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-debuggit 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-debug)<a href="https://agentmods.dev/skills/obsidian-owl/specwright/sw-debug"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-debug/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-debug"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-debug.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 | $0.00033 | $0.00860 |
| Opus 5.5 | $0.00013 | $0.00344 |
| Sonnet 5.5 | $0.00007 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
sw-debug 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specwright Debug
Goal
First-class debugging path. Scope the problem, investigate concurrently,
diagnose with evidence, then decide: fix it now, log it, or defer. Operates
autonomously, applying protocols/decision.md for the fix/log/defer decision.
Inputs
- Problem description (argument or recent error context)
- Initial evidence: error messages, logs, failing test output
{projectArtifactsRoot}/config.json—backlog.typeandbacklog.label- Codebase files — read during investigation
Outputs
diagnosis.mdat{workArtifactsRoot}/{id}/diagnosis.md— always producedspec.mdat{workArtifactsRoot}/{id}/spec.md— Fix path only (2-3 acceptance criteria)decisions.mdat{workArtifactsRoot}/{id}/decisions.md— fix/log/defer decision recorded perprotocols/decision.md
Constraints
Stage boundary (LOW freedom):
Follow protocols/stage-boundary.md. Investigate and diagnose. NEVER write code,
run tests, branch, or commit. Fix path: produce spec.md, handoff to /sw-build.
Scope (MEDIUM freedom):
- If argument provided, use it. If no argument, infer from recent error context (last failed command, error output in conversation). If genuinely undetermined, apply DISAMBIGUATION: choose the most likely problem from available context.
- Collect evidence: error messages, stack traces, failing tests. Define boundary.
Investigate (HIGH freedom):
Delegate concurrently per protocols/delegation.md: specwright-researcher (code
context, call paths) and specwright-architect (root cause, blast radius).
Diagnose (MEDIUM freedom):
Write diagnosis.md: Problem (observed vs expected), Root Cause (confidence level,
file:line evidence), Blast Radius (affected / not affected), Fix Approach (high-level),
Alternatives Considered. If agents return insufficient evidence: produce low-confidence
diagnosis and note the gap in decisions.md.
Decision (MEDIUM freedom):
Apply protocols/decision.md DISAMBIGUATION + reversibility:
- Fix spans ≤3 files with local architectural scope → Fix it now (Type 2). Write
spec.md, handoff to
/sw-build. - Fix spans >3 files or crosses architectural boundaries → halt and recommend
/sw-design(Type 1 — structural scope). - Known pattern (matches patterns.md entry) → Log it as BL-{n} per
protocols/backlog.md. - Requires design-level decisions → Defer as BL-{n} with
defertag. Record the decision in decisions.md.
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.
- 1mo ago First seen · 88 lines · 33 tokens per session scan A 3a9c41c56aba
sw-debug is a skill published in the GitHub repository Obsidian-Owl/specwright (10 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 860 once invoked, about $0.0001 per session on Opus 5.5. 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.
shipyard-debugging
Investigates root cause systematically before any fix is proposed. Use when encountering any bug, test failure, unexpected behavior, or error message. Also use for tracebacks, exceptions, "not working" complaints, build failures, performance problems, or integration issues, and whenever the next step would be to…
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…
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-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…