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 anton-abyzov/specweave --skill dogit clone --depth 1 https://github.com/anton-abyzov/specweaveWrote 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/anton-abyzov/specweave/do)<a href="https://agentmods.dev/skills/anton-abyzov/specweave/do"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/do/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/anton-abyzov/specweave/do"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/do.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01933 |
| Opus 5.5 | $0.00018 | $0.00773 |
| Sonnet 5.5 | $0.00009 | $0.00387 |
| Haiku 4.5 | $0.00005 | $0.00193 |
Grade A, and why
do 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.
sw-do: work an increment to done
Tasks are defined in spec.md under ## Tasks; their state lives only in the
increment's ledger.jsonl, which the CLI appends to. Never write state into spec.md.
Start
specweave pickup applies any handoff pushed from another tool or account, then prints
the open increment, the next task with its acceptance criteria, claims other agents
hold, and notes left for you. No increment yet? Run sw-increment first.
The loop
specweave task nextprints the next claimable task with its AC text.specweave task claim T-03 --line "Writing the ledger fold". Exit 3: someone holds it (your own earlier claim from a crashed session: say so, then--force); 4: its Files overlap a live claim; 6: its dependencies are not done. Otherwise pick another. Never edit before claiming.- Implement inside that task's
Filesonly. Need another file? Claim the task that owns it, or add a task to spec.md## Tasks. Use the words inGLOSSARY.md, if the project has one, for every new name. - Run the task's
Test. Red means fix the code; never skip, weaken or delete a test. Don't write tests first or add unit tests the task did not ask for (unless the project'stestingconfig or conventions require them): check the AC end to end, the way a user would hit it. - Commit with the increment id first:
git commit -m "0042: fold the ledger". specweave task done T-03 --run "npm run test:e2e -- double-claim" --line "Wrote the ledger fold" --link <PR URL>. Exit 5: the command failed and the task stays open. NoTest?--evidence "<sha> + what you checked".--lineis the card text (one line, past tense when done, at most 100 characters);--linkis the PR, report or artifact behind it.- Stuck:
specweave task block T-03 --reason "<what is missing>". Not needed:specweave task skip T-03 --reason "<why>". Then back to 1.
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 Changed · +11 lines 391720de3b20
- 4d ago Changed · +36 lines · +2 tokens per session a88a65974b71
- 10d ago Changed · +3 lines 2223031c1389
- 26d ago Changed · +17 lines · +44 tokens per session a408627dc1e2
- 1mo ago First seen · 57 lines · 0 tokens per session scan A ac50e0c07552
do is a skill published in the GitHub repository anton-abyzov/specweave (166 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,933 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 2026-09-03.
Other skills, from other repositories
work
Handle issue/PR work items with worktree isolation. Triggered by "/work [issuelink|description]" to start focused work.
creating-issues-and-pull-requests
Use when creating GitHub pull requests or issues with template compliance. Triggers: 'create a PR', 'open a pull request', 'file an issue', 'create issue'. Also invoked by finishing-a-development-branch. NOT for: deciding whether to merge or PR (use finishing-a-development-branch).
gitlab-guide
Use when managing GitLab tickets/work items, issue-board kanban, merge-request delivery/review, durable issue or MR context notes, or native CI/policy enforcement on GitLab.com, Self-Managed, or Dedicated. Triggers on glab issue, issue links, work items, board lists/status moves, glab mr, Notes/discussions, approvals…
version-bump
Automate version bumping in npm monorepos with CHANGELOG promotion and PR automation.
baron
Drive work tracking (issues) and source control (pull requests) through Baron's provider-agnostic ports. Use when the user asks to create/transition/comment/link/query issues, open branches or pull requests, or run a Baron recipe — across Azure DevOps, GitHub, or whatever the repo's .baron/policy.json binds.
4x-autopilot
An owner-only automation mode for the 4x feature pipeline, which manages tracked development tasks from selection through completion and merging. It runs one feature at a time and reads project settings to determine the repositories and workflow.