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 commands/jzl-maker/ea-skill/newgit clone --depth 1 https://github.com/jzl-maker/EA-SKILLWhat 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 | $0.00000 | $0.01046 |
| Opus 5 | $0.00000 | $0.00523 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00105 |
Grade A, and why
new 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
命令: /ea new (新功能开发)
功能
进入新功能开发流程。嵌入式聚焦的两档分流：轻档直接改，标准档 brainstorm → plan → execute。避免轻量需求被重流程拖累，也避免重特性被轻流程带偏。
触发
/ea new <功能描述> # AI 推荐档位，用户确认
/ea new <功能描述> --light # 强制轻档
/ea new <功能描述> --std # 强制标准档（默认）
两档总览
| 档位 | 适用 | 产出文件 | 时长 | 工作流 |
|---|---|---|---|---|
| 轻 light | < 2h 工作量、单文件改动、bugfix、调参、简单逻辑 | quick-plan.md |
~5 min | workflows/new-light.md |
| 标准 standard（默认） | 跨模块特性、新外设、需设计 | brainstorm.md + milestones.md |
~15 min | workflows/new-standard.md |
档位推荐启发式
| 信号 | 加分到 |
|---|---|
| 描述 ≤ 30 字 / 关键词：修复/fix/调整/优化/改进/重命名 | 轻 |
| 关键词：实现/接入/集成/添加模块 | 标准 |
| 关键词：架构/系统/协议栈/状态机/重构 | 标准 |
| 涉及新外设/新芯片/时序/实时性（嵌入式硬件维度） | 标准（强制硬件对齐阶段） |
默认: 标准档。
执行流程
- 【状态目录】
get_state_dir()→ 不存在提示/ea init - 【读 context】 必须先读
<STATE_DIR>/context.md（芯片/外设/模块地图/保护区）——理解工程再规划 - 【步骤号分配】 读
state.md/project-spec.md步骤表，取最大 S + 1 - 【档位选择】
- 命令带
--light/--std→ 直接采用 - 否则按启发式推荐，输出：
🆕 新功能: <描述> 分配步骤: S<N> 推荐档位: <轻|标准> 理由: <一句话> 其他档位: /ea new ... --light | --std ━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 输入 `继续` 采用推荐档位，或输入 `轻/标准` 改档。
- 命令带
- 【加载对应工作流】 轻 →
new-light.md；标准 →new-standard.md - 【按工作流执行】 标准档含嵌入式硬件对齐阶段（外设/引脚/时序/实时性约束）
- 【收尾】 更新
state.md（下一步动作 =/ea verify s<N>），写入project-spec.md步骤表
公共规则
- 步骤编号：
S<数字>，废弃不复用 - 讨论目录：
<STATE_DIR>/discussion/<YYYYMMDD>-<slug>/ - 修改红线：开发过程中所有文件改动遵守 SKILL.md 红线——保护区文件禁随意改、增量修改、改动给 diff
- 强制约束：流程未完成禁止
/ea verify//ea record
输出格式（确认阶段后）
🆕 S<N>: <功能描述>
档位: <轻|标准>
讨论ID: <YYYYMMDD>-<slug>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<工作流首阶段提示，由对应 workflow 文件给出>
设计原则
- superpower 精神：先 brainstorm → 再 plan → 再 execute
- 两档分流：轻量需求不被重流程拖累；嵌入式硬件维度进标准档
- 先 context 后动手：AI 对老工程有上下文感知再开发
- 增量约束：全程给 diff，禁全盘重写
相关文件
workflows/new-light.md— 轻档流程workflows/new-standard.md— 标准档流程templates/context.md— 工程上下文（先读）commands/verify.md— 验证
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 · 79 lines · 0 tokens per session scan A 310ab518adf9
new is a command published in the GitHub repository jzl-maker/EA-SKILL (6 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,046 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 2026-08-31.
Other commands, from other repositories
analyze-repo
Analyze an existing repository's structure, conventions, and guardrails.
go-review
Go code review for idiomatic patterns.
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.
doctor
Run IJFW health check (files, MCP server, hooks, memory, caps, framing).
example-only
This command documents how to dispatch. Example only.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.