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-adoptnpx skills add Obsidian-Owl/specwright --skill sw-adoptgit 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-adopt)<a href="https://agentmods.dev/skills/obsidian-owl/specwright/sw-adopt"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-adopt.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 | $0.00027 | $0.00882 |
| Opus 5 | $0.00014 | $0.00441 |
| Sonnet 5 | $0.00005 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
sw-adopt 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specwright Adopt
Goal
Attach an existing work to the current worktree without creating split-brain ownership. This skill attaches only the current worktree session.
Inputs
- target work ID from the argument, or the current worktree session's
attachedWorkIdwhen re-adopting the already-selected work {worktreeStateRoot}/session.jsonfor the current worktree{repoStateRoot}/work/{workId}/workflow.json- repo-wide
session.jsonfiles discovered viagit worktree list --porcelain
Outputs
- updated
{worktreeStateRoot}/session.jsonfor the current worktree only - updated selected work
workflow.json.attachmentpointing at the current worktree when adoption succeeds - concise outcome explaining whether the work was adopted, blocked by a live owner, or blocked by branch mismatch
Constraints
Scope (LOW freedom):
/sw-adoptis the explicit same-work adoption flow. It must not silently run during/sw-design,/sw-plan,/sw-build,/sw-verify, or/sw-ship./sw-adoptnever rewrites another worktree'ssession.json.- Subordinate sessions must not run
/sw-adopt.
Target resolution (LOW freedom):
- Resolve the target work from the argument first, then the current worktree's
session.json.attachedWorkIdas a fallback. - Validate that the target work exists under
{repoStateRoot}/work/{workId}. - If no target work resolves, STOP and tell the operator to pass a work ID or
run
/sw-design.
Ownership validation (LOW freedom):
- Use live-versus-dead session state as the adoption authority.
- Inspect repo-wide
session.jsonfiles to determine live-versus-dead session state for the target work. - Treat live top-level sessions as authoritative owners.
- Treat dead top-level sessions as stale attachments that may be superseded.
- Treat subordinate sessions as non-owners even when they reference the same
workId. - If another live top-level worktree owns the target work, STOP and tell the
operator to continue there or make that owner stale first.
/sw-adoptdoes not perform remote session surgery.
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 · 95 lines · 27 tokens per session scan A 50c83dac0c5d
sw-adopt is a skill published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 882 once invoked, about $0.0001 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".