doctor is agent-read markdown (skill) from okisdev/claude-code-fusion: Audits the orchestration setup without changes for model drift, stale pins, and environment overrides. Use when routing behaves oddly, after a CLI upgrade, or when model drift is suspected..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
Audit the orchestration setup and report findings as a short checklist with a clear verdict per item.
Environment overrides captured at invocation:
- CLAUDE_CODE_SUBAGENT_MODEL: !`sh -c 'printenv CLAUDE_CODE_SUBAGENT_MODEL || echo "(unset)"'`
- ANTHROPIC_MODEL: !`sh -c 'printenv ANTHROPIC_MODEL || echo "(unset)"'`
- ANTHROPIC_DEFAULT_HAIKU_MODEL: !`sh -c 'printenv ANTHROPIC_DEFAULT_HAIKU_MODEL || echo "(unset)"'`
- ANTHROPIC_DEFAULT_FABLE_MODEL: !`sh -c 'printenv ANTHROPIC_DEFAULT_FABLE_MODEL || echo "(unset)"'`
Checks to perform:
1. A set CLAUDE_CODE_SUBAGENT_MODEL can silently override every agent model pin (Claude Code behavior as observed on 2.1.x); flag it as a problem unless the user says it is deliberate.
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_pq4cnznymjloqj5b
GET https://markdownregistry.com/api/v1/resolve?ref=okisdev/claude-code-fusion/doctor
GET https://markdownregistry.com/api/v1/blob/e414c66b8d0f89df87fe0bd65e11967043937f742b779968b50f033a43004036
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
okisdev/claude-code-fusion · plugins/codex/skills/adversarial-review/SKILL.md · Runs a read only Codex review that challenges implementation and design decisions. Use when preparing to merge a…
okisdev/claude-code-fusion · plugins/codex/skills/history/SKILL.md · Lists canonical local Codex companion history with resumable thread IDs. Use when resuming or auditing past Codex work.
okisdev/claude-code-fusion · plugins/codex/skills/rescue/SKILL.md · Forwards a request to the Codex rescue agent without exposing arguments to a shell. Use when Fusion routing or the user…
okisdev/claude-code-fusion · plugins/codex/skills/result/SKILL.md · Shows or waits for a stored Codex job result. Use when collecting a background Codex job named by ID.
okisdev/claude-code-fusion · plugins/codex/skills/review/SKILL.md · Runs a read only Codex review of local Git state. Use when the user wants Codex to review uncommitted or branch changes.
okisdev/claude-code-fusion · plugins/codex/skills/setup/SKILL.md · Checks whether the local Codex runtime is ready. Use when installing for the first time, after a CLI upgrade, or after…
okisdev/claude-code-fusion · plugins/codex/skills/status/SKILL.md · Shows active and recent Codex jobs. Use when asked what Codex is doing or whether a job is still running.
okisdev/claude-code-fusion · plugins/codex/skills/task/SKILL.md · Runs a Codex task through the companion runtime. Use when delegating a bounded implementation, investigation, or…
okisdev/claude-code-fusion · plugins/fusion/skills/config/SKILL.md · Configures model defaults, capability scores, and orchestration posture across the Claude, Grok, and Codex…
blackbelttechnology/pi-agent-dashboard · packages/extension/.pi/skills/doctor/SKILL.md · Diagnose why pi-flows, the Anthropic-messages bridge, model resolution, a pi install, a peer, a plugin/bridge, or a…
yonatangross/orchestkit · src/skills/doctor/SKILL.md · OrchestKit doctor for health diagnostics across manifest integrity, hook configuration, skill validation, agent…
yonatangross/orchestkit · plugins/ork/skills/doctor/SKILL.md · OrchestKit doctor for health diagnostics across manifest integrity, hook configuration, skill validation, agent…
agenttoolkit/altk-evolve · platform-integrations/claw-code/plugins/evolve-lite/skills/evolve-lite/doctor/SKILL.md · Diagnose evolve health on Claude — verify the CLAUDE.md @import is actually loading the thin EVOLVE.md into sessions
agenttoolkit/altk-evolve · platform-integrations/claude/plugins/evolve-lite/skills/evolve-lite/doctor/SKILL.md · Diagnose evolve health on Claude — verify the CLAUDE.md @import is actually loading the thin EVOLVE.md into sessions
crisandrews/clawcode · skills/doctor/SKILL.md · Run diagnostic checks on the agent workspace. Triggers on /agent:doctor, "diagnóstico", "diagnostico", "doctor"…
