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/simpleeve/eo-skills/eo-loopnpx skills add SimpleEve/eo-skills --skill eo-loopgit clone --depth 1 https://github.com/SimpleEve/eo-skillsWrote 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/simpleeve/eo-skills/eo-loop)<a href="https://agentmods.dev/skills/simpleeve/eo-skills/eo-loop"><img src="https://agentmods.dev/badge/skills/simpleeve/eo-skills/eo-loop.svg" alt="Measured on agentmods" 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 | $0.00151 | $0.04524 |
| Opus 5 | $0.00076 | $0.02262 |
| Sonnet 5 | $0.00030 | $0.00905 |
| Haiku 4.5 | $0.00015 | $0.00452 |
Grade A, and why
eo-loop 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 today.
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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eo-loop — eo 流程总控
总控只做五件事：识别、派发、路由、循环、汇报。三不做：不亲自写代码、不改 change 实质内容、不复述下游流程（节点内部怎么做由各 eo-* skill 自治）。
总控无状态：流程真相只在 change.md frontmatter 与报告文件里。会话断了，任何 agent 重读 frontmatter 即可从当前节点继续。
总控在哪：用户在哪个会话喊 /eo-loop，哪个会话就是总控。
前置条件
- 必须能找到
.eo-project.json。同目录存在.eo-project.local.json时顶层字段覆盖合并（local 优先）。找不到 → 报错退出，提示运行/eo-project-init - 线段涉及已有 change 时，定位其
eo-doc/changes/<NN>-<slug>/（口头引用按 ../eo-shared/conventions.md §2 经 INDEX 解析）
调度哲学（四步闭环）
① 圈线段：从用户话语确定三要素——入口节点、出口节点、收敛标准。v3 默认线段很短：
默认主路：change → implement → archive
信号命中：主路对应位置插入闸门（change 确认后插 change-review；implement 后插 test / review）
地图是 ../eo-shared/conventions.md §3 的状态机。三要素判不出的，先查偏好文件补缺省（见「经验沉淀」）；仍缺 → 按封闭选择协议（../eo-shared/questioning.md §4）问一次，不追问第二轮。
入口是已确认的 change 序列（带「依赖 #N」标注，如 brainstorming 捕获出口确认后的产物）时：按依赖序串行推进（无标注 = 串行），逐个 change 走完对应 eo-* 节点（默认主路，信号命中照常插闸门）；节点边界 = 观测点，按「可观测性」节口径汇报。
随手小改先过 trivial 闸：总控会话里用户随手提的修改，先按 ../eo-shared/granularity.md §2 判定——trivial → 总控直改（需起环境验证才派原 impl worker），commit 前缀按 conventions §2.5，不进状态机、不产工件；改动使活跃 change 的 AC / 文本与实际不符时，顺手就地精化文本。四判据任一不满足 → 回到正常圈段。
举例措辞判据：用户意图含「比如 / 之类 / 例如」= 形态未定稿——先安排探针对齐（change 确认）把形态钉下来再派实施节点，不得让例子直接当定稿进派发 prompt。
条件式 Execution Guard：圈段后若命中任一条件——长程（跨多轮或跨节点）、并行、无人值守、高风险（安全 / 权限 / 数据 / 不可逆动作）、存在开放未知——本线段启用 ../eo-shared/goal-contract.md，总控在每个节点派发前从现有真相源即时编译控制包。来源限于当前 change.md、报告、Git 基线与用户本轮授权；本轮授权只能收紧运行边界，若与已冻结的 Why / 范围 / AC 冲突，必须先走用户裁决与 change 回炉。控制包只存在于本轮派发上下文，不落盘、不造第二信源。未命中条件则沿用普通调度。
控制包只投影六项，不创造新要求：意图与出口 / 证据门（每项结论由哪个角色基于什么工件证明）/ 运行边界 / 取舍顺序（引 goal-contract）/ 未知权限（引 goal-contract Unknown 分流）/ 路由事实。
Unknown 的运行时动作（分类语义以 goal-contract 为唯一来源）：
- A 类：核对确在权限包络内 → 允许 worker 先做后报
- B 类：worker 变更前发求裁决信号并暂停受影响分支；总控把同窗 B 类合并成一次封闭选择交用户
- C 类：worker 变更前立即停下，总控立即上交用户
- 证据未知：只允许一次有界探测（写清问题、预算、停止条件）；仍拿不到 → fail-closed，结论只能「未验证 / 阻塞」，不得用 worker 自述补证
What ships with it
5 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.
- today First seen · 176 lines · 151 tokens per session scan A c1848dfcefec
eo-loop is a skill published in the GitHub repository SimpleEve/eo-skills (31 stars, last pushed 3d ago), licensed MIT. It adds 151 tokens to every session and 4,524 once invoked, about $0.0008 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 2026-09-04.
Other skills, from other repositories
to-issues
Decompose a PRD and/or SPEC into implementable, vertically-sliced Issues with real blocking edges, then create them in your chosen platform (GitHub or Local). Use after /prd (and optionally /prd-to-spec) to turn requirements into agent-ready tickets. Triggers on: create issues, to-issues, 创建issue, 拆解issue, 生成卡片, 创建卡片…
issue-report-generator
Automatically generate clear, actionable issue reports from failing tests and repository analysis. Analyze test failures to understand expected vs. actual behavior, identify affected code components, and produce well-structured Markdown reports suitable for GitHub Issues or similar trackers. Use when a test fails…
github-triage
Unified GitHub triage for issues AND PRs. Classifies open items, answers questions from codebase, analyzes bugs, reviews PRs, and produces a structured triage report. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'.
python-repo-quickstart
Quickly analyzes Python repositories to understand their purpose, structure, and setup requirements. Use when Claude needs to onboard to a new Python codebase, understand project structure, identify entry points, determine dependencies, or generate setup instructions. Trigger when users ask to "analyze this Python…
openase-platform
Platform operations for tickets, projects, and runtime coordination inside OpenASE.
ticket-workpad
Maintain the persistent ticket work log comment on the current ticket and use it as the execution log.