 794 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 Yeachan-Heo/oh-my-claudecode at commit 454bae0, republished under its MIT licence (© Yeachan-Heo). 794 words, ~1,427 tokens.
Download SKILL.mdSave it as
.claude/skills/refit/SKILL.md (or your agent's skills folder).- name
- refit
- description
- Cross-session environment retrospective driven by OMC's own instrumentation — trace timelines, friction reports, logs, and plan notepads. Every finding lands on the surface that owns the fix (deterministic check, steering volume, tooling, or information access); nothing is written without user approval.
- argument-hint
- [--scope <area>] [--last <N sessions>]
- disable-model-invocation
- true
Refit
Refit surveys the environment the agent worked in — not the code it produced (review and verify own that) and not one launch run's lessons (the sediment pass owns that). Every kind of work leaves friction behind: a ralph loop that kept tripping on the same check, an autopilot run that stalled waiting for a signal, a debugging session where the decisive output was never captured anywhere. OMC instruments all of it. Refit reads the instruments and converts recorded friction into environment changes, so the next run starts in a better yard.
Evidence first
The survey starts from OMC's instruments, not from a checklist. Read before asking the user anything:
trace_timeline/trace_summary— where turns stalled, repeated, or fanned out wastefullyomc session friction report— friction the session recorded about itself.omc/logs/and session state — errors, retries, swallowed failures- plan notepads
.omc/notepads/*/issues.mdandproblems.md— problems that accumulated across a plan - the repo's own check surface (
package.jsonscripts, CI workflows) — read before proposing any new check, because a check that exists but sits unwired or silently broken is the finding, not a reinvention
Findings emerge from what the data shows. An empty survey is a valid result and is stated plainly; an invented finding is the same violation as skipping the survey. A repo with no wired automated checks is itself a finding, not a neutral default.
Four fix-owner surfaces
Every finding names the surface that owns its fix. A finding that fits no surface is declined, explicitly and with the reason.
- Deterministic check — the failure was mechanical: a fixed syntactic pattern, a banned API, an import shape, a file-location rule. The fix is a lint rule, hook, or CI job — whichever the repo's existing guardrails make cheapest. Default to building the check over writing the rule.
- Steering surface — the failure was a judgement call no guardrail substitutes for: cross-file consistency, matches-surrounding-style. The fix lands in the matching
docs/standards/volume, or inCLAUDE.md/AGENTS.mdwithin the thin-entry budget the launch sediment pass defines. Navigation pointers over prose. - Tool surface — the drag was tooling itself: expensive or token-inefficient MCP calls, missing automation, checks too slow to be run when they matter. The fix lands in
.mcp.json,scripts/, hooks, or OMC config. - Information surface — the agent needed a signal it could not reach: dev-server logs, service state, third-party readonly access. The fix tees the log, exposes the state, or documents the access path.
The split rests on where enforcement pressure lives: implementation contexts carry the most of it (exploration, writing, and debugging all at once); review contexts receive a diff with none of it. Standards therefore belong to reviewers and checks — never to more instructions loaded onto the implementer.
Show full SKILL.md (346 more words)Show less
Proposal and landing
- Present findings ranked by severity, each as
finding → surface → intended change, with one line of instrument evidence (which instrument, what it showed). - Stop for user approval. Each line is individually approvable or vetoable.
- Write approved findings to their surfaces. Before writing any steering prose, call the Skill tool with
agent-doc-disciplineand pass its verification checklist. A newly installed deterministic check must be proven to bite before it counts as landed: run it clean once, then demonstrate it failing on a deliberately introduced violation, then revert the violation. A check that cannot be shown failing goes back to the proposal — a guardrail nobody has seen fire is decoration, not protection. - Record where each finding landed — one file location per line — so the next refit starts from the record, not from memory. A refit on a launch-run session starts from that run's sediment list; a launch run may defer a lesson to a later refit by naming it.
Headless refit (unattended invocation)
Refit is user-invoked, but its survey does not need the user at the keyboard to run — only to dispose. A host scheduler (cron, CI timer, an automation tool) may start a headless agent session that invokes this skill; the survey runs to its natural boundary under the same contract:
- The survey reads the same instruments and lands nothing anywhere: headless refit produces the proposal list only —
finding → surface → intended change, each with one line of instrument evidence — written to.omc/refit/pending-proposals.mdand, when a notification channel is configured (configure-notifications), summarized there so the user learns a survey is waiting. - Nothing reaches a surface without the user's approval, exactly as in an interactive refit: proposals wait ranked, each independently vetoable, and the next interactive refit starts from the pending list instead of re-running the survey.
- An empty survey is stated plainly ("no findings"), never padded — inventing findings is the same violation as skipping the survey.
Output
- Findings ranked by severity, each with evidence, surface, and intended change — every line independently decidable
- After approval: what landed and where
- Declined findings, with reasons
© Yeachan-Heo, 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 skills/refit of Yeachan-Heo/oh-my-claudecode.
Open the folder on GitHubat commit 454bae0
Compare with similar skills
Refit Environment Retrospective 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 |
|---|---|---|---|---|---|---|
| Refit Environment Retrospective this skillYeachan-Heo/oh-my-claudecode | 40k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Agent Setup Health Audittw93/Waza | 7.2k | — | ~5.2k | Automated safety check: Notes | MIT | |
| Working With Claude Code Docsobra/superpowers-developing-for-claude-code | 142 | — | ~1.5k | Automated safety check: Pass | None | |
| Directional Promptingkingbootoshi/directional-prompting | 143 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Agenticashibing624/agentica | 352 | — | ~1.8k | Automated safety check: Notes | Apache-2.0 | |
| Claude Code Mastery Squadohmyjahh/xquads-squads | 277 | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Working With Claude Code Docs
obra/superpowers-developing-for-claude-code
Looks up official Claude Code documentation stored as reference files instead of guessing about CLI commands, configuration, or plugin APIs.
Directional Prompting
kingbootoshi/directional-prompting
Write prompts, system instructions, agent directives, slash commands, and skill descriptions using two stacked layers — outcome-first (define the destination, success criteria, stopping condition)…
Agentica
shibing624/agentica
How to answer questions about the agentica product you are running inside — CLI flags, config.yaml profiles, API keys, models, sessions, resume, workspace, AGENTS.md standing rules, skills, logs…
Claude Code Mastery Squad
ohmyjahh/xquads-squads
Routes a request to one of eight specialist agents covering hooks, skills, subagents, MCP integration and context engineering for Claude Code.
Vault Setup
earlyaidopters/second-brain
Interactive Obsidian vault configurator. An agent skill from earlyaidopters/second-brain.
More from Yeachan-Heo/oh-my-claudecode
All 47 skills in this repoAsk Advisor Routing
Yeachan-Heo/oh-my-claudecode
Sends a question or task to another locally installed agent CLI, such as Codex or Gemini, through omc ask and saves the answer as a file.
Ask Navigator
Yeachan-Heo/oh-my-claudecode
Charts a foggy effort into a map of decision tickets on the repo's issue tracker and works through them one per session, producing decisions rather than deliverables.
Self-Improve Evolutionary Loop
Yeachan-Heo/oh-my-claudecode
Runs an autonomous improvement loop on a repository: agents propose and execute plans, a tournament picks the winner by benchmark, and each round is recorded and plotted.
Autopilot
Yeachan-Heo/oh-my-claudecode
Takes a short product idea through requirements, design, planning, parallel implementation, QA cycles and multi-reviewer validation to produce working code.
OMC Mode Cancellation
Yeachan-Heo/oh-my-claudecode
Detects and gracefully cancels whichever OMC mode, autopilot, ralph, swarm, pipeline, or team, is currently active, then clears its state.
Hierarchical AGENTS.md Generator
Yeachan-Heo/oh-my-claudecode
Maps a codebase directory by directory and writes linked AGENTS.md files, each pointing to its parent, to document what each area contains.
Related
Categories
Questions about Refit Environment Retrospective
What does Refit Environment Retrospective do?
Reads an agent environment's own traces, friction reports and logs across sessions, then proposes fixes on the surface that owns each one, only with your approval. Refit studies the environment the agent worked in rather than the code it produced.json scripts and CI workflows.
When should I use Refit Environment Retrospective?
Refit Environment Retrospective fits situations like: after several sessions where the agent kept tripping on the same check; turning recorded friction into lint rules, hooks or doc changes; auditing which of a repo's checks are unwired or silently broken.
How do I install Refit Environment Retrospective in Claude Code?
Run `npx skills add Yeachan-Heo/oh-my-claudecode --skill refit -a claude-code`. Or copy the skill folder (skills/refit in Yeachan-Heo/oh-my-claudecode) into .claude/skills/refit in your project. Claude Code loads it when a task matches its description.
How do I install Refit Environment Retrospective in Codex?
Run `npx skills add Yeachan-Heo/oh-my-claudecode --skill refit -a codex`. Or copy the skill folder (skills/refit in Yeachan-Heo/oh-my-claudecode) into .agents/skills/refit in your project. Codex loads it when a task matches its description.
Can I use Refit Environment Retrospective 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 Yeachan-Heo/oh-my-claudecode --skill refit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/refit, .gemini/skills/refit, .github/skills/refit and .opencode/skills/refit in your project.
What does Refit Environment Retrospective need to run?
SKILL.md names no scripts, command-line tools or credentials: Refit Environment Retrospective is instructions for the agent only. Our summary lists: OMC instrumentation such as trace timelines and session friction reports.
Does Refit Environment Retrospective 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 Refit Environment Retrospective 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 Refit Environment Retrospective use?
Refit Environment Retrospective 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 Refit Environment Retrospective use?
About 1.4k tokens (SKILL.md is roughly 5.7k 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 Refit Environment Retrospective?
Skills that share tags, products or a category with Refit Environment Retrospective: Agent Setup Health Audit (tw93/Waza, 7.2k stars), Working With Claude Code Docs (obra/superpowers-developing-for-claude-code, 142 stars), Directional Prompting (kingbootoshi/directional-prompting, 143 stars) and Agentica (shibing624/agentica, 352 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Refit Environment Retrospective?
Yeachan-Heo (a GitHub user) maintains it in Yeachan-Heo/oh-my-claudecode, which has 39,720 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on October 8, 2026.
Source: Yeachan-Heo/oh-my-claudecode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.