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 skills add XRenSiu/claude-code-forge --skill verify-requirementgit 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/skills/xrensiu/claude-code-forge/verify-requirement)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/verify-requirement"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/verify-requirement/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/skills/xrensiu/claude-code-forge/verify-requirement"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/verify-requirement.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 | $0.00116 | $0.04791 |
| Opus 5.5 | $0.00046 | $0.01916 |
| Sonnet 5.5 | $0.00023 | $0.00958 |
| Haiku 4.5 | $0.00012 | $0.00479 |
Grade A, and why
forge-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 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 — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Verify - 独立需求验证
描述需求 → 结构化 → 映射代码实现 → 测试验证 → 差距报告。
这是 forge-teams 的独立需求验证入口。复用 spec-reviewer 的逐条验证方法论,但输入不依赖 P1 的 PRD,而是直接接收用户提供的需求描述。
Announce at start: "I'm using the forge-verify skill to check whether the described requirements are implemented in the current codebase."
注意: 本 skill 不需要 Agent Teams,使用 Lead 单 agent 流程执行。
用法
/forge-verify <requirement-description> [options]
参数说明
| 参数 | 说明 | 默认值 |
|---|---|---|
<requirement-description> |
需求描述(文本、文件路径、或 URL) | 必填 |
--strict |
严格模式:PARTIAL 视为 FAIL | 宽松模式 |
--with-tests |
对每条 "已实现" 需求检查测试覆盖 | 不检查 |
--fix |
发现 Gap 后自动补齐实现(PARTIAL → 补全,NOT_IMPLEMENTED → 实现) | 不修复 |
--loop <N> |
修复后重新验证,最多 N 轮(需配合 --fix) |
3 |
--format <format> |
输出格式:matrix(完整合规矩阵)或 summary(摘要) |
matrix |
--scope <path> |
限定验证范围到指定目录 | 整个项目 |
示例
# 只验证,不修复
/forge-verify "用户可以通过邮箱注册,密码至少8位,注册后发送验证邮件"
# 从文件加载需求
/forge-verify requirements.md
# 严格模式 + 检查测试覆盖
/forge-verify "支持 OAuth2 登录和 JWT token 刷新" --strict --with-tests
# 验证 + 自动补齐实现
/forge-verify "用户可以通过邮箱注册,密码至少8位,注册后发送验证邮件" --fix
# 验证 + 补齐 + 多轮循环直到全部通过
/forge-verify "支持 OAuth2 登录和 JWT token 刷新" --fix --loop 5
# 只检查特定目录
/forge-verify "API 支持分页和排序" --scope src/api/
输出目录
docs/forge-verify/
└── [requirement-slug]-[timestamp]/
├── structured-requirements.md # 结构化需求
├── code-mapping.md # 需求到代码映射
├── test-coverage.md # 测试覆盖检查(--with-tests)
├── gap-report.md # 差距报告
├── fix-log.md # 修复记录(--fix)
└── summary.md # 最终摘要
Protocol Overview
┌─────────────────────────────────────────────────────────────────┐
│ VERIFY REQUIREMENT │
├─────────────────────────────────────────────────────────────────┤
│ │
│ Phase 0: STRUCTURIZE 将大白话需求翻译成可验证条件 │
│ ↓ EARS 格式 + 验收标准 │
│ │
│ Phase 1: CODE MAPPING 逐条需求搜索代码实现 │
│ ↓ Grep + Glob + 代码阅读 │
│ │
│ Phase 2: TEST VERIFY 检查测试覆盖(可选) │
│ ↓ 对 "已实现" 的需求验证测试 │
│ │
│ Phase 3: GAP REPORT 综合差距报告 │
│ ↓ 5 级分类 + 修复建议 │
│ │
│ [--fix enabled] │
│ │
│ Phase 4: AUTO FIX 逐条补齐缺失实现 │
│ ↓ 按优先级: NOT_IMPLEMENTED → PARTIAL │
│ TDD: 先写测试 → 再实现 → 验证通过 │
│ │
│ Phase 5: RE-VERIFY 重新验证(回到 Phase 1) │
│ 只重验 Phase 4 修改的需求 │
│ 最多 --loop N 轮 │
│ │
└─────────────────────────────────────────────────────────────────┘
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 · 540 lines · 116 tokens per session scan A 2869a84c4bea
forge-verify is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 116 tokens to every session and 4,791 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…