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-shipnpx skills add Obsidian-Owl/specwright --skill sw-shipgit 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-ship)<a href="https://agentmods.dev/skills/obsidian-owl/specwright/sw-ship"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-ship.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 | $0.00031 | $0.02288 |
| Opus 5 | $0.00015 | $0.01144 |
| Sonnet 5 | $0.00006 | $0.00458 |
| Haiku 4.5 | $0.00003 | $0.00229 |
Grade A, and why
sw-ship 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specwright Ship
Goal
Merge the current work unit to main via a pull request. The PR body maps
evidence to acceptance criteria and derives its reviewer-facing audit summary
from review-packet.md so reviewers can verify without opening raw transcripts
or reconstructing rationale from the diff alone. The PR itself is the human
gate — reviewers verify before merge.
Inputs
{worktreeStateRoot}/session.json-- selected work for this worktree{repoStateRoot}/work/{selectedWork.id}/workflow.json-- selected work unit, gate results{workDir}/spec.md-- acceptance criteria for PR body{workDir}/review-packet.md-- reviewer-facing audit summary assembled by/sw-verify{workDir}/evidence/-- gate evidence files{projectArtifactsRoot}/config.json-- git config (PR tool, branch prefix, main branch)
Outputs
{repoStateRoot}/work/{selectedWork.id}/units/{selectedWork.unitId}/stage-report.md-- shipping handoff digest with attention-at-top- Pull request created with a review-packet-grounded, evidence-mapped body
- Selected work's
workflow.jsonstatus set toshipped
Constraints
Stage boundary (LOW freedom):
Follow protocols/stage-boundary.md. Create PRs and mark shipped. NEVER start new
work, run builds, or begin next unit. After PR: show URL, suggest /sw-learn, handoff.
Pre-flight checks (LOW freedom):
- Resolve the selected work from the current worktree session. If another live
top-level worktree owns it, STOP with explicit
/sw-adoptguidance instead of generic adopt/takeover behavior. - Verify the selected work exists and status is
verifying. Rejectbuildingwith: "Run /sw-verify first." Reject all other statuses with the standard transition error. - All enabled gates in
config.gatesmust have a verdict in the selected work'sworkflow.json. Gates without a verdict → STOP: "Gate {name} has no verdict. Run /sw-verify first." - No gate verdict may be
FAILorERROR. FAIL/ERROR → STOP: "Gate {name} failed. Fix and re-run /sw-verify." - Re-check shipping freshness during pre-flight via
protocols/git-freshness.md. For branch-head validation, branch-headrequireblocks stale, diverged, and blocked freshness results. Queue-managed validation remains distinct and must not force a local rebase by default. When branch-head validation is blocked andrebaseormergereconcile is configured, runprotocols/git-reconcile.mdin the owning worktree and continue shipping in that same run after a successful reconcile.manualremains an explicit fallback: STOP with the same manual reconcile guidance used by build and verify: reconcile the current branch against the recorded target in the owning worktree, or run/sw-adoptfirst if a linked-worktree ownership conflict exists, then rerun/sw-verifyfollowed by/sw-ship. Do not silently rewritetargetRefor freshness metadata to bypass the block. review-packet.mdmust exist at{workDir}/review-packet.md. Missing packet → STOP: "Review packet missing for {unitId}. Re-run /sw-verify."- Evidence files must exist at
{workDir}/evidence/{gate-name}-report.mdfor each gate with a non-SKIP verdict. Missing evidence file → STOP: "Evidence missing for gate {name}. Re-run /sw-verify." - Uncommitted changes: commit only files within the work unit's plan.md file-change-map. Report out-of-scope uncommitted files in the gate handoff — do not commit them.
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 · 158 lines · 31 tokens per session scan A 8fe3c19ace39
sw-ship is a skill published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 2,288 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
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
bump-version
Bump the Logic-Lens version across all six metadata locations at once (package.json, the four plugin manifests, and the README badge), then validate. Use when cutting a release or when npm run validate reports a version mismatch.
release-docs
Diff-driven documentation sync after a release. Determines what source files changed, delegates changelog to zuvo:docs, updates only docs whose source changed. Flags: --dry-run, explicit range argument.
publish
Use when the user invokes /evo:publish or asks to release a new version, ship a release, or publish a tag. Wraps the go-native self-healing release pipeline (evolve release) — pre-flight checks, auto-changelog, atomic ship, marketplace propagation poll, auto-rollback on failure.
release
Use when the user asks whether a release is ready, or to gate/verify release criteria before publishing. A thin readiness-gate that runs the existing read-only verifiers (evolve release-preflight, evolve release-consistency), adds the CI-green-on-main and no-WIP-commit checks they don't cover, then delegates execution…
verify-release
Use when the user invokes /evo:verify-release or asks to check whether a release has propagated, whether the marketplace is up to date, or whether installed plugins reflect the latest version. Wraps legacy/scripts/release/marketplace-poll.sh for standalone post-publish verification.