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 sw-autogit 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/sw-auto)<a href="https://agentmods.dev/skills/anton-abyzov/specweave/sw-auto"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-auto/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/sw-auto"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-auto.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 | $0.00036 | $0.00589 |
| Opus 5.5 | $0.00014 | $0.00236 |
| Sonnet 5.5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
sw-auto 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 20d 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.
What it actually says
sw-auto: run until done
Auto mode is the sw-do loop without stopping to ask. The bar does not drop: claim
before editing, a passing test for every done, verify before closing.
Start
- The spec has no open questions and every task has
Filesand aTest. If not, fix the spec first. specweave auto 0042records the session (--dry-runpreviews it,--resetclears stale state). In a tool that runs SpecWeave's Stop hook (Claude Code with theswplugin) the hook hands you the remaining work after every turn until nothing is left. In any other tool, nothing feeds you back: keep looping yourself.specweave auto-statusshows progress;specweave cancel-autostops it.
Each turn
specweave task next→specweave task claim T-NN→ implement inside itsFiles→ commit0042: ...→specweave task done T-NN --run "<Test>".- A failing test is fixed in the next turn, never marked done.
- Genuinely blocked (missing secret, ambiguous spec, external dependency):
specweave task block T-NN --reason "<what is missing>"and move on. Blocked tasks still count as work left: when only blocked tasks remain, runspecweave cancel-autoand tell the user what each one needs, instead of looping until the turn limit. - Nothing claimable left: run sw-done (verify, review, complete).
Running out of budget
Before the session ends for tokens or time: specweave handoff --reason "auto: out of tokens". The next session, in any tool or account, says "pick up" and continues.
Manual path (no CLI)
Without the CLI there is no hook and no session file: follow the manual path of sw-do
in a loop until every task in spec.md has a done or skip line, then sw-done.
Rules
- Never edit
.specweave/state/auto-mode.jsonby hand;specweave auto --resetclears it. - One auto session per project; check
specweave auto-statusbefore starting another. - Never widen a task's
Filesor weaken a test to keep the loop moving.
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.
- 20d ago First seen · 48 lines · 36 tokens per session scan A be39e2abaa3a
sw-auto is a skill published in the GitHub repository anton-abyzov/specweave (165 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 589 once invoked, about $0.0001 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 2026-09-26.
Other skills, from other repositories
product
Consolidated Galyarder Framework Product intelligence bundle.
diet-remove
Remove a dependency identified by uzomuzo diet — analysis + issue (default) or direct PR.
review-story
QA gate for a story — verdict PASS/CONCERNS/FAIL/WAIVED + lifecycle transition. Use when: review story, qa gate, qa-gate, /review-story.
aiox-review-story
QA gate for a story — verdict PASS/CONCERNS/FAIL/WAIVED + lifecycle transition. Use when: review story, qa gate, qa-gate, /review-story.
acceptance
Test a PR review end to end and prove it honoured every guarantee in INVARIANTS.md. Use when asked to test/validate a review of a pull request, to check a finished run, or to run the 3-provider x 2-runtime acceptance matrix. Drives pr-review verify and scripts/acceptance.mjs — never hand-checks the guarantees.
intent-verify
Verify current requirements against implementation and actual results across a product or change scope, including completed features. Run permissible existing checks and report findings without fixes.