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 SimpleEve/eo-skills --skill eo-fixgit 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-fix)<a href="https://agentmods.dev/skills/simpleeve/eo-skills/eo-fix"><img src="https://agentmods.dev/badge/skills/simpleeve/eo-skills/eo-fix.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.04675 |
| Opus 5 | $0.00046 | $0.02337 |
| Sonnet 5 | $0.00018 | $0.00935 |
| Haiku 4.5 | $0.00009 | $0.00468 |
Grade A, and why
eo-fix 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 4d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eo-fix — Bug 修复
三层按需付费：默认快路 ≈ 直接修 + 30 秒记账；只有要推翻一个「可能是有意的行为」时才取证；只有定位不了才深挖。对一个 typo，本 skill 的开销趋近于零——任何不触发的层都不存在。
核心原则
- 快路优先：明显缺陷（报错、崩溃、数据错、无争议逻辑错）不查任何文档，直接修
- 推翻行为前必取证：现象是「应该/不应该」类语义分歧时，先花几百 token 确认该行为不是有意设计——防止静默推翻已确认的决策
- 落点记账不豁免：修复必须落进体系（勾 AC / commit 前缀），这是 archive 归集、看板、retro 统计的输入
- 定位靠代码反查：症状 grep 源码 + git log 前缀追溯，精确且便宜；禁止全局 grep eo-doc 正文
- 深挖有门：升级必宣告、结束必还原
前置
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。
工作流程
第一步：分诊（一眼定路）
| 现象特征 | 走 |
|---|---|
| 「坏了 / 报错 / 崩了 / 数据不对」——对错无需文档裁决 | 快路（第二步 → 第三步） |
| 「这里应该… / 为什么会… / 这个行为不对吧」——行为疑似有意实现、涉及业务规则或数值 | 取证路（第二步 → 第四步） |
| 描述弥散、无从下手 | 第二步定位；仍无果 → 深挖（第五步） |
同时按 ../eo-shared/lessons.md §1 消费 lessons——同类坑踩过的，「规则」节直接给答案或作假设先验。
第二步：定位（代码反查为主，~500-900 token）
- 锚定代码：有症状字符串（报错文案 / UI 文案）→ 直接 grep 源码，几乎一步中的；没有 →
.codegraph/索引存在则codegraph explore定位模块入口，不存在则按目录收敛直读源码 - 反查归属：
git log --oneline -n 20 -- <嫌疑文件>看 commit 前缀——[<change-id>]（slug 或存量数字前缀）→ 相关 change 直达；fix:/ui:→ 直改历史（无书面期望）；无前缀 → 存量代码 - 需要书面期望时只读该 change 的 frontmatter + §2 AC，不通读
辅路（代码反查不灵时才用）：扫 eo-doc/changes/INDEX.md——活跃 change 置顶且通常只有 0-3 个，先看它们（刚做完的最容易坏）；不中再按关键词扫 archived 区。候选 >3 或全无匹配 → 追问用户。
第三步：快路修复
最小变更修复 → 用户给的复现步骤转成回归验证跑通 → 跳到第六步落点记账。中途发现行为其实可能是有意的 → 转第四步。修复代码注释零溯源：change/AC/finding 标记与修复辩护不进注释（项目级完整纪律见 eo-doc/agent-handbook/comments.md，如已启用）。
复现与回归都取最低成本层：修前先在该层复现失败（这是根因判断的依据，也是「改完看起来对了」之外唯一的证据），修后在同层验通过。层的选法——纯逻辑用单测 / node -e 等价复刻（秒级），接口契约用一次请求，确属集成 / UI 态才起环境（环境纪律见 ../eo-shared/ac-spec.md）。不要每改一行就重新 build + 起环境。
第四步：取证路（仅语义分歧）
证据瀑布——期望行为不是单一锚点，按可得性降级取证：
| 优先 | 证据 | 作用 |
|---|---|---|
| 1 | 用户当下的口述 | 最高权威，永远存在 |
| 2 | 相关 change 的 §2 AC（若有） | 最优书面期望 |
| 3 | eo-doc/state/ 现状篇（若 state.enabled 启用） |
意图佐证：行为被现状篇记为规则 = 曾被认为正常（state 是代码派生快照，只能佐证不能裁决）；篇≠码 → 文档陈旧，提示可跑 /eo-doc-manager sync |
| 4 | <project_root>/decisions/ 与 brainstorm/ 的记录 |
意图佐证：行为被钉为决策 = 曾被认为正常（只能佐证意图，不能裁决代码对错） |
| 5 | git 归属（commit 前缀） | 追溯行为来源 |
What ships with it
1 file 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.
- 4d ago Changed · -25 lines · -53 tokens per session ef762bd47e0f
- 8d ago First seen · 191 lines · 144 tokens per session scan A 1eac6a15d5fb
eo-fix is a skill published in the GitHub repository SimpleEve/eo-skills (31 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 4,675 once invoked, about $0.0005 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
bug-localization
Identify the precise location of bugs in source code, modules, and systems. Use this skill when debugging applications, investigating test failures, analyzing error reports, tracing runtime issues, or performing root cause analysis. Analyzes stack traces, error messages, failing tests, and code patterns to pinpoint…
bug-to-patch-generator
Generate code fixes and patches from bug reports, failing test cases, error messages, and stack traces. Use this skill when debugging code, fixing test failures, addressing GitHub issues, resolving runtime errors, or patching security vulnerabilities. Analyzes the bug context, identifies root causes, and generates…
counterexample-generator
Generate concrete counterexamples when formal verification, assertions, or specifications fail. Use this skill when debugging failed proofs, understanding why verification fails, creating minimal reproducing examples, analyzing assertion violations, investigating invariant breaks, or diagnosing specification…
runtime-error-explainer
Explains runtime errors and compilation failures with actionable debugging guidance. Use when Python or Java code throws runtime exceptions (NullPointerException, TypeError, AttributeError, etc.), compilation errors (syntax errors, type mismatches, import failures), or dependency issues. Analyzes error messages, stack…
abstract-trace-summarizer
Performs abstract interpretation to produce summarized execution traces and high-level program behavior representations. Highlights key control flow paths, variable relationships, loop invariants, function summaries, and potential runtime states using abstract domains (intervals, signs, nullness, etc.). Use when…
code-optimizer
Analyzes and optimizes code for better performance, memory usage, and efficiency. Use when code is slow, memory-intensive, or inefficient. Supports Python and Java optimization including execution speed improvements, memory reduction, database query optimization, and I/O efficiency. Provides before/after examples with…