A read-only diagnostic command for checking whether an SDLC pipeline is set up correctly. It reports missing add-ons, runtime checks, active stack profiles, model-routing settings, and the cost baseline.

Use it to inspect pipeline dependencies, confirm stack detection, review runtime status, and troubleshoot setup before starting feature work.

It helps explain why a pipeline may not run as expected without making project changes, except for creating a missing cost-baseline scaffold. It also shows which technology profile would be selected.

doctor — Command for Claude Code by AratKruglik

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add AratKruglik/claude-sdlc

Claude Code

/plugin install sdlc

Made for: Claude Code.

Or install sdlc, the plugin that ships this one along with the rest of its 3 skills, 5 commands, 5 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/commands/aratkruglik/claude-sdlc/doctor/github.svg)](https://agentmods.dev/commands/aratkruglik/claude-sdlc/doctor)

Your own site

<a href="https://agentmods.dev/commands/aratkruglik/claude-sdlc/doctor"><img src="https://agentmods.dev/badge/commands/aratkruglik/claude-sdlc/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/commands/aratkruglik/claude-sdlc/doctor"><img src="https://agentmods.dev/badge/commands/aratkruglik/claude-sdlc/doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,704 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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	$0.00038	$0.04704
Opus 5	$0.00019	$0.02352
Sonnet 5	$0.00008	$0.00941
Haiku 4.5	$0.00004	$0.00470

Measured 6d ago against content hash d879764f1d5c, 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 1 finding 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 6d 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

2. **Run the same preflight algorithm as Step 0a in `pipeline-orchestrator/SKILL.md`** (Step 0a-2 through 0a-3 — enumerate available skills via `mcp__skills__list_skills` with FS fallback to `~/.claude/plugins/cache/{plu

plugins/sdlc/commands/doctor.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdlc:doctor

Snapshot of the pipeline's runtime environment. Reuses the same Step 0a preflight code-path that /sdlc:start runs on every invocation, but in a diagnostic mode that never aborts.

What this command does

Locate the runtime dependencies file. Try these paths in order, take the first that exists:
- ~/.claude/plugins/cache/sdlc/runtime-dependencies.json
- <repo>/plugins/sdlc/runtime-dependencies.json (development checkout)
If neither exists, print 🔌 Dependency preflight: no runtime-dependencies.json found. and skip step 2.
Run the same preflight algorithm as Step 0a in pipeline-orchestrator/SKILL.md (Step 0a-2 through 0a-3 — enumerate available skills via mcp__skills__list_skills with FS fallback to ~/.claude/plugins/cache/{plugin}/skills/{skill}/SKILL.md, then compute per-dependency status). DO NOT enforce policy in /sdlc:doctor — block does NOT exit here. Just collect status.
Locate active stack profiles. Doctor always computes this fresh — same discipline as its git-flow check below ("a doctor that echoes a stale cache cannot diagnose a stale cache"): run scripts/detect-stack.py --repo . (resolve the path the same three-way way as every other script: ${CLAUDE_PLUGIN_ROOT}/scripts/detect-stack.py, then the installed cache copy, then <repo>/plugins/sdlc/scripts/detect-stack.py in a development checkout). This is the exact same algorithm pipeline-orchestrator/SKILL.md Step 0b runs — reusing the script instead of re-deriving the Glob+Read+parse sequence by hand keeps this command from silently drifting out of sync with it.

If python3 is unavailable, fall back to the inline algorithm (Glob ~/.claude/plugins/cache/**/stack.md, parse frontmatter, evaluate detect rules) — the same fallback Step 0b's full scan uses.

Separately, check whether ~/.claude/.sdlc-stack-cache/{sha1(realpath(cwd))[:16]}.json exists (the file the SessionStart hook writes) and report its age. If it disagrees with the fresh detection above (different primary_profile.stack, or different aspect_ties), flag it exactly like the git-flow cache-disagreement check — that is a repo whose installed-plugin set or detectable files changed since the hook last ran. Doctor reports the disagreement; it does not decide which one /sdlc:start will trust (Step 0b's own trust rules do that).

Read the full file on GitHub · 279 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.

6d ago Changed · +22 lines d879764f1d5c
7d ago First seen · 257 lines · 38 tokens per session scan B b576a0d67ad6

Subscribe to this mod's changes

doctor is a command published in the GitHub repository AratKruglik/claude-sdlc (33 stars, last pushed 6d ago), licensed MIT. It adds 38 tokens to every session and 4,704 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Debugging Project management

bug-report

Draft a bug report issue for lean4-skills.

cameronfreer/lean4-skills · 13 tokens

triage

Query open Node bugs, classify by priority and sub-team, suggest assignments, and generate a triage summary.

openshift-eng/ai-helpers · 21 tokens

speckit.companion.doctor

Report on a spec's run health — unfinished steps, unjournaled tasks, step bleed, drift you can judge, a step that closed having verified nothing, a step that closed without the file it promised, and why completion did not land (read-only, retroactive, never halts).

alfredoperez/speckit-companion · 59 tokens

doctor