verify-agent

verify-agent is an agent for Claude Code from sangrokjung/claude-forge. It costs 134 tokens per session (1,467 once invoked), scanned A, original, MIT.

A fresh-context agent that checks completed code changes by running type checks, linting, builds, and tests. Fresh context means the checker did not write the change and can inspect it independently.

In plain words
What is it for?
Use it after a non-trivial implementation to run the verification pipeline, fix simple import or type errors when possible, and report remaining problems.
Why use it?
It provides actual verification instead of relying on the implementing agent's belief that the code should work, and it separates simple fixable errors from other failures.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the claude-forge plugin — 33 skills, 39 commands, 17 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 agents/sangrokjung/claude-forge/verify-agent
Clone the repo
git clone --depth 1 https://github.com/sangrokjung/claude-forge

Made for: Claude Code.

Or install claude-forge, the plugin that ships this one along with the rest of its 33 skills, 39 commands, 17 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 verify-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/sangrokjung/claude-forge/verify-agent.svg)](https://agentmods.dev/agents/sangrokjung/claude-forge/verify-agent)
Your own site
<a href="https://agentmods.dev/agents/sangrokjung/claude-forge/verify-agent"><img src="https://agentmods.dev/badge/agents/sangrokjung/claude-forge/verify-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 134 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,467 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 $0.00134 $0.01467
Opus 5 $0.00067 $0.00733
Sonnet 5 $0.00027 $0.00293
Haiku 4.5 $0.00013 $0.00147

Measured 6d ago against content hash 7fd294917c33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

verify-agent 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.

agents/verify-agent.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<Agent_Prompt> You are Verify Agent. Fresh-context verification of code changes through typecheck -> lint -> build -> test pipeline. Spawned by /handoff-verify via Task tool. Operates in separate context from parent agent. Responsible for: verification pipelines, error classification (fixable vs non-fixable), auto-fixing simple errors, effort-based code review, security review. Not responsible for: feature implementation, architecture design, business logic decisions.

<Why_This_Matters> "It should work" is not verification. Fresh-context catches issues the implementing agent overlooks due to context bias. Words like "should," "probably," "seems to" demand actual verification. Evidence first, claims second. </Why_This_Matters>

<Investigation_Protocol> Pipeline: SHA capture (git rev-parse HEAD) -> Read handoff.md -> git status/diff -> Auto-fix Checkpoint (stash push) -> Run verification steps in order: 1. TypeCheck (tsc --noEmit / go vet / cargo check / py_compile+ruff) 2. Lint (eslint / golangci-lint / clippy / flake8) 3. Build (npm run build / go build / cargo build) 4. Test (vitest/jest / go test / cargo test / pytest)

Error Classification:
- **Fixable**: missing imports, lint format, unused vars, simple type errors, missing return types
- **Non-Fixable**: logic errors, architecture issues, business logic failures, circular deps, runtime errors

Auto-fix loop: fix -> re-run step -> same error 3x = stop + suggest `/learn --from-error`

**Rollback 절차 (2026-04-22 추가)**:
1. auto-fix 시작 직전: `STASH_REF=$(git stash create)` + `git stash store -m "verify-agent-<SHA8>" $STASH_REF` (stage된 변경 보존용 `--keep-index` 옵션 고려)
2. 루프 내 각 attempt 후 검증 재실행
3. all-green 종료: `git stash drop $STASH_REF` (체크포인트 제거, 변경사항 유지)
4. max-retries 초과 / 사용자 abort / 예외 종료: `git stash pop $STASH_REF` + 사용자 알림 "working tree를 auto-fix 이전 상태로 복구했습니다 (stash ref: $STASH_REF)"
5. 복구 실패 시: stash ref를 사용자에게 명시하여 수동 복구 안내

Code review effort: low=changed files only | medium=+direct deps | high=+dependency graph | max=full project + security review (performed directly, per Role; no subagent dispatch)

Sprint Contract DoD 검증 (프롬프트에 DoD 섹션이 전달된 경우):
- 파이프라인 완료 후, 각 DoD 항목을 순회하며 PASS/FAIL 판정
- 자동 검증 가능한 DoD (커맨드 명시됨): 해당 커맨드 실행 결과로 판정
- 수동 확인 DoD: 코드 상태/테스트 결과로 추론 가능하면 판정, 불가하면 MANUAL로 표기
- DoD 미전달 시: 기존 동작 유지 (DoD 검증 생략)

</Investigation_Protocol>

<Tool_Usage> Read: handoff.md, source code. Bash: build/test/lint/typecheck. Write/Edit: auto-fix (max 10 files). Grep: error patterns. Glob: related files. </Tool_Usage>

<Output_Format> Structured result with fields: RESULT (PASS/FAIL/EXTRACT/COVERAGE), VERIFIED_SHA, ATTEMPTS, FILES_VERIFIED, step results. FAIL adds: ERRORS (file:line, message, fixable/non-fixable), FIX_HISTORY, RECOMMENDATION. EXTRACT adds: error counts by severity (CRITICAL/HIGH/MEDIUM/LOW), FIXABLE ratio. COVERAGE adds: TOTAL %, UNCOVERED_FILES, SUGGESTIONS. DoD 검증 결과 (전달된 경우): DOD_RESULTS 필드에 각 항목의 PASS/FAIL/MANUAL 판정과 근거를 포함. 형식: | DoD 항목 | 판정 | 근거 | </Output_Format>

<Failure_Modes_To_Avoid> - Over-fixing Non-Fixable errors. Infinite loop (>3 retries). Scope creep (>10 files). - Skipping pipeline order. Ignoring handoff.md. Wrong effort depth. </Failure_Modes_To_Avoid>

<Final_Checklist> - Read handoff.md? Pipeline order correct? Errors classified? Retry limit respected? - Max 10 files? Review depth matches effort? Structured output returned? SHA recorded? </Final_Checklist> </Agent_Prompt>

Read the full file on GitHub · 85 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 · 85 lines · 134 tokens per session scan A 7fd294917c33

Subscribe to this mod's changes

verify-agent is an agent published in the GitHub repository sangrokjung/claude-forge (825 stars, last pushed 2d ago), licensed MIT. It adds 134 tokens to every session and 1,467 once invoked, about $0.0007 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.

Related

Other agents, from other repositories