What is verification-before-completion?

A completion checklist that requires an agent to identify, run, read, and verify a full test or validation command before claiming work is finished. It is a bridge to a more detailed verification process.

Use it at the end of coding tasks, before commits, and before handing over a completed development sprint.

It prevents unsupported claims such as saying a bug is fixed without running the command that can demonstrate it. Failed verification means the work must be fixed and checked again.

verification-before-completion — Skill for Claude Code and Codex by Bl

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 BlueprintOS/analysis-to-delivery --skill verification-before-completion

Clone the repo

git clone --depth 1 https://github.com/BlueprintOS/analysis-to-delivery

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/verification-before-completion.svg)](https://agentmods.dev/skills/blueprintos/analysis-to-delivery/verification-before-completion)

Your own site

<a href="https://agentmods.dev/skills/blueprintos/analysis-to-delivery/verification-before-completion"><img src="https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/verification-before-completion.svg" alt="Measured on agentmods" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 873 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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.00873
Opus 5	$0.00022	$0.00436
Sonnet 5	$0.00009	$0.00175
Haiku 4.5	$0.00004	$0.00087

Measured 8d ago against content hash c03b9570817f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

verification-before-completion 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.

skills/orchestration/development/verification-before-completion/SKILL.md · 91 lines

What it actually says

Verification-Before-Completion(桥接到 superpowers)

Contract

Inputs: completion claim, verification commands, implementation/documentation outputs
Outputs: verification report using IDENTIFY/RUN/READ/VERIFY/THEN
Gates: full verification command succeeds and output supports the claim
Required disciplines: stage-gate
Next: commit, fix loop, or /handoff

本仓库不维护此 skill 的内容。完整纪律请读: <SUPERPOWERS_SKILL_ROOT>/verification-before-completion/SKILL.md

何时调

每个子任务结束时(在 commit 之前)
整个开发冲刺结束时(在 HANDOVER 之前)

衔接点

产出:验证报告(IDENTIFY → RUN → READ → VERIFY → THEN 5 步门控)
下一步:commit(通过)或修复(失败)
门控:disciplines/stage-gate 第 3 层(失败必须重新跑)

5 步门控

参考完整纪律:

IDENTIFY — 什么命令能证明这个声明?
RUN — 执行完整的验证命令
READ — 读完整输出,检查退出码
VERIFY — 输出是否确认了声明?
THEN — 才能做出声明

铁律:跳过任何一步 = 撒谎,不是验证。

降级方案(superpowers 未装时)

如果 <SUPERPOWERS_SKILL_ROOT>/verification-before-completion/ 不存在,严格按以下 5 步门控(铁律,不允许跳):

1. IDENTIFY — 什么命令能证明这个声明?

把"已完成 / 通过 / 成功"翻译成可执行的命令
例如:"已修复 ASN 收货 bug" → mvn test -Dtest=AsnReceiveServiceTest
❌ 没有命令 = 你不知道自己在声称什么

2. RUN — 执行完整命令

命令必须完整执行(不能只看 stdout 头几行就停)
包含退出码 / 错误输出
用 ; echo "exit=$?" 拿退出码

3. READ — 读完整输出

读全部输出,不只是你期望的那部分
数失败数 / 数 PASS 数 / 检查退出码
❌ 看一半就跳 = 漏掉隐藏失败

4. VERIFY — 输出是否真的支持声明?

把命令输出对照你的声明
输出支持 → 进 THEN
输出反对你的声明 → 立刻如实汇报(不允许"应该可以了")
❌ "看起来是对的" 一律不算

5. THEN — 才能做出声明

经过前 4 步后才能写"完成 / 通过 / 成功"
必须附证据:命令 + 退出码 + 关键输出片段
❌ 没跑就声明 = 撒谎

最小纪律摘要

IDENTIFY 写不出命令 = 这个声明不成立
RUN 不完整 = 假装在验
READ 跳着看 = 漏失败
VERIFY 不严 = 给自己找借口
THEN 没附证据 = 不可信

安装提示

npx skills@latest add obra/superpowers-verification-before-completion

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.

8d ago First seen · 91 lines · 44 tokens per session scan A c03b9570817f

Subscribe to this mod's changes

verification-before-completion is a skill published in the GitHub repository BlueprintOS/analysis-to-delivery (26 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 873 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 2026-08-30.

Claude Code Testing anthropic claude-skills documentation-tool hermes prd

qa-testing

Run QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full). Use this skill whenever the user asks to QA a page or site, run a smoke test after a deploy, verify a page before launch, or run a regression sweep. Triggers on QA, QA sweep, smoke test, regression test, post-deploy…

rampstackco/claude-skills · 170 tokens

visual-qa

Runs rigorous visual QA across web, terminal, and paginated surfaces with screenshot evidence and a verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right.

code-yeongyu/oh-my-openagent · 47 tokens

agent-browser

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

code-yeongyu/oh-my-openagent · 51 tokens

remove-ai-slops

Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.

code-yeongyu/oh-my-openagent · 45 tokens

senpi-qa

QA the omo Senpi adapter (packages/omo-senpi, packages/senpi-task) against the REAL senpi binary in strict isolation, and write every artifact to the one canonical evidence path .omo/evidence/omo-senpi-adapter/ /. The live drivers under packages/omo-senpi/scripts/qa/ create their own isolated SENPICODINGAGENTDIR and…

code-yeongyu/oh-my-openagent · 251 tokens

suede-ai-eval

Suede Labs AI eval design and coverage audit: AI-SPEC, failure-mode rubric with severity scoring, concrete pass/fail eval cases, coverage and infrastructure scores, and mechanical acceptance gates. Use when a change ships LLM, RAG, agent, classifier, prompt, or generated-media behavior, or when asked to write evals…

JasonColapietro/suede-creator-skills · 178 tokens