harness-verify

harness-verify is a command for Claude Code from kimsanguine/hplan. It costs 65 tokens per session (945 once invoked), scanned A, original, MIT.

A completion check that compares a task or feature with the conditions recorded in STATE.md. It marks a condition verified when its referenced file exists.

In plain words
What is it for?
Use it before closing a task or sprint, or run a full specification compliance review with the optional spec mode.
Why use it?
It prevents declaring work complete while required evidence is missing. It also reports whether all conditions are complete, partly verified, or blocked.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the hplan plugin — 8 skills, 11 commands, 4 agents shipped together

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 commands/kimsanguine/hplan/harness-verify
Clone the repo
git clone --depth 1 https://github.com/kimsanguine/hplan

Made for: Claude Code.

Or install hplan, the plugin that ships this one along with the rest of its 8 skills, 11 commands, 4 agents.

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 harness-verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/kimsanguine/hplan/harness-verify.svg)](https://agentmods.dev/commands/kimsanguine/hplan/harness-verify)
Your own site
<a href="https://agentmods.dev/commands/kimsanguine/hplan/harness-verify"><img src="https://agentmods.dev/badge/commands/kimsanguine/hplan/harness-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 945 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 5.1 $0.00065 $0.00945
Opus 5 $0.00032 $0.00473
Sonnet 5 $0.00013 $0.00189
Haiku 4.5 $0.00006 $0.00094

Measured 6d ago against content hash bc2a23b66633, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

harness-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.

hplan/commands/harness-verify.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/harness-verify

개발 중 완료 선언 전에 실행하는 증거 게이트. harness/STATE.mdverified_by 파일 존재를 확인하고 조건 상태를 갱신합니다.

Instructions

You are running /harness-verify for: $ARGUMENTS

Step 1 — STATE.md 로드

cat harness/STATE.md 2>/dev/null || echo "STATE_MISSING"

STATE_MISSING → Stop. "harness/STATE.md 없음 — /harness-build 실행 후 CONDITIONAL_GO 출력이 필요합니다." 출력.

Step 2 — 조건 anchor 검사

STATE.mdActive 조건 테이블에서 verified_by 경로를 추출. 각 경로에 대해:

# 각 verified_by 경로에 대해
ls <verified_by_path> 2>/dev/null && echo "EXISTS" || echo "MISSING"

규칙:

  • verified_by = "추후 기입" → 상태 유지 ❌, 경고만 출력 ("이 조건의 verified_by 파일 경로가 아직 기입되지 않았습니다.")
  • 파일 EXISTS → 상태 ✅로 갱신
  • 파일 MISSING → 상태 ❌ 유지

중요: 파일 존재 여부만 확인합니다. 테스트 통과 여부는 CI/pytest 책임입니다.

Step 3 — STATE.md 갱신

검사 결과를 harness/STATE.md에 반영:

  • ✅ 로 바뀐 조건은 해당 행의 상태 컬럼을 업데이트
  • 변경된 행이 있으면 파일 저장 후 "N개 조건 갱신됨" 출력

Step 4 — 완료 선언 판정

상태 판정 출력
모든 조건 ✅ COMPLETE "모든 조건 검증 완료 — 완료 선언 가능합니다."
일부 ✅, 일부 ❌ PARTIAL "미검증 조건 N개 남음. 완료 선언 보류." + 미검증 목록
전부 ❌ BLOCKED "검증된 조건 없음. verified_by 파일을 먼저 생성하세요."

Step 5 — 대상 조건 매칭 (선택)

$ARGUMENTS가 조건 이름과 매칭되면 해당 조건만 선택적으로 체크:

  • "free quota", "gate f", "p95" 등 부분 문자열 매칭
  • 매칭된 조건 없으면 전체 조건 대상으로 실행

Output Format

hplan-verify — [날짜]

조건 상태:
  ✅ [조건 1] — verified_by: tests/unit/test_foo.py
  ❌ [조건 2] — verified_by: 추후 기입 (경로 미기입)
  ❌ [조건 3] — verified_by: tests/unit/test_bar.py (파일 없음)

판정: PARTIAL — 미검증 조건 2개
다음: verified_by 파일을 생성하거나 경로를 STATE.md에 기입하세요.

주의

  • 이 커맨드는 파일 존재만 확인합니다. 테스트 실행은 pytest tests/ 로 별도 실행하세요.
  • STATE.md의 verified_by를 채우는 것은 개발자 책임입니다.
  • COMPLETE 판정이 나와야 하나의 CONDITIONAL_GO 사이클이 닫힙니다.

--spec 단축 플래그

$ARGUMENTS--spec으로 시작하면 /harness-build --step spec-review로 라우팅한다.

# STATE.md 검사 대신 spec compliance 체크 실행
# /harness-verify --spec [brief]
# → harness-build --step spec-review [brief] 와 동일

이 플래그는 개발 완료 후 즉시 spec 준수 여부를 확인하고 싶을 때 사용한다. STATE.md 조건 검사(기본 동작)와 달리 PRD 대비 구현 완성도를 검토한다.

Read the full file on GitHub · 93 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 · 93 lines · 65 tokens per session scan A bc2a23b66633

Subscribe to this mod's changes

harness-verify is a command published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 20d ago), licensed MIT. It adds 65 tokens to every session and 945 once invoked, about $0.0003 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.