A diagnostic skill for checking a project's .claude configuration, including commands, paths, hooks, and agents.

Use it after initializing or updating a project configuration to identify issues that need fixing.

It finds broken references, invalid settings, missing files, and other setup problems before they cause failures.

How yash-gadodia/claude-init configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to yash-gadodia/claude-init. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/yash-gadodia/claude-init/main/.claude/skills/doctor/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/yash-gadodia/claude-init

Made for: Claude Code.

Or install claude-init, the plugin that ships this one along with the rest of its 11 skills, 1 command, 7 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yash-gadodia/claude-init/doctor/github.svg)](https://agentmods.dev/skills/yash-gadodia/claude-init/doctor)

Your own site

<a href="https://agentmods.dev/skills/yash-gadodia/claude-init/doctor"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/doctor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yash-gadodia/claude-init/doctor"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,960 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.01960
Opus 5	$0.00021	$0.00980
Sonnet 5	$0.00008	$0.00392
Haiku 4.5	$0.00004	$0.00196

Measured 3d ago against content hash 140a560e82f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

doctor scanned grade B with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- [ ] No dangling symlinks under `.claude/rules/` — `find .claude/rules -xtype l` should return nothing (shared rule libraries are linked in via symlink; a broken link silently drops those rules from context)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- [ ] Any `` !`cmd` `` or ```` ```! ```` shell-preprocessing blocks run read-only commands only (never `rm`, `curl http://...`, writes, or long-running ops)

.claude/skills/doctor/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doctor: Validate Your Config

Run diagnostics on the .claude/ configuration and report issues.

Checks

1. CLAUDE.md Health

Exists at repo root
Under 80 lines (warn if over, error if over 200)
All @import paths resolve to existing files
Commands section: verify each command actually runs (e.g., npm test --help, cargo test -- --help)
No placeholder text left from templates (e.g., <your-framework-here>)
No content that merely restates what Claude could derive by reading the codebase (full dependency/version lists duplicating package.json, directory trees ls would show, verbatim README paragraphs) — flag for trimming, matching Claude Code's own /doctor CLAUDE.md-trimming check (changelog 2.1.206)

2. Agents

For each .claude/agents/*.md:

Valid YAML frontmatter (name, description present)
Model is valid (opus, sonnet, haiku, fable, inherit, or a full model ID)
Referenced tools exist
background is a boolean and memory is one of user/project/local if present
effort is one of low/medium/high/xhigh/max, isolation is worktree, color is one of red/blue/green/yellow/purple/orange/pink/cyan, and permissionMode is one of default/acceptEdits/auto/dontAsk/bypassPermissions/plan/manual — if present (per https://code.claude.com/docs/en/sub-agents frontmatter table)
No empty markdown body

3. Skills

For each .claude/skills/*/SKILL.md:

Valid YAML frontmatter
name matches the skill's directory name and is lowercase-kebab-case
Description is specific enough (not just "does stuff")
Description is third-person and contains a when-to-use trigger (Use when…, Use before…, or Auto-triggered…) — descriptions with no trigger won't reliably fire
Description is ≤1024 characters
Description does NOT summarize the workflow steps — a process summary in the description makes Claude follow the summary instead of reading the skill
Skill body has Red Flags / rationalization-rebuttal content and a verification step (the generated skills should all carry these)
SKILL.md body is under 500 lines (warn over ~150 — push long examples/scripts into sibling reference files)
If context: fork, verify no Task/Skill tool references in body (forked skills can't spawn subagents)
If context: fork, verify background is explicitly set (true or false) rather than omitted — since Claude Code 2.1.218 these skills default to running in the background, so an omitted field means a Claude Code upgrade can silently change the skill from blocking to backgrounded
If paths: frontmatter exists, verify globs match at least one file (dead scopes = skill never loads)
allowed-tools uses real tool names (Read, Edit, Write, Bash, Grep, Glob, Agent — not Tool, File, etc.)
Any !`cmd` or ```! shell-preprocessing blocks run read-only commands only (never rm, curl http://..., writes, or long-running ops)
Referenced scripts in scripts/ directory exist and are executable
Recommend running Claude Code's native /skill-doctor (2.1.261+) as a complementary check — it reports which loaded skills go unused and what they cost in context, which this structural review does not measure

Read the full file on GitHub · 113 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.

3d ago Changed · +1 lines 140a560e82f1
6d ago Changed 26f1af186972
11d ago First seen · 112 lines · 42 tokens per session scan B a6cd14ef2a85

Subscribe to this mod's changes

doctor is a skill published in the GitHub repository yash-gadodia/claude-init (5 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 1,960 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Debugging ai-native automation claude cli developer-tools

swiftui-performance-audit

Audit and improve SwiftUI runtime performance. Use for requests to diagnose slow rendering, janky scrolling, high CPU/memory usage, excessive view updates, or layout thrash in SwiftUI apps.

patrickserrano/lacquer · 45 tokens

github-ci-fix

Use when PR checks fail, CI is red, or GitHub Actions workflows break - systematically inspects failing checks via gh CLI, pulls logs, checks for flakiness and scopes the breaking commit, scopes external checks, then creates fix plan using existing plan skill.

patrickserrano/lacquer · 57 tokens

ios-debugger-agent

Build, run, and debug iOS apps on a simulator. Use when asked to run an iOS app, interact with the simulator UI, capture logs, or diagnose runtime behavior.

patrickserrano/lacquer · 42 tokens

native-app-profiling

Profile native macOS/iOS apps for CPU hotspots, hangs, and hitches using Instruments traces. Use when asked to identify performance hotspots, profile CPU usage, or diagnose slow code paths without opening Instruments.

patrickserrano/lacquer · 47 tokens

refactor

Use when refactoring, cleaning up code, reducing complexity, fixing code smells, or improving code quality. Audits code for dead code, nesting, and patterns.

tartinerlabs/skills · 36 tokens

xcsym

Symbolicate and triage iOS/macOS crash reports (.ips, MetricKit, legacy .crash, Xcode Organizer .xccrashpoint) via the xcsym CLI. Use when given a crash file to diagnose, when TestFlight/App Store Connect crashes need triage, when a crash comes back unsymbolicated, or when asked what kind of crash something is.

patrickserrano/lacquer · 82 tokens

claude-init: Skill for Claude Code