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/xcodethink/open-claude-code-skills/14npx skills add xcodethink/open-claude-code-skills --skill 14git clone --depth 1 https://github.com/xcodethink/open-claude-code-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/xcodethink/open-claude-code-skills/14)<a href="https://agentmods.dev/skills/xcodethink/open-claude-code-skills/14"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/14.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 | $0.00249 | $0.00677 |
| Opus 5 | $0.00125 | $0.00338 |
| Sonnet 5 | $0.00050 | $0.00135 |
| Haiku 4.5 | $0.00025 | $0.00068 |
Grade A, and why
14-问题修复标准流程 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.
What it actually says
问题修复标准流程
核心原则：先分析再改、改一个验一个、用户确认后才动手。
历史教训：跳过分析直接改代码 → 改出新 bug。 这个技能强制 11 步流程，每步有交付物，防止跳步。
触发场景
| 场景 | 说明 |
|---|---|
| 审计/体检发现问题 | 按 13-系统体检和审计 发现的问题清单执行 |
| 用户报 bug | 从用户描述开始，走完整流程 |
| 生产事故 | 紧急修复也必须走调研→方案→验证 |
| 代码审查发现问题 | 不是看到就改，先评估影响面 |
| 性能/安全问题 | 同上 |
文档
| 文档 | 内容 |
|---|---|
问题修复标准流程.md |
完整 11 步流程、每步交付物、禁止事项、防跳步机制 |
反馈回路优先.md（借自 mattpocock/skills，MIT） |
硬 bug 在假设根因前先造 red-capable 反馈回路；Phase 1-6（复现难/反复修不好时读，是「问题分析铁律」追数据流的抓手） |
与其他技能的关系
| 技能 | 关系 |
|---|---|
13-系统体检和审计 |
审计发现问题后，进入本流程修复 |
01-通用要求 |
本流程中的代码修改必须遵循通用开发规则 |
07-测试规范 |
第 8/9 步的验证和回归遵循测试规范 |
06-部署和运维 |
第 10 步的部署遵循部署规范 |
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.
- 4d ago First seen · 38 lines · 249 tokens per session scan A d74b7bb57d87
14-问题修复标准流程 is a skill published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 29d ago), licensed MIT. It adds 249 tokens to every session and 677 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
android-finance-spec
Use when generating, reviewing, or refactoring Android Kotlin code for financial apps that require BigDecimal/String precision, RTL/i18n safety, Kotlin style discipline, and "do not reinvent existing project patterns" constraints.
elite-engineer
The operating system for elite software engineering in TypeScript, React, and Next.js. Enforces the cognitive models, architecture laws, type-level patterns, component design, visual standards, and performance mandates that separate exceptional software from the ordinary — grounded in named sources (Torvalds…
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
implementation-readiness
Verify BRD-lite, PRD, SRS/FRS, UX, and test prerequisites before implementation starts.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.