verify

A verification workflow for checking whether a code change works correctly in its current application context.

In plain words
What is it for?
It helps test an implementation and report whether it passes, partially works, or fails, with evidence. It does not modify the code.
Why use it?
It catches failures on the main user path, relevant edge cases, nearby regressions, and connections to outside systems before the result is treated as working.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/baleen37/bstack/verify
Any agent
npx skills add baleen37/bstack --skill verify
Clone the repo
git clone --depth 1 https://github.com/baleen37/bstack

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,284 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash f14fd3a4f862, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugins/me/skills/verify/SKILL.md · 162 lines

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:

  1. Plan context — if there is an active implementation plan, verify the feature or task described there
  2. Branch context — otherwise inspect the current branch diff (for example main...HEAD) and verify the affected behavior
  3. 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: plan
  • Scope source: branch
  • Scope 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

Read the full file on GitHub · 162 lines

Files

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.

Changes

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.

  1. yesterday First seen · 162 lines · 48 tokens per session scan A f14fd3a4f862

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens