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-auditgit 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-audit)<a href="https://agentmods.dev/skills/obsidian-owl/specwright/sw-audit"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-audit/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-audit"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-audit.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 | $0.00036 | $0.00909 |
| Opus 5.5 | $0.00014 | $0.00364 |
| Sonnet 5.5 | $0.00007 | $0.00182 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
sw-audit 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specwright Audit
Goal
Find systemic codebase issues that per-change quality gates miss. Architecture debt, complexity growth, convention drift, and accumulated workarounds compound silently. Surface them, let the user prioritize, and persist findings for future design cycles.
Inputs
- The codebase itself
{projectArtifactsRoot}/CONSTITUTION.md-- practices to check against{projectArtifactsRoot}/AUDIT.md-- prior findings (if exists, for ID matching){projectArtifactsRoot}/LANDSCAPE.md-- module structure (if exists, for triage){projectArtifactsRoot}/config.json-- audit config (optionalauditsection)
Outputs
{projectArtifactsRoot}/AUDIT.md-- findings perprotocols/audit.mdformat- Findings presented to user grouped by dimension before saving
Constraints
Scope (LOW freedom):
- This skill reads and analyzes. It NEVER modifies source code, creates branches, runs builds, or starts work units.
- Does NOT create
currentWorkin workflow.json. Does NOT require a lock. Can run while a work unit is in progress. - It is not a core workflow stage and never claims top-level work ownership.
- On compaction: re-run from scratch (no state to recover).
Triage (MEDIUM freedom):
- Determine audit depth from argument and codebase size:
- Path argument → Focused: analyze specified directory/module only
--fullargument → Full: parallel agents, all dimensions- No argument → auto-triage: Standard (<50 files) or Full (50+ files)
- If LANDSCAPE.md exists, use module count to inform triage.
Analysis (HIGH freedom):
- Four dimensions: architecture, complexity, consistency, debt.
- Delegate per
protocols/delegation.md:specwright-architect: architecture + complexity (structural analysis)specwright-reviewer: consistency + debt (convention and quality analysis)
- Standard depth: 2 agent calls (sequential or parallel).
- Full depth: up to 4 parallel calls (one per dimension).
- Include constitution practices as the baseline for consistency checks.
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 · 92 lines · 36 tokens per session scan A 6ec1e1520b79
sw-audit is a skill published in the GitHub repository Obsidian-Owl/specwright (10 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 909 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.
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…
debug
Systematic bug investigation with a five-phase framework: reproduce, narrow, diagnose, fix, verify. Supports automated regression bisect via --regression flag. Produces a structured debug report with root cause analysis, regression test, and CQ/Q self-evaluations.
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…