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 skills/programmeranthony/expert-coding-harness/subagent-driven-developmentnpx skills add ProgrammerAnthony/Expert-Coding-Harness --skill subagent-driven-developmentgit clone --depth 1 https://github.com/ProgrammerAnthony/Expert-Coding-HarnessWhat 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 | $0.00066 | $0.01746 |
| Opus 5 | $0.00033 | $0.00873 |
| Sonnet 5 | $0.00013 | $0.00349 |
| Haiku 4.5 | $0.00007 | $0.00175 |
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 2d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
子代理驱动开发
按书面实施计划逐任务推进：每个任务派发新的实现子代理（隔离上下文），任务完成后依次做 规格符合性审查 → 代码质量审查（顺序不可颠倒）。主会话负责读计划一次、提取任务全文、协调与决策，不把整段对话历史灌给子代理。
开场声明：「我正在使用子代理驱动开发技能执行计划。」
与「同会话逐步执行」的区别： 本技能强调每任务新子代理 + 双审查；若用户选择在当前会话手写每一步、不用 Task 派子代理，可改按 references/inline-execution-hint.md 配合 tdd-master（TDD 开发大师） 与 code-review-expert（代码审查专家），不再套用下文的 Task 模板。
Inputs / Outputs / Gates / Handoffs（统一契约）
- Inputs（最小输入）：一份书面实施计划（必须包含任务全文：步骤、代码块、命令、预期输出）；当前分支/工作目录信息。
- Outputs（产物形态）：按任务推进的执行记录（主会话 Todo 勾选）+ 每任务的 3 段产物：实现结果、规格符合性审查、代码质量审查。
- Gates（继续前必须满足）：
- 不允许子代理自行打开计划文件代替你粘贴任务全文（除非平台强制且无法粘贴，并需说明风险）。
- 审查顺序硬门控：先规格符合性审查 → 后代码质量审查。
- 发现阻塞问题必须回到实现修复并复审，通过后才进入下一任务。
- Handoffs（推荐下游）：
code-review-expert（代码审查专家）：整体收尾审查/质量门禁debug-expert（调试专家）：实现或测试失败时切换排查
适用条件
- 已有实施计划（推荐由
writing-plans（实施计划编写）产出），任务粒度小、相对独立。 - 平台支持 Task / 子代理 等派发能力；若不支持，改用同会话执行提示文件。
flowchart TD
A[有实施计划?] -->|否| Z[先完成方案设计与实施计划编写]
A -->|是| B[任务可独立切片?]
B -->|否| Y[收紧计划或改人工串行]
B -->|是| C[本技能: 子代理逐任务]
总流程
- 读计划一次，提取全部任务标题与完整任务正文（含步骤、代码块、命令），不要让子代理自己去读计划文件。
- 用 TodoWrite（或等价方式）列出所有任务，随进度更新。
- 对每个任务循环：
- 派发 实现子代理（
references/implementer-prompt.md） - 根据返回状态处理（见下节「实现者状态」）
- 通过后派发 规格符合性审查（
references/spec-reviewer-prompt.md） - 规格 ✅ 后派发 代码质量审查（
references/code-quality-reviewer-prompt.md，对齐code-review-expert（代码审查专家）的严重度与证据要求） - 两道审查均未决问题后，勾选任务完成
- 派发 实现子代理（
- 全部任务完成后：建议对整体变更再做一次
code-review-expert（代码审查专家）级别的汇总审查（可再派子代理），并请用户确认合并/PR；若项目后续提供「分支收尾」类技能可再衔接。
实现者状态处理
实现子代理须返回以下之一：
| 状态 | 处理 |
|---|---|
| DONE | 进入规格符合性审查 |
| DONE_WITH_CONCERNS | 先阅读关切；涉及正确性/范围的先处理再审查；仅为观察性备注可记录后继续 |
| NEEDS_CONTEXT | 补充上下文后重新派发同一任务 |
| BLOCKED | 缺信息则补上下文；能力不足则换更强模型；任务过大则拆计划；计划错误则上升用户 |
禁止忽视 BLOCKED、禁止无变更重复派发同模型硬重试。
模型选用（节省成本）
- 机械实现（1–2 文件、规格完整）：较快、较省模型。
- 多文件集成与判断：标准能力模型。
- 架构与审查：在可用范围内选最强模型。
提示词模板（必读路径）
| 文件 | 用途 |
|---|---|
references/implementer-prompt.md |
实现子代理 |
references/spec-reviewer-prompt.md |
规格符合性审查（先） |
references/code-quality-reviewer-prompt.md |
代码质量审查（后） |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 132 lines · 66 tokens per session scan A 87f580960eed
subagent-driven-development is a skill published in the GitHub repository ProgrammerAnthony/Expert-Coding-Harness (234 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 1,746 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 2026-08-30.
Other skills, from other repositories
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
agentmail
Use when an agent needs AgentMail CLI email inboxes.
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
skill-creator
Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.