doctor
Skill0 starsChanged 59 days agoMITView on GitHub
Verify codex-paired-superpowers prerequisites are correctly installed and configured. Use when the plugin reports setup errors, when installing for the first time, when troubleshooting "module not found" / "codex not on PATH" / authentication errors, or any time you want a fast health check of the install.
85 other projects use a version of this.
Adopted by
Most recently taken up by
- aaroncohn/babysittertheir own version, first seen Nov 16, 2026
- Yomudogly/oh-my-agytheir own version, first seen Nov 16, 2026
- timursafiullin/aodtheir own version, first seen Nov 15, 2026
- dcamunas/model-routertheir own version, first seen Nov 15, 2026
- Noah-OS/longhaultheir own version, first seen Nov 15, 2026
- stunt-double/stuntdouble-mcptheir own version, first seen Nov 8, 2026
Used with
Projects with it also use uninstall, cancel and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AnthropicSkilluninstall
Uninstall a community skill that was installed via the hub. Confirms before deleting files, refuses to touch first-party plugin skills, and logs every action. Use when the user wants to fully remove a community skill ("uninstall [skill]", "remove this skill") rather than just disable it.
Also in 6 projects that use this
woosikkimSkillcancel
Clear any stale OMC-Slim state
Also in 3 projects that use this
ibahgatSkillmode
Inspect or switch omi operating mode/profile for speed, depth, autonomy, or strict quality gates.
Also in 3 projects that use this
BlockSkillopen
Open markdown documents in Penpal for collaborative review. Use when you want a human to review a document, plan, or research artifact.
Also in 3 projects that use this
QinghongLinSkilleditor
Read analyst.json and detective.json, make all editorial decisions — what the blog argues, which findings matter, narrative arc and section structure. No visual design. Outputs editor.md (prose) and editor.json (structure with edt_xx IDs).
Also in 3 projects that use this
AnthropicSkillstatus
Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.
Also in 15 projects that use this
Other versions85 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 85
- Yeachan-Heo/oh-my-codex★ 34ksame name
- jihe520/MathModelAgent★ 6.2ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
- fakechris/obsidian_vault_pipeline★ 165same name
- NoobyGains/godmode★ 120same name
- Rich627/whatsapp-claude-plugin★ 114same name
- bluzir/claude-code-design★ 102same name
- jjanczur/tyran★ 79same name
- svy04/ballast★ 73same name
- Hainrixz/agente-pagokit★ 68same name
75 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- app-autopilotSkill
- autopilotSkill
- brainstormingSkill
- executionSkill
- honest-reportingSkill
- receiving-code-reviewSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- writing-plansSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 64 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Run the bundled diagnostic script and report results to the user.
- Distinctive: line 17
Read the output. Each check produces one of:
- Very specific: line 22
If any check FAILs, surface the exact fix: line printed under that check verbatim.
- Distinctive: line 24
If all checks pass, confirm "All checks green.
- Distinctive: line 34
Do NOT run the doctor automatically before every skill invocation — that adds latency.
“Common” is measured: kept by at least 6 in 10 of the 64 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Doctor — codex-paired-superpowers preflight
Run the bundled diagnostic script and report results to the user.
What to do
- Run the script:
It's oncodex-paired-doctorPATHwhile the plugin is enabled (Claude Code installsbin/entries automatically). - Read the output. Each check produces one of:
- PASS — the prerequisite is in place.
- WARN — non-blocking; the user should review if they hit issues.
- FAIL — blocking; the user must address before the plugin can do useful work.
- If any check FAILs, surface the exact
fix:line printed under that check verbatim. Don't paraphrase — the fix lines are the commands the user runs to resolve the issue. - If all checks pass, confirm "All checks green. Plugin is ready to use." and stop. Don't pad the response with explanation.
When to invoke this skill
Invoke doctor proactively (without being asked) in these situations:
- The user has just installed the plugin and asks any "how do I get started" / "is this working" question.
- A skill (brainstorming, autopilot, etc.) errors with output mentioning:
Cannot find module,proper-lockfile,codex: command not found,codex not authenticated,ENOENT, or any "module-load" / "binary-not-found" pattern. These are setup-failure signatures; doctor pins them quickly. - The user explicitly asks "is my setup OK" / "check my install" / "diagnose" / "preflight" / similar.
Do NOT run the doctor automatically before every skill invocation — that adds latency. The signal is errors that match the patterns above, or explicit user request.
Machine-readable mode
For programmatic consumption (e.g., autopilot's Phase B.PRE may want to gate on doctor results), invoke with --json:
codex-paired-doctor --jsonOutput schema:
{
"summary": { "pass": N, "warn": N, "fail": N },
"checks": [
{ "status": "pass|warn|fail", "name": "...", "detail": "...", "fix": "..." | null }
]
}Exit code: 0 if all PASS or only WARN; 1 if any FAIL.
What the doctor checks
The full check list lives in bin/codex-paired-doctor (the source of truth). Current set:
- node — Node v20+ on PATH (required for
lib/codex-bridge/*modules + the bundled MCP server). - codex-cli —
codexon PATH (required for the Claude↔Codex 7-round loop via MCP). - codex-auth — codex credentials present (login state).
- git — git v2.5+ (worktree support required by autopilot's parallel slice dispatch).
- vendored-deps —
proper-lockfile+ transitive pure-JS deps present atnode_modules/(mailbox lockfile requirement). - bridge-cli —
lib/codex-bridge/cli.jsloads cleanly (catches corruption / missing deps that the vendored-deps check missed). - hooks — PostToolUse hooks present and executable.
- project-state-dir —
.codex-paired/in cwd is writable (informational; auto-created by autopilot when first needed). - models (v0.16.0) — resolves the four model roles (
planning,review,implement,implement_fallback) and printsrole: model effort (source); FAILs only on a malformedmodelsconfig; WARNs when the Codex model catalog (~/.codex/models_cache.json) lacks a configured model, lists a retirement date for it, does not support the configured effort, is unreadable, or is older than seven days. An absent catalog is not an error. - codex-transport (v0.16.0) — WARNs when
codex --versionis older than the version this release was validated against (0.153.4), and when this Codex build no longer offerscodex mcp-server(the transport the plugin uses).
Adding a new prerequisite? Update the script — the skill auto-tracks because it just runs the script verbatim.
11. agy (v0.17.0) — the availability report lists the Antigravity CLI (agy, Gemini); the models check also validates roles with cli: agy against agy models (WARN when the configured id is not listed, or when a role uses agy but it is not installed). Installs that never set cli: agy are unaffected.
12. review-panel (v0.19.0) — resolves the configured review panels; WARNs when a member uses the same model as the implement role (self-review:<member_id>: code reviewed by the model that wrote it) or when the panel configuration cannot be resolved.
13. worktrees (v0.19.0) — lists checkouts this plugin left behind (a crashed or halted run) with each one's kind, age and why it is kept; WARN when there are any, never FAIL. Worktrees the user created are ignored, and only the current user's processes are inspected when deciding whether a checkout is in use. Remove the safe ones with node lib/codex-bridge/cli.js worktree-reap --apply --repoRoot <repo> (without --apply it only lists).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

