Acceptance Tester — Testing & QA agent for Claude Code
PlanGate V-1 受け入れ検査エージェント.
How to install Acceptance Tester
Installs to ~/.claude/agents/s977043-plangate-acceptance-tester.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/s977043/PlanGate/HEAD/.claude/agents/acceptance-tester.md -o ~/.claude/agents/s977043-plangate-acceptance-tester.md Restart Claude Code, or start a new session, for it to be picked up.
What Acceptance Tester does
name: acceptance-tester description: PlanGate V-1 受け入れ検査エージェント。test-cases.md の完了条件を1つずつ機械的に突合し、PASS/FAIL を判定する。推測ではなく実行結果のみで判定する。 tools: Read, Grep, Glob, Bash model: inherit
Acceptance Tester — V-1 Verification Agent
プロジェクト共通制約は `CLAUDE.md` を参照。日本語でやり取りし、安全・品質を優先する。
V-1 受け入れ検査を担当する。test-cases.md の完了条件を**1つずつ機械的に突合**し、実行結果に基づいて PASS/FAIL を判定する。
Iron Law
`NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE`
推測・記憶・過去の結果に基づく判定は禁止。全テストケースを**今この瞬間に**実行し、その出力を根拠とする。
Commo
Alternatives in Testing & QA
- Civitai Test Review — Reviews the tests in a feature segment of the main Civitai Next.js app (src/) for whether they would actually 7.2k ★
- Fable Verifier — Cold verifier for finished fable deliverables 837 ★
- Bowser QA Agent — UI validation agent that executes user stories against web apps and reports pass/fail results with screenshots 222 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Frontend Tester
Frontend web testing specialist that uses BYOB MCP to execute UI test scenarios and return structured results.
Device Tester
Executes a manual test scenario on an Android app running on the connected device. Acts, doesn't analyze. Retu
Tms Agent
Use this agent for anything involving the test management REST API - creating test cases from a specs/ .plan.m
Squad QA
Operate as the squad's behavioral QA gate — verify observable behavior against acceptance criteria and risk, r
Uiux
Writes an HDS-grounded UI spec before any UI-affecting task is coded, and runs the post-test visual pass again
Playwright Tester
Runs Playwright spec files against the local dev server and reports AC pass/fail. Evaluator role — does not wr
Related Skills
Execute Test Cases
Thực thi manual test cases trên browser thật qua Playwright MCP — chấm PASS/FAIL/BLOCKED/SKIPPED, thu evidence
QA Integration
Run integration/E2E QA against a RUNNING app via a real browser — execute new + regression test cases, assert
Octobench
Benchmark harness that compares coding agents — not just models — on real, contamination-resistant tasks: 80 f