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-statusnpx 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.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 5.1 | $0.00043 | $0.01242 |
| Opus 5 | $0.00022 | $0.00621 |
| Sonnet 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 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 — 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.
- 5d 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 (9 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,242 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".