doctor

A diagnostic tool for a learning-loop installation that runs health checks, reports problems, and confirms fixes after you approve them.

In plain words
What is it for?
Use it to inspect installation health, repair approved issues one at a time, verify repairs, or scan data files for leaked credentials.
Why use it?
It helps find setup or configuration issues without changing them automatically. A separate redaction mode checks plugin data for exposed credentials.

Skill for Claude CodeCodex

Part of the learning-loop plugin — 24 skills, 20 agents, 6 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/robinslange/learning-loop/doctor
Any agent
npx skills add robinslange/learning-loop --skill doctor
Clone the repo
git clone --depth 1 https://github.com/robinslange/learning-loop

Made for: Claude Code, Codex.

Or install learning-loop, the plugin that ships this one along with the rest of its 24 skills, 20 agents, 6 hooks.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,768 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00058 $0.02768
Opus 5 $0.00029 $0.01384
Sonnet 5 $0.00012 $0.00554
Haiku 4.5 $0.00006 $0.00277

Measured 3d ago against content hash 1252ddd967a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/doctor/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/learning-loop:doctor

A read-mostly diagnostic. Runs the health-check library, presents the result, and walks you through fixes one at a time.

If invoked with --redact, skip the normal health-check steps and run the Redact mode section instead.

Paths

Resolve PLUGIN_DATA, VAULT, and the plugin root per ${CLAUDE_PLUGIN_ROOT}/skills-shared/paths-preamble.md (read it and apply).

fix strings in the health-check JSON prefix paths with a user-facing PLUGIN shorthand for the plugin root (defined in guide/troubleshooting.md; the guide/ tree is not shipped with the plugin). Show them verbatim when the user will run the command; substitute ${CLAUDE_PLUGIN_ROOT} for the leading PLUGIN segment when you execute it yourself via Bash.

Step 1: Run all checks

node ${CLAUDE_PLUGIN_ROOT}/scripts/health-check.mjs --full --json

Parse the JSON. The schema:

{
  "ts": "...",
  "ran": "full",
  "checks": [
    { "id", "name", "status": "ok" | "fail", "severity": "ok" | "warn" | "fail", "detail", "fix" }
  ]
}

Step 2: Present the report

Format the dashboard like this:

learning-loop doctor
====================

Health checks (N passed, M warnings, F issues):

  ✓ Node.js                     v25.9.0
  ✓ Claude Code                 2.1.145
  ⚠ ~/.local/bin on PATH        not on PATH
    → Add to your shell rc: export PATH="$HOME/.local/bin:$PATH"
  ✗ ll-search binary            missing at /Users/.../bin/ll-search
    → Run /learning-loop:init to re-download the binary
  …

F issues, M warnings.

Icon rules:

  • when status === "ok"
  • when status === "fail" && severity === "warn"
  • when status === "fail" && severity === "fail"

Step 3: If F + M === 0

Print ✓ All checks pass. Nothing to fix. and exit.

Step 4: Otherwise, iterate fails first, then warns

For each check with status === "fail":

  1. Show the check:
    ✗ <name>: <detail>
      Suggested fix: <fix>
    
  2. Ask via AskUserQuestion:
    • Option A: Fix this (auto-runnable) — only when the fix is in the auto-runnable table below
    • Option A': Run the suggested command and tell me when done — when the fix is manual
    • Option B: Skip — I'll handle this later
    • Option C: Stop the doctor session — exits cleanly
  3. On choice A: execute the corresponding fix command via Bash. After it finishes, re-run node ${CLAUDE_PLUGIN_ROOT}/scripts/health-check.mjs --full --json and find the same check by its id field. Report:
    • ✓ Fixed (new state: <detail>) if the check now returns ok
    • ⚠ Still warning: <new detail> if it improved to warn
    • ✗ Still failing: <new detail> if it didn't help (don't loop — move on)
  4. On choice A' (manual): print the command, then ask Done? [Y]es / [N]o. On Yes, re-run node ${CLAUDE_PLUGIN_ROOT}/scripts/health-check.mjs --full --json and find the same check by its id field, then report as above.
  5. On choice B: track as skipped and move to next.
  6. On choice C: print summary and exit.

Read the full file on GitHub · 214 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 214 lines · 58 tokens per session scan A 1252ddd967a3

Subscribe to this mod's changes

doctor is a skill published in the GitHub repository robinslange/learning-loop (11 stars, last pushed 12d ago), licensed Apache-2.0. It adds 58 tokens to every session and 2,768 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens