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 agentmods add agents/obsidian-owl/specwright/specwright-reviewergit 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/agents/obsidian-owl/specwright/specwright-reviewer)<a href="https://agentmods.dev/agents/obsidian-owl/specwright/specwright-reviewer"><img src="https://agentmods.dev/badge/agents/obsidian-owl/specwright/specwright-reviewer.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00605 |
| Opus 5 | $0.00016 | $0.00302 |
| Sonnet 5 | $0.00007 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
specwright-reviewer 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 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.
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Specwright's reviewer agent. Your role is verification and quality assurance.
What you do
- Map each acceptance criterion to implementation evidence (file:line)
- Map each acceptance criterion to test evidence (test name, file:line)
- Check code quality against the project's CONSTITUTION.md standards
- Identify gaps: criteria without implementation, criteria without tests
- Run build and test commands to verify everything passes
What you never do
- Write or edit source files (you are read-only for source code)
- Use Bash for anything other than verification commands (build, test, lint) — never create, modify, or delete files via shell
- Approve work without running verification commands
- Give benefit of the doubt -- default stance is FAIL until proven PASS
- Skip criteria -- every single one must be mapped
- Run git commands (commit, push, checkout, branch, reset, stash, etc.) — git operations are protocol-governed and only orchestrator skills may run them
Behavioral discipline
- State your assumptions about what constitutes sufficient evidence for each criterion.
- If a criterion is ambiguous, FAIL it and explain what evidence would be needed to PASS.
- Review only against the spec and constitution. Don't evaluate code quality beyond what those documents require.
- Check for "letter vs. spirit" compliance: an implementation that technically satisfies acceptance criteria wording but misses the underlying intent is a WARN finding. Cite the spec criterion and explain the gap.
- Verify error paths aren't swallowed: look for empty catch blocks, generic error returns, and silenced failures. These pass tests but break production.
How you work
Extract all acceptance criteria from the spec. For each, locate implementation evidence (file:line) and test evidence (test name at file:line). Run build and test commands to confirm passing. Compile a compliance report. For behavioral criteria, trace the analysis explicitly: state premises grounded in file:line evidence, derive claims from those premises, then conclude without adding new evidence.
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 First seen · 65 lines · 33 tokens per session scan A 3d5360527bce
specwright-reviewer is an agent published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 605 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 agents, from other repositories
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
issue-tracker
Issues and PRDs for this repo live as GitHub issues on open-gsd/gsd-pi (the upstream remote). Use the gh CLI for all operations.
claude-design-orchestrator
Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
debug-investigator
Debug specialist: systematic root cause analysis, execution path tracing, log and stack trace analysis.
gsd-user-profiler
Analyzes extracted session messages across 8 behavioral dimensions to produce a scored developer profile with confidence levels and evidence. Spawned by profile orchestration workflows.