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/baleen37/bstack/verifynpx skills add baleen37/bstack --skill verifygit clone --depth 1 https://github.com/baleen37/bstackWhat 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 | $0.00048 | $0.01284 |
| Opus 5 | $0.00024 | $0.00642 |
| Sonnet 5 | $0.00010 | $0.00257 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
verify 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 yesterday.
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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/verify: Scope → Verify → Report
You are an implementation verifier. /verify checks whether a feature or change behaves correctly
in context. It does not act as a release-readiness gate and it does not fix code.
Which skill to use
/verify— does one change behave as intended (default path)/e2e-scenario-testing— drive a running app through its real interface, one scenario/story-loop— catalog the whole repository as scenarios, then loop to green
What /verify checks
Focus on the current work context:
- the intended golden path
- the most relevant edge cases
- obvious regressions near the changed behavior
- all risk surfaces identified in Phase 0 (외부 시스템 접점은 항상 직접 검증)
/verify is the default verification path. If cross-service or multi-layer flow integrity is the main risk, add /e2e-scenario-testing.
Scope resolution
Decide scope in this order unless the user explicitly overrides it:
- Plan context — if there is an active implementation plan, verify the feature or task described there
- Branch context — otherwise inspect the current branch diff (for example
main...HEAD) and verify the affected behavior - User hint — if the user gives extra guidance without explicit override, use it to refine the current context
If the user explicitly narrows scope (for example: "login only", "verify checkout success flow only"), treat that as user override and use it as the primary scope.
If the user names a verification environment or execution path (a named deploy environment, a CI job, a batch or data pipeline), treat it as scope refinement. Before writing the report, confirm the verification set includes that named environment/path or mark it incomplete.
Always report the scope source as one of:
Scope source: planScope source: branchScope source: user override
Verification flow
Phase 0: Risk surface
변경된 코드가 외부 시스템 접점(OpenSearch, DB, message queue, 외부 API, 파일 시스템 등)과 상호작용하는지 식별한다.
식별 단서:
- diff에 외부 클라이언트/리포지토리/게이트웨이 호출이 포함됨
- 계획서나 Rollout 메모에 "배포 전 ~ 확인 권장" 같은 항목이 있음
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 162 lines · 48 tokens per session scan A f14fd3a4f862
verify is a skill published in the GitHub repository baleen37/bstack (4 stars, last pushed 11d ago), licensed MIT. It adds 48 tokens to every session and 1,284 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…