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-statusgit 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-status)<a href="https://agentmods.dev/skills/obsidian-owl/specwright/sw-status"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-status/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-status"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-status.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 | $0.00043 | $0.01242 |
| Opus 5.5 | $0.00017 | $0.00497 |
| Sonnet 5.5 | $0.00009 | $0.00248 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
sw-status 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specwright Status
Goal
Tell the user what this worktree is attached to, what that work is doing, what other works are active in the repository, which runtime layout is active, and what the next action should be.
Inputs
{projectArtifactsRoot}/config.json{worktreeStateRoot}/session.json{repoStateRoot}/work/*/workflow.json{workArtifactsRoot}/{selectedWork.id}/approvals.mdwhen a work is attached{workDir}/review-packet.mdwhen the selected unit has reached verify or ship artifacts
Outputs
- Formatted status display for the current session and selected work
- Repo-wide summary of active works and their owner worktrees
- In
--repairmode: remediation outcome for the targeted shipped unit
Constraints
Display (HIGH freedom):
- Print the resolved
projectArtifactsRoot,repoStateRoot,worktreeStateRoot, andworkArtifactsRootbefore the session summary so tracked project artifacts and the active runtime layout are inspectable. - Name the runtime layout explicitly:
project-visibleruntime roots under.specwright-local/are the recommended interactive default, whilegit-adminroots under.git/specwright/are compatibility mode. - Show the current session first:
worktreeId, mode, branch, andattachedWorkId. - If the session is attached, show that work's status, unit/task progress, the selected work's target branch and latest freshness state, configured work-artifact publication mode when present, approval freshness reason, latest closeout or review-packet availability, review-packet presence, gates, and per-work lock freshness.
- Keep the operator vocabulary aligned with the primary adapter surfaces: attached work, branch validity, approval or closeout posture, live ownership, and next action.
- If the attached work is already owned by another live top-level worktree,
surface that conflict explicitly and point the operator to
/sw-adoptinstead of implying that status can mutate ownership. - Enumerate other active works discovered under
repoStateRoot/work/*, along with their recorded owner worktrees and whether the owner still has a live top-level session. - If no work is attached in this worktree, say so and suggest
/sw-design. - Keep the output concise.
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 · 122 lines · 43 tokens per session scan A a8970b608be2
sw-status is a skill published in the GitHub repository Obsidian-Owl/specwright (10 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 1,242 once invoked, about $0.0002 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
recipe-plan
Create work plan from design document and obtain plan approval.
shipyard-executing-plans
Executes a written implementation plan with agents. Use when a written plan is ready to execute, in the current session or a separate one. Also use when the user says "build this", "implement this", "execute the plan", or "run the plan", or when a loaded plan file has independent tasks suitable for agent dispatch.
import-spec-file
Imports a handwritten spec document into Shipyard in place of brainstorming. Use when a freeform spec, requirements, or design document already exists.
shipyard-writing-plans
Breaks a spec, requirements, or design into an implementation plan with file paths and verification commands. Use for any multi-step task before touching code. Also use when the user says "plan this", "break this down", "create tasks", or "decompose this feature", when a task needs more than 2-3 steps, or when tasks…
import-spec
Imports a spec-kit feature spec into Shipyard in place of brainstorming. Use when a spec-kit feature directory with spec.md exists.
lessons-learned
Extracts reusable lessons from completed work. Use when a phase or milestone is complete, before shipping, or when reflecting on finished work. Also use when the user says "what did we learn", "capture lessons", "retrospective", "wrap up", "ship this phase", or "done with this phase". A phase must not ship without…