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.
npx skills add Obsidian-Owl/specwright --skill sw-doctorgit clone --depth 1 https://github.com/Obsidian-Owl/specwrightWrote 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.
[](https://agentmods.dev/skills/obsidian-owl/specwright/sw-doctor)<a href="https://agentmods.dev/skills/obsidian-owl/specwright/sw-doctor"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-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.
<a href="https://agentmods.dev/skills/obsidian-owl/specwright/sw-doctor"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00043 | $0.01485 |
| Opus 5 | $0.00022 | $0.00743 |
| Sonnet 5 | $0.00009 | $0.00297 |
| Haiku 4.5 | $0.00004 | $0.00148 |
Grade A, and why
sw-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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specwright Doctor
Goal
Validate that a Specwright installation is coherent across the tracked project-artifact root, shared repo-state root, and per-worktree session model, then print actionable repair hints using the same runtime-root and ownership vocabulary the adapters expose.
Inputs
{projectArtifactsRoot}/config.json{projectArtifactsRoot}/CONSTITUTION.mdand{projectArtifactsRoot}/CHARTER.md{worktreeStateRoot}/session.jsonwhen present{repoStateRoot}/work/*/workflow.json{workArtifactsRoot}/{workId}/approvals.mdand{workDir}/review-packet.mdwhen present- gate skill files, hook config, and configured commands
Outputs
- PASS/WARN/FAIL health table
- Optional backfill of
prNumberandprMergedAton the owning work'sworkflow.json
Constraints
Pre-condition (LOW freedom):
- If neither the shared layout nor the legacy fallback can be resolved, stop
immediately and tell the user to run
/sw-init. - Always report layout status first:
shared/session,legacy fallback, ormissing. - When layout resolves, describe the active runtime mode explicitly:
project-visibleruntime roots under.specwright-local/are the preferred interactive default;git-adminroots under.git/specwright/are compatibility mode.
Checks (LOW freedom — run all 13 in order):
- Anchor docs — tracked Constitution and Charter exist and are non-empty
- Config — tracked config parses and contains
gatesandgit - State — current session parses when present, every discovered workflow parses with a null or fresh per-work lock, and layout status is explicit
- Gates — enabled gate skills exist
- Build command — configured build command exists on PATH
- Test command — configured test command exists on PATH
- Format/lint — configured format or lint commands exist on PATH
- Hooks — hook manifest parses and referenced hook files exist
- Backlog config — configured backlog target is usable
- ast-grep — INFO availability only
- OpenGrep — INFO availability only
- LSP — PASS/WARN/INFO based on available platform or standalone LSP
- STATE_DRIFT — enumerate repo-wide workflows and flag shipped units with
status=shippedandprNumber=null
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.
- 9d ago First seen · 149 lines · 43 tokens per session scan A d2fef13ddac6
sw-doctor is a skill published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,485 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
ai-development-guide
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
recipe-diagnose
Investigate problem, verify findings, and derive solutions.
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
logic-review
Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Trigger when a user shares code and suspects something is wrong without naming a concrete failure — phrases like "review this", "does this look right", "check this function", "audit this…
logic-fix-all
Autonomous repository-wide audit-and-fix pipeline: health → review → locate/explain → fix → diff-verify → iterate until clean. Starts with a mandatory consent prompt (token-intensive); after consent runs hands-free. Trigger when the user wants ALL logic issues found and fixed — "fix everything", "fix all logic…
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…