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-reviewgit 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-review)<a href="https://agentmods.dev/skills/anton-abyzov/specweave/sw-review"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-review/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-review"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-review.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 | $0.00042 | $0.00941 |
| Opus 5 | $0.00021 | $0.00470 |
| Sonnet 5 | $0.00008 | $0.00188 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
sw-review 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 8d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sw-review — adversarial review with citations
The only review gate that changes code: a fresh reader, hunting for real
failures, citing path:line, and re-checking every claim before writing it
down. Writes .specweave/increments/<id>/reports/review.md.
Non-negotiables
- Fresh context. The session that wrote the code never approves it. Start a new conversation (or a sub-agent, in tools that have them). If you wrote this code in this session, say so and stop — the review is not credible.
- Every finding cites
path:lineand a concrete failure: inputs or state → wrong output, crash, hang, corruption or leak. "Consider refactoring" is not a finding. - Re-verify before reporting. Re-open the cited lines and, where a test can show it, run one. Drop anything that does not survive. A wrong finding costs more than a missed one.
- Severity: critical / high / medium / low. Only critical and high should block a close.
- Nits: at most 5, collected in one line at the end. Style opinions are not review output.
No CLI? Nothing changes: git diff and the project's test runner are the whole
toolchain, and you write reports/review.md by hand. The manual path and the
CLI path produce the same report.
Steps
-
Scope — read
spec.md(ACs + Approach) and theFiles:fields intasks.md. Review that diff, not the repository:git diff $(git merge-base HEAD origin/HEAD)...HEAD -- <the tasks' Files>Falling back when there is no merge base:
git diff HEAD~1...HEAD. -
Pass — in this order: correctness (wrong logic, unhandled errors, races, off-by-one, injection, secret leakage, data loss) → ACs claimed but not implemented → tests that assert nothing (no expectation, mocked subject, snapshot of the bug) → cross-platform breakage (bash-only code,
\paths, BOM,>>in PowerShell).--full: run three passes — correctness, security, spec-compliance — and merge, dropping duplicates. -
Verify — for each candidate, re-read the lines and state the failure scenario in concrete terms. If you cannot, delete it.
-
Report — write
reports/review.mdin the shape below. A machine-readable siblingreports/review.jsonis optional:{"ok":false,"findings":[{"severity":"critical","file":"src/a.ts","line":142,"summary":"…"}]}. -
Hand back — critical/high go back to
sw-doas tasks (or get fixed and re-tested), thenspecweave verify <id>again beforespecweave complete <id>.
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.
- 8d ago First seen · 66 lines · 42 tokens per session scan A 8fb2951a8b5a
sw-review is a skill published in the GitHub repository anton-abyzov/specweave (160 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 941 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 2026-09-03.
Other skills, from other repositories
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
change-review
Use when reviewing a set of changes before they merge — a PR, a branch diff, or the working-tree changes you just made — in a Repowise-indexed codebase (.repowise/ directory exists). Activates for "review this PR", "is this safe to merge", "what's the blast radius of these changes", "did I miss anything", or "what…
genie-orca-review
Independent, read-only review of a group, a wish, or a PR on Orca — SHIP / FIX-FIRST / BLOCKED with severity-tagged findings. Council and retro are this skill with a different input.
code-review
You are a senior code reviewer. You receive diffs via stdin.
go-conventions
Go code conventions covering Effective Go, error wrapping, golangci-lint, govulncheck, table-driven tests, interfaces, context usage, modules, and concurrency. Load when writing or reviewing Go code.
handoff
Transfer the current coding, debugging, planning, or architecture session to AI Badger. Use for broad session continuation; use badger-review for an independent review.