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-syncnpx skills add Obsidian-Owl/specwright --skill sw-syncgit clone --depth 1 https://github.com/Obsidian-Owl/specwrightWhat 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 | $0.00036 | $0.01145 |
| Opus 5 | $0.00018 | $0.00573 |
| Sonnet 5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
sw-sync 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 2d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specwright Sync
Goal
Keep the local repository current without deleting branches that are still claimed by a live Specwright session or a subordinate helper worktree.
Inputs
{projectArtifactsRoot}/config.json{worktreeStateRoot}/session.json{repoStateRoot}/work/*/workflow.jsongit worktree list --porcelain
Outputs
- Remotes fetched and pruned
- Base branch fast-forwarded when safe
- Candidate stale branches previewed, then deleted only after confirmation
- Summary report: branches fetched, removed, skipped, protected, and any stale active works detected
Advisory Reporting
- After fetch/prune completes,
sw-syncmay report stale active works against their recorded targets and latest known freshness state. - This report is advisory only and does not take ownership of reconcile-or-ship decisions away from the lifecycle skills.
sw-syncnever rebases, merges, retargets, or clears a freshness block on behalf ofsw-build,sw-verify, orsw-ship.
Constraints
Fetch (HIGH freedom):
- Run
git fetch --all --prune.
State-aware protection set (LOW freedom):
- Build a branch protection set from:
- the currently checked out branch
- the configured base branch and perennial branches
- branches recorded by live
session.jsonfiles acrossgit worktree list - branches recorded in attached work
workflow.json.branch - helper branch patterns
worktree-*andspecwright-wt-*
- Treat subordinate helper worktrees discovered via
git worktree list --porcelainas protected branch owners even when they are not user-facing sessions. - Never delete a branch that appears in that protection set.
Stale branch detection (HIGH freedom):
- Primary signal:
git branch -vventries with[gone] - Supplementary signal:
git branch --mergedagainst the configured base branch - Do not promote a branch to deletion solely because it is merged if a live session still references it.
- Do not delete a branch when a live session or subordinate helper still claims it.
- Classify confirmed stale branches into:
safe-deletefor branches that should still usegit branch -dforce-delete-candidatefor[gone]branches only when they are not protected, not invalid, and not claimed by a live session or subordinate helper worktree
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.
- 2d ago First seen · 124 lines · 36 tokens per session scan A f7f31769d992
sw-sync is a skill published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 1,145 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
ai-spec-project-start
Install or upgrade SDAD; migrate an existing SDAD project; recover or repair sdad-state.yaml, INDEX, ledger, or handoff consistency; run or interpret SDAD Doctor; or diagnose the SDAD control plane. Use only for SDAD-specific bootstrap, migration, repair, and Doctor operations.
phase-7-testing
Phase 7 — Test Strategy with pyramid, coverage gates, load tests, and Critical User Journeys.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
create-mcp-server
Build, iterate, and evaluate Model Context Protocol (MCP) servers that expose external services as tools an LLM can call. Covers schema/tool design, error handling, pagination, MCP Inspector testing, and an eval set. Use when asked to "build an MCP server", "create an MCP tool", "wrap this API as MCP", "expose X to…
spk-team-auth
Handle Spec Kitty team authentication, hosted credentials, account selection, and auth-related recovery.