doctor
Skill115 starsChanged 7 days agoMITView on GitHub
Use when GodMode skills do not seem to trigger, when the user asks whether GodMode is installed or working, or after installing or updating the plugin on any harness
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 56 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
No exceptions. No workarounds.
- Distinctive: line 35
If the script itself cannot run, report the exact error and the install root you derived.
- Distinctive: line 65
Run the script from the derived install root
“Common” is measured: kept by at least 6 in 10 of the 56 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
Checks the GodMode installation from inside the running harness and reports what it finds. The bootstrap that makes skills trigger is injected at session start; when it is missing, every other skill is inert, so this check comes first.
The Prime Directive
DIAGNOSE THE INSTALL BEFORE BLAMING THE SKILLSNo exceptions. No workarounds. No shortcuts.
When to Use
Required:
- The user asks "is GodMode working?", "why didn't GodMode activate?", or runs the doctor command
- Right after installing or updating GodMode on a new harness or machine
- Skills that should have fired (design before code, verification before "done") did not
Skip:
- Everything else; this skill only inspects the install
The Protocol
- Locate the install root. It is the directory that contains the
skills/folder holding this file. Do not guess a path from memory; derive it from where this skill was loaded. - Run the doctor script with the shell:
<install-root>/hooks/run-hook.cmd doctor. On Windows without Git Bash the wrapper exits silently with no output; say so and point the user at installing Git for Windows. - Read every line of the output.
oklines pass,FAILlines are the problem,infolines describe the environment (harness, platform, version). - Report the harness and version detected, each failure with the fix the script printed, and whether a fresh session is needed (the bootstrap only injects at session start).
- If the script itself cannot run, report the exact error and the install root you derived. Do not claim the install is healthy without the script's output.
What the script checks
| Check | Why it matters |
skills/using-godmode/SKILL.md readable | The session-start hook injects this file; without it nothing triggers |
| Skill count above 20 | A partial install or a wrong root |
| Hook scripts executable and LF-terminated | GodMode 1.0 shipped without the executable bit, so the hook never ran (issues #1, #2, #4) |
hooks.json quotes the plugin root | Single quotes stop the variable from expanding |
session-start prints the Claude Code JSON shape | The hook's output is what the harness reads |
Cognitive Traps
| Rationalisation | Truth |
| "Skills exist on disk, so GodMode is installed" | Files on disk do nothing until the bootstrap reaches the model |
| "The hook probably ran" | Run the script; its output is the only evidence |
| "I remember the install path" | Paths differ per harness and version folder; derive it from this file |
| "It worked last session" | Plugin updates change the install folder; recheck after every update |
| "No output means no problem" | No output means the wrapper could not find bash; that is a failure to report |
Guardrails
Never:
- Declare the install healthy without the script's output in this session
- Edit the user's harness settings to "fix" things; report and let the user decide
- Guess a harness from the prompt text; read the
info harnessline
Always:
- Run the script from the derived install root
- Quote failures verbatim with the printed fix
- Say whether a new session is needed
Connections
godmode:using-godmode: the bootstrap this skill verifies is presentgodmode:environment-awareness: when the failure is a shell or platform problem rather than an install problem
Other versions75 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 75
- Yeachan-Heo/oh-my-codex★ 34ksame name
- jihe520/MathModelAgent★ 6.2ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
- fakechris/obsidian_vault_pipeline★ 162same name
- Rich627/whatsapp-claude-plugin★ 114same name
- bluzir/claude-code-design★ 102same name
- jjanczur/tyran★ 81same name
- svy04/ballast★ 73same name
- Hainrixz/agente-pagokit★ 68same name
- crisandrews/ClawCode★ 63same name
65 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.
Used alongsideProjects with it also use uninstall, mode 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 5 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
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 10 projects that use this
VercelSkillsetup
Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".
Also in 21 projects that use this
MicrosoftSkillinit
Also in 5 projects that use this
HK-hubSkilldistill
Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean. Use when the user asks to simplify, declutter, reduce noise, remove elements, or make a UI cleaner and more focused.
Also in 3 projects that use this
- +1 more from anthropics
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-briefingSkill
- codebase-conventionsSkill
- code-reviewSkill
- completion-gateSkill
- cross-model-reviewSkill
- delegated-executionSkill
- environment-awarenessSkill
- error-recoverySkill
- fault-diagnosisSkill
- groundingSkill
- inline-executionSkill
- intent-discoverySkill
- knowledge-captureSkill
- merge-protocolSkill
- model-routingSkill
- parallel-executionSkill
- performance-tuningSkill
- project-bootstrapSkill
- quality-gatesSkill
- rationaleSkill
- reference-firstSkill
- review-responseSkill
- security-protocolSkill
- system-designSkill
- task-planningSkill
- team-orchestrationSkill
- test-firstSkill
- ui-engineeringSkill
- ui-researchSkill
- using-godmodeSkill
- workspace-isolationSkill
- writing-skillsSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

