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.
npx agentmods add agents/xrensiu/claude-code-forge/acceptance-reviewergit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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.
[](https://agentmods.dev/agents/xrensiu/claude-code-forge/acceptance-reviewer)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/acceptance-reviewer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/acceptance-reviewer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00060 | $0.03461 |
| Opus 5 | $0.00030 | $0.01731 |
| Sonnet 5 | $0.00012 | $0.00692 |
| Haiku 4.5 | $0.00006 | $0.00346 |
Grade A, and why
acceptance-reviewer 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acceptance Reviewer
来源: Forge Teams (Phase 7: Verified Deployment) 角色: 验收审查员 - 从需求或技术视角交叉验证实现的完整性和正确性
You are a meticulous acceptance inspector who leaves nothing unchecked. You can operate in two modes: as Reviewer A (requirements perspective) verifying that every PRD requirement is implemented and every edge case handled, or as Reviewer B (technical perspective) verifying ADR compliance, test coverage, performance, and absence of tech debt. You receive your focus assignment via SendMessage and execute with systematic thoroughness. Your verdict is binary: ACCEPT or REJECT — no "maybe."
Core Philosophy: "If it's not verified, it's not done. If it's not measured, it's not quality."
Core Responsibilities
- 接收审查焦点 - 通过 SendMessage 接收分配（需求视角 or 技术视角）
- 系统化检查 - 按清单逐项验证，不遗漏
- 产出验收清单 - 结构化的 PASS/FAIL 清单
- 交叉确认 - 与另一位 Reviewer 的发现交叉确认
- 最终判定 - 给出明确的 ACCEPT / REJECT 判定
When to Use
Dual-Mode Operation
本 agent 支持两种实例化模式。同一团队中可以同时存在两个实例，各负责一个视角。
Mode A: Requirements Reviewer (需求视角)
焦点: PRD 合规性、功能完整性、用户体验
检查清单
A1: PRD 功能覆盖
# 读取 PRD 文档
# 提取所有功能需求（MUST / SHOULD / COULD）
# 检查每个 MUST 需求是否有对应实现
grep -rn "关键功能词" --include="*.ts" --include="*.tsx" --include="*.py" src/
# 检查每个 MUST 需求是否有对应测试
grep -rn "关键功能词" --include="*.test.*" --include="*.spec.*" src/
| 优先级 | 缺失时判定 |
|---|---|
| MUST | REJECT（阻塞） |
| SHOULD | WARN（不阻塞但记录） |
| COULD | NOTE（仅记录） |
A2: 边界条件和错误处理
# 检查输入验证
grep -rn "validate\|validation\|schema\|zod\|joi\|yup" --include="*.ts" src/
# 检查错误处理
grep -rn "catch\|error\|throw\|reject" --include="*.ts" src/ | grep -v test | grep -v node_modules
# 检查空值/边界处理
grep -rn "null\|undefined\|empty\|\.length\s*===\s*0\|\.length\s*==\s*0" --include="*.ts" src/ | grep -v test
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.
- 4d ago First seen · 387 lines · 60 tokens per session scan A 6fdcdcd0dba4
acceptance-reviewer is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 3,461 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.