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/ktkid/x-dev-pipeline/x-fixnpx skills add KtKID/x-dev-pipeline --skill x-fixgit clone --depth 1 https://github.com/KtKID/x-dev-pipelineWrote 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/ktkid/x-dev-pipeline/x-fix)<a href="https://agentmods.dev/skills/ktkid/x-dev-pipeline/x-fix"><img src="https://agentmods.dev/badge/skills/ktkid/x-dev-pipeline/x-fix.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 5.1 | $0.00181 | $0.01967 |
| Opus 5 | $0.00090 | $0.00983 |
| Sonnet 5 | $0.00036 | $0.00393 |
| Haiku 4.5 | $0.00018 | $0.00197 |
Grade A, and why
x-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 6d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
x-fix 修复执行框架
模式判断（第一步必做）
按输入来源选择模式：
- 有 x-verify / x-qa-gate fail 报告（包含
verify-report-*.md，或 RC/R1/R2/R3 review 问题映射与issue-<n>）→ 加载references/qa-gate-fix-mode.md - 有 x-cr CR 报告（用户在指令中提供了
reports/cr/cr-report-*.md路径，或提到"按 CR 报告"、"CR 问题"）→ 加载references/cr-fix-mode.md - 用户直接描述 bug 或问题现象 → 加载
references/bug-fix-mode.md
修复报告模板（模式 1 产出物）
所有修复完成后，必须在 reports/fix/ 产出报告或修补单：
reports/fix/fix-report-YYYYMMDD-HHmmss.md：CR 驱动、跨文件、需要完整闭环的修复reports/fix/fix-note-YYYYMMDD-HHmmss.md：人工发现的单点小修补
# [Bug 名称] 修复报告
> 修复时间：YYYY-MM-DD HH:mm
> 修复人：Claude (x-fix)
## Bug 描述
[用户描述的问题现象]
## 根因分析
[定位到的根本原因]
## 修复方案
[具体如何修复]
## 修改文件
| 文件 | 修改内容 |
|------|----------|
| `src/xxx.ts` | [描述改动] |
## 测试验证
[验证方式：无/本地测试/用例说明]
报告路径统一写入 reports/fix/，文件类型由修复范围决定。
如果是单点人工修补，优先写 fix-note-YYYYMMDD-HHmmss.md；如果是完整 bug 修复或 CR 驱动修复，优先写 fix-report-YYYYMMDD-HHmmss.md。
CR 报告修复（模式 2）输出
执行完 references/cr-fix-mode.md 的流程后，在对话中输出：
✅ 修复完成
- 已修复：X 条
- 无需修复（误报）：X 条
- 已跳过（P3）：X 条
- 修改文件：X 个（列出文件路径）
输出末尾追加：📄 报告已更新：<完整文件路径>
x-cr / x-qa-gate 边界
- x-cr 报告来自手动软件正确性调查，x-fix 按
references/cr-fix-mode.md修复并回写同一份reports/cr/cr-report-*.md。 - x-verify / x-qa-gate 报告来自自动门禁，x-fix 按
references/qa-gate-fix-mode.md一次批量修复本轮 issue 清单，修完交回触发 gate 做增量复审。 - 当前自动门禁链路是
x-dev -> x-verify -> x-qa-gate -> x-fix。 - README
risk: Q0/Q1在 verify 通过后交付；Q2 进入 RC；Q3 进入 R1→R2→R3。 - 手动正确性调查和 CR 复查由用户明确触发 x-cr。
单次修复的边界约束
- 不跨任务：一次 x-fix 调用只处理当前任务的问题，不得修复其他任务范围内的代码
- 不扩大修改：不得"顺便"重构其他代码、改无关风格、补其他任务的遗漏
- 不吞错：修复中遇到文件不存在、行号完全错位等异常 → 在报告中标记
➖无需修复并继续下一条，不允许静默跳过
Gate 回流：批量修 + 增量复审
x-fix 同时接收 bug 报告、cr-report，以及 x-verify / x-qa-gate reviewer（RC/R1/R2/R3）的 fail 触发。执行结构是一次批量修完本轮全部 issue，交回 gate 做增量复审；增量复审与熔断逻辑见 skills/x-qa-gate/SKILL.md「回流」。
批量修协议
- 输入 = 主 agent 提供的完整 issue 问题映射（每条含
issue-<n>、task、severity、loc、msg 和 reviewer 证据）或 verify 报告的全部 fail 命令。 - 按严重度处置：P0 全修；P1 逐条修复或写豁免理由；P2 只登记不修。
- 每修一个 P0 必须留一条可复跑反例（单元/集成测试断言或 verify 脚本步骤），防止回归。
- 修完自跑受影响验证（相关测试 + dev-report 命令中受影响条目），不许带着红灯交回复审。
- 产出逐条处置表（见下），控制权交回主 agent 触发增量复审。
- 修复过程保持 dev-checklist 状态单元格与 issue ledger 原样；状态升钩由主 agent 在复审通过后完成。
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.
- 6d ago First seen · 146 lines · 181 tokens per session scan A 346d470cff25
x-fix is a skill published in the GitHub repository KtKID/x-dev-pipeline (12 stars, last pushed 1mo ago), licensed MIT. It adds 181 tokens to every session and 1,967 once invoked, about $0.0009 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
review-agent-harness
Review whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, verification, delivery, and learning. Use when asked to assess agent readiness, repeated agent failures, Rules/Skills/Hooks/Memory effectiveness, missing validation or recovery loops, or whether a…
codex-log-guard
Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default. Use when a user mentions logs2.sqlite, logs2.sqlite-wal, blockloginserts, SSD/TBW wear, or explicitly asks to protect, clean up, verify, or restore Codex diagnostic logging.
codex-agent
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.
project-health-auditor
Comprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking dependencies, or assessing project structure.
structured-logging-lite
Design, audit, or implement application structured logging architecture from repository evidence. Use when a user asks whether or where to add logs, how to choose or migrate a logger, how to standardize events/fields/levels/redaction, how to add HTTP access or panic logs, or why production logs cannot answer an…
css-debug
Use this skill to diagnose CSS and frontend layout issues such as positioning, overflow clipping, Tailwind class conflicts, z-index stacking, and React rendering visibility problems.