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.
git 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/commands/xrensiu/claude-code-forge/accept)<a href="https://agentmods.dev/commands/xrensiu/claude-code-forge/accept"><img src="https://agentmods.dev/badge/commands/xrensiu/claude-code-forge/accept/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/xrensiu/claude-code-forge/accept"><img src="https://agentmods.dev/badge/commands/xrensiu/claude-code-forge/accept.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.06613 |
| Opus 5.5 | $0.00000 | $0.02645 |
| Sonnet 5.5 | $0.00000 | $0.01323 |
| Haiku 4.5 | $0.00000 | $0.00661 |
Grade A, and why
accept 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 1mo 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 — 779 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
执行三阶段验收审查（规格合规、代码质量、安全漏洞），从选定的审查角度进行评估。必须输出持久化报告文件。可选自动修复发现的问题并在智能断路器保护下重新验证。
规格输入方式
直接指定
单个文件：
/accept docs/prd/user-auth.md src/auth/
多个文件：
/accept docs/prd/auth.md docs/prd/session.md src/auth/
Glob 模式 (--spec-pattern)：
/accept --spec-pattern "docs/prd/v2/*.md" src/
目录扫描 (--spec-dir)：
/accept --spec-dir docs/prd/payment/ src/payment/
索引驱动
对于多功能项目，维护 specs/manifest.json 索引文件：
{
"version": "1.0",
"features": [
{
"name": "user-auth",
"description": "用户认证和会话管理",
"specs": ["docs/prd/auth/login.md", "docs/prd/auth/session.md"],
"code": ["src/auth/**", "src/middleware/auth.ts"],
"status": "complete"
},
{
"name": "payment-checkout",
"description": "支付处理和结账流程",
"specs": ["docs/prd/payment/checkout.md"],
"code": ["src/payment/**"],
"status": "in-progress"
}
]
}
按功能名 (--feature)：
/accept --feature user-auth
/accept --feature user-auth --feature payment-checkout
按状态 (--status)：
/accept --status in-progress
/accept --status in-progress --fix --loop
审查员选择
包含标志（只运行指定的）
| 标志 | 说明 |
|---|---|
--design |
只运行设计还原审查 |
--spec |
只运行规格审查 |
--code |
只运行代码审查 |
--security |
只运行安全审查 |
组合使用：--spec --code 运行规格和代码审查，跳过安全审查
排除标志（运行除指定外的所有）
| 标志 | 说明 |
|---|---|
--skip-design |
跳过设计还原审查 |
--skip-spec |
跳过规格审查 |
--skip-code |
跳过代码审查 |
--skip-security |
跳过安全审查（不推荐） |
默认行为：无标志 = 运行全部审查（设计审查仅在有设计参考时自动启用）
自动修复选项
修复标志
| 标志 | 说明 |
|---|---|
--fix |
审查后自动修复所有问题 |
--fix-blockers |
审查后仅自动修复 blocker 问题 |
| 无标志 | 仅审查不修复（默认） |
循环标志（需配合 --fix）
| 标志 | 说明 |
|---|---|
--loop |
修复后重新验证，最多重复 3 次（默认） |
--loop <N> |
设置最大迭代次数（1-10） |
循环行为：
- 所有问题解决后提前停止
- 断路器触发后停止
- 收到完成承诺后停止
- 每次迭代在会话目录中生成独立报告
断路器
断路器通过检测卡住状态防止无限或浪费的循环。
断路器状态
| 状态 | 符号 | 行为 |
|---|---|---|
| CLOSED | 🟢 | 正常运行，继续修复 |
| HALF-OPEN | 🟡 | 测试恢复中，仅修复 blocker |
| OPEN | 🔴 | 检测到卡住，停止修复，需人工干预 |
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.
- 1mo ago First seen · 779 lines · 0 tokens per session scan A 7fb866aa538c
accept is a command published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,613 tokens. 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 2026-09-05.
Other commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
refactor
Systematic code refactoring with smart scope detection.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).