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 subagent-driven-developmentgit 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/subagent-driven-development)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/subagent-driven-development/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/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/subagent-driven-development.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 | $0.02198 |
| Opus 5.5 | $0.00000 | $0.00879 |
| Sonnet 5.5 | $0.00000 | $0.00440 |
| Haiku 4.5 | $0.00000 | $0.00220 |
Grade A, and why
subagent-driven-development 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent-Driven Development
来源: PDForge 类型: 协作模式型 Skill
Announce at start: "I'm using the subagent-driven-development skill to ensure high-quality implementation through fresh-context subagents and two-stage review."
Core Concept
每个任务分发给一个全新上下文的子代理执行:
- 子代理不知道其他任务的实现细节
- 子代理专注于当前任务
- 避免"上下文污染"导致的假设和捷径
每个任务完成后经过两阶段审查:
- 规格合规审查 - 是否满足计划要求
- 代码质量审查 - 是否符合最佳实践
Workflow
digraph skill_flow {
rankdir=TB;
node [shape=box];
READ_PLAN [label="读取计划\n提取任务列表"];
NEXT_TASK [label="获取下一个任务"];
DISPATCH_IMPL [label="Dispatch\nImplementer Subagent"];
IMPL_WORK [label="Implementer:\n遵循 TDD 实现\n自检后提交"];
SPEC_REVIEW [label="Dispatch\nSpec Reviewer Subagent"];
SPEC_CHECK [label="规格合规?" shape=diamond];
QUALITY_REVIEW [label="Dispatch\nCode Quality Reviewer Subagent"];
QUALITY_CHECK [label="质量合格?" shape=diamond];
MARK_DONE [label="标记任务完成"];
MORE_TASKS [label="还有任务?" shape=diamond];
DONE [label="全部完成"];
READ_PLAN -> NEXT_TASK;
NEXT_TASK -> DISPATCH_IMPL;
DISPATCH_IMPL -> IMPL_WORK;
IMPL_WORK -> SPEC_REVIEW;
SPEC_REVIEW -> SPEC_CHECK;
SPEC_CHECK -> QUALITY_REVIEW [label="通过"];
SPEC_CHECK -> IMPL_WORK [label="不通过\n修复"];
QUALITY_REVIEW -> QUALITY_CHECK;
QUALITY_CHECK -> MARK_DONE [label="通过"];
QUALITY_CHECK -> IMPL_WORK [label="不通过\n修复"];
MARK_DONE -> MORE_TASKS;
MORE_TASKS -> NEXT_TASK [label="是"];
MORE_TASKS -> DONE [label="否"];
}
Why Two-Stage Review?
单一审查常遗漏问题:
| 问题类型 | 单一审查 | 两阶段审查 |
|---|---|---|
| "代码写得好但不符合规格" | ❌ 常遗漏 | ✅ 规格审查捕获 |
| "符合规格但代码质量差" | ❌ 常遗漏 | ✅ 质量审查捕获 |
| "两者都有问题" | ⚠️ 可能只发现一个 | ✅ 分别发现 |
顺序不可颠倒:
- 先确保做对的事(规格合规)
- 再确保把事做好(代码质量)
Subagent Roles
1. Implementer (实现者)
职责:按任务规格实现代码
# 见 implementer-prompt.md
- 读取任务详情
- 遵循 TDD 实现
- 运行验证命令
- 自检后提交
2. Spec Reviewer (规格审查员)
职责:检查实现是否符合任务规格
# 见 spec-reviewer-prompt.md
- 对照任务规格检查
- 不关心代码质量
- 只关心"是否做了规格要求的事"
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 · 269 lines · 0 tokens per session scan A 4cfbef8e553b
subagent-driven-development is a skill 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 2,198 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 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…