verify

verify is a skill for Claude Code, Codex from tigu77/tiguclaw. It costs 273 tokens per session (1,556 once invoked), scanned A, original, Apache-2.0.

A verification procedure for checking that a code change was actually built, deployed, and executed by the running system.

In plain words
What is it for?
Use it before declaring a change complete, after a deployment, or when confirming that a new branch, formatter, module, or runtime behavior is active.
Why use it?
It catches cases where source files changed but the live program still uses an older build. It also checks that new conditions and replacement code paths are exercised.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it before declaring a change complete, after a deployment, or when…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tigu77/tiguclaw/verify
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.

Any agent
npx skills add tigu77/tiguclaw --skill verify
Clone the repo
git clone --depth 1 https://github.com/tigu77/tiguclaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/tigu77/tiguclaw/verify.svg)](https://agentmods.dev/skills/tigu77/tiguclaw/verify)
Your own site
<a href="https://agentmods.dev/skills/tigu77/tiguclaw/verify"><img src="https://agentmods.dev/badge/skills/tigu77/tiguclaw/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 273 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,556 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00273 $0.01556
Opus 5 $0.00137 $0.00778
Sonnet 5 $0.00055 $0.00311
Haiku 4.5 $0.00027 $0.00156

Measured 6d ago against content hash 55d0dc9f37ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

skills/verify/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify — 변경이 실제로 배포·동작하는지 구동 확인

"고쳤다"·"커밋했다"가 아니라 "신 코드가 라이브에서 실제로 도는가" 를 grep·프로세스·실행으로 확정한다. 어댑터(claude/codex/openai) 무관 — 전부 Bash 명령 수준. SYSTEM.md §1 「완료」 정의의 실행 절차.

A. 반영 실측 — 변경이 실제로 도는가

원칙: 네가 바꾼 소스와 지금 실제로 도는 것이 같은지 확인한다. 인터프리트 실행이면 리로드로, 컴파일·빌드 산출물이면 재빌드+재배포 후에야 반영된다 — 그 프로젝트의 배포·실행 방식을 따른다.

  • ① 산출물–소스 일치: 이번에 바꾼 고유 마커(새 함수명·새 문구)가 실제로 도는 산출물에도 있는지 grep. 없으면 빌드/배포 누락(소스만 바뀐 상태). 옛 마커가 산출물에 남았는지 역방향으로도 확인하라 (신·구 공존 = 부분 빌드 신호).
  • ② 시각 순서: 소스 수정 ≤ 빌드/배포 ≤ 프로세스 기동 순서여야 신 코드가 로드된 것. mtime 은 ls -la, 프로세스 기동은 ps -o lstart= -p <pid>. 소스가 산출물보다 새로우면 빌드 후 재수정된 것 — 재빌드부터.
  • ③ 실동작 마커: 바뀐 경로를 실제 1회 흘려 로그·출력·응답에서 신 동작을 관측한다.
  • 불일치 → 그 런타임의 재빌드·재배포 → 재실측. 소스 저장·커밋·typecheck 통과만 = 미완.

예 — 컴파일·빌드 후 배포되는 서비스: 소스 수정 → 재빌드 → 재배포/프로세스 재시작 → 도는 산출물에서 마커 grep(①) + 산출물 mtime vs 프로세스 기동시각(②) + 런타임 로그·응답에서 신 동작 관측(③). 인터프리트·핫리로드 런타임이면 빌드 단계 없이 리로드 후 ①③. 정적 사이트·스크립트도 같은 골격: 바꾼 것실제로 서비스되는 것에 반영됐는지 대조한다.

B. 분기 커버리지 — 새 분기를 실제로 탔는가

  • 이번 변경에서 새로 만들거나 바꾼 조건분기를 나열한다(git diff 에서 if/삼항/switch/길이·개수 비교).
  • 분기마다 그 분기를 실제로 타는 입력 최소 1개로 실측한다(단위 실행·수동 호출·실메시지). 예: length > 4096 분기를 새로 만들었으면 4096자 초과 입력을 반드시 하나 넣어본다.
  • 기존 픽스처·테스트가 전부 같은 분기만 치면 새 경로는 미검증으로 명시하라 — "테스트 통과"가 그 분기의 검증이 아니다.

C. 행동 보존 대조 — 교체가 무엇을 잃었나 (교체·리팩터 시만)

  • 옛 구현의 동작 인벤토리를 먼저 만든다: 입력 유형별 관측 동작·엣지 케이스·포맷 보장. (git show 로 교체 코드를 읽고 목록화 — 신 코드만 보고 추정 금지.)
  • 신 구현과 항목별 대조: 각 옛 동작이 보존 / 의도적 변경 / 회귀 중 무엇인지 명시한다.
  • 회귀를 '의도적 다운그레이드'로 합리화하지 마라 — 의도적 변경이면 그 근거와 사용자 영향을 적고, 근거가 없으면 복구한다.

D. 완료 보고 전 체크리스트

보고 직전 아래를 확인하고, 미충족 항목은 "미완/보류"로 명시한다(조용한 '완료' 금지):

  • 라이브 반영됨(빌드·배포가 필요한 런타임이면 재빌드·재배포 실행)
  • 산출물 마커 grep + 시각 순서(소스≤산출물≤기동) 통과 (§A①②)
  • 새 분기마다 실입력 1개 실측 (§B)
  • (교체·리팩터면) 옛 행동 인벤토리 대조 완료 (§C)
  • 실동작 마커로 신 경로 1회 관측 (§A③)

경계 — code-review 와의 분업 (중복 구현 금지)

  • code-review = 정적 결함 탐지("이 코드에 버그·더 나은 방법이 있나" — diff 를 읽는다). 반영 .
  • verify = 동적 구동 확인("이 변경이 실제로 반영·동작하나" — 산출물을 돌린다). 반영 .
  • verify 는 결함 분석을 재구현하지 않고, code-review 는 배포·부팅·분기 실측을 하지 않는다.

Read the full file on GitHub · 61 lines

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. 6d ago First seen · 61 lines · 273 tokens per session scan A 55d0dc9f37ef

Subscribe to this mod's changes

verify is a skill published in the GitHub repository tigu77/tiguclaw (6 stars, last pushed today), licensed Apache-2.0. It adds 273 tokens to every session and 1,556 once invoked, about $0.0014 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

commonly

You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…

Team-Commonly/commonly · 0 tokens

github

Interact with GitHub (issues, PRs, repos, releases) using the gh CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.

Team-Commonly/commonly · 49 tokens

pandic-office

Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.

Team-Commonly/commonly · 59 tokens

pdf

Manipulate PDF files — extract text, count pages, render thumbnails, merge or split documents. Use for PDF-specific operations that don't fit markdown-converter (general read) or pandic-office (write from markdown).

Team-Commonly/commonly · 49 tokens

tmux

Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).

Team-Commonly/commonly · 48 tokens

community-research-insight

Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.

clawdotnet/openclaw.net · 41 tokens