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 skills/obsidian-owl/specwright/sw-verifynpx skills add Obsidian-Owl/specwright --skill sw-verifygit 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-verify)<a href="https://agentmods.dev/skills/obsidian-owl/specwright/sw-verify"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-verify.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 | $0.00032 | $0.03054 |
| Opus 5 | $0.00016 | $0.01527 |
| Sonnet 5 | $0.00006 | $0.00611 |
| Haiku 4.5 | $0.00003 | $0.00305 |
Grade A, and why
sw-verify 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 5d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specwright Verify
Goal
Run quality gates against the work unit. Continue through all gates
regardless of failures and present the report at handoff
per protocols/decision.md.
Inputs
{worktreeStateRoot}/session.json-- selected work{repoStateRoot}/work/{selectedWork.id}/workflow.json-- work state and gate results{projectArtifactsRoot}/config.json-- gate configuration{workDir}/spec.md-- for spec compliance gate{workDir}/implementation-rationale.md-- curated build rationale when present{workArtifactsRoot}/{selectedWork.id}/integration-criteria.md-- behavioral IC list when present- Gate skill files in
skills/gate-*/SKILL.md
Outputs
{repoStateRoot}/work/{selectedWork.id}/units/{selectedWork.unitId}/stage-report.md-- verify handoff digest- Evidence files in
{workDir}/evidence/, one per gate {workDir}/review-packet.md-- reviewer synthesis from approvals, rationale, proof, and gate outcomes- Selected work's
workflow.jsonupdated with gate results; statusverifying - Aggregate report presented at gate handoff
Constraints
Stage boundary (LOW freedom):
Follow protocols/stage-boundary.md. Run quality gates and show findings. NEVER fix
code, create PRs, or ship. After gate handoff, STOP.
Ownership check (LOW freedom):
Resolve the selected work from the current worktree session. If another live
top-level worktree owns that work, STOP with explicit /sw-adopt guidance and
do not rely on generic adopt/takeover behavior.
Assumption re-validation (LOW freedom) — before gate execution: Scan the design assumptions artifact from the design-level directory. Check ACCEPTED/VERIFIED assumptions against current code. Invalid → WARN in the aggregate report. Runs silently.
Approval lineage check (LOW freedom) — before gate execution:
Use protocols/approvals.md and the shared helper to validate the recorded
design and current unit-spec approval hashes. Missing, STALE, or
SUPERSEDED lineage becomes a distinct approval finding; headless verify may
report it but never create APPROVED entries.
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.
- 5d ago First seen · 249 lines · 32 tokens per session scan A e38aa21d2034
sw-verify is a skill published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 3,054 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
rust-skills
Rust best practices — 179 rules across 14 categories for idiomatic, optimized Rust code.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
llm-friendly-context
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
cco-task
Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or mark the active one done. Pairs with /cco-pack to load minimal context per task.
cco-templates
Manage context templates for common task types.
discuss
Use when exploring a feature idea before committing, or revisiting a parked one. Triggers — "/engineer.discuss", "/engineer.discuss ", "I have an idea about", "should we build", "let's think about".