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 kings0527/agent-skills --skill devtracegit clone --depth 1 https://github.com/kings0527/agent-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/kings0527/agent-skills/devtrace)<a href="https://agentmods.dev/skills/kings0527/agent-skills/devtrace"><img src="https://agentmods.dev/badge/skills/kings0527/agent-skills/devtrace/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kings0527/agent-skills/devtrace"><img src="https://agentmods.dev/badge/skills/kings0527/agent-skills/devtrace.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.03498 |
| Opus 5.5 | $0.00000 | $0.01399 |
| Sonnet 5.5 | $0.00000 | $0.00700 |
| Haiku 4.5 | $0.00000 | $0.00350 |
Grade A, and why
DevTrace 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 1mo 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevTrace 技术决策五算子（Agent Skill）
skill_name: DevTrace_Technical_Decision_Framework
version: 1.1
定位: 给 Agent 增加"综合开发/架构判断能力"的决策自检框架（偏工程落地，不强制量化）
适用场景: 架构决策、技术选型、代码审查、重构方案评估、技术债务评估、项目风险预判
触发条件（自动启用）: 当用户讨论"要不要做/怎么做/选哪个/改动影响/风险如何/能否上线/是否重构/是否拆分/是否引入依赖"等技术决策时启用
核心约束: 不凭空臆测。信息不足时先追问；若必须回答，用"条件化结论 + 前置条件"表达。
0. Skill 行为准则（Agent Operating Rules）
- 先画拓扑再谈方案：任何建议先说明影响范围、关键路径、故障域。
- 先守边界再谈优化：先检查抽象边界/契约是否被破坏，再谈实现细节。
- 默认可逆：优先推荐可灰度、可回滚、可旁路、可降级的方案。
- 默认先问缺口：如果缺少关键上下文，先问最小问题集；否则输出"需要补充的信息"。
- 红线触发就否决：任一算子出现"高风险且无可行缓解"必须输出"不建议实施"或"需先解决前置条件"。
1️⃣ 拓扑（Topology）——结构算子
核心定义
这不是孤立的代码，是依赖网络中的一个节点——改动它，依赖图会传导；依赖图变了，它会失效。
需要关注的工程问题
- 调用链深度：影响直接下游/间接下游/是否可能级联雪崩？
- 数据流向：是数据源（SSOT）还是数据汇（Consumer）？改动会污染、断裂、还是扩散？
- 故障域边界：故障可隔离在进程/容器/服务/集群？是否会跨边界扩散？
- 循环依赖/隐性耦合：是否形成 A→B→C→A，或"共享DB/共享缓存/共享配置"的隐性环？
默认追问（信息不足时至少问其中3个）
- 变更发生在哪：服务/模块/仓库/接口/表/队列/定时任务？
- 关键入口是什么（API/消息/批任务）？关键出口是什么（DB/外部服务）？
- 同步调用还是异步事件？超时/重试/熔断策略是什么？
- 故障时如何降级：返回兜底/跳过步骤/排队/人工介入？
- 是否属于关键路径（支付/登录/下单/结算等）？
必出产物（输出中必须出现）
- 拓扑图（文字描述）：节点+边+关键路径+故障传播点（见输出模板）
2️⃣ 抽象（Abstraction）——分层算子
核心定义
你写的代码是接口还是实现？稳定层在哪，易变层在哪？——混淆层级是技术债务的主要源头。
需要关注的工程问题
- Leaky Abstraction：抽象是否泄漏实现细节（ORM/框架/云厂商细节渗透到业务层）？
- 依赖倒置：高层策略是否依赖低层细节？能否依赖接口/契约？
- 正交性：变更是横向跨模块（容易扩散）还是纵向穿层（容易破坏边界）？
- API 契约：对外暴露的是稳定承诺还是临时实现？是否有版本策略？
默认追问
- 对外契约是什么：API/事件schema/表结构/配置字段？
- 是否允许破坏性变更？有没有版本兼容策略（v1/v2、双写、双读）？
- 上层代码是否出现基础设施细节（SQL方言、SDK对象、云服务特性）？
- 是否出现"上帝类/上帝函数"跨层协调所有事情？
典型反模式提示（用于代码审查/方案评估）
- 业务层直接拼SQL、直接依赖云SDK类型、直接跨服务读写别人的数据库
- 为了"快"把基础设施对象一路透传到Controller/Domain
- 以"内部接口"为名实际对外扩散，后续无法演进
3️⃣ 熵增（Entropy）——腐烂算子
核心定义
代码天然在腐烂——你要评估的不是"现在能跑"，而是"6个月后维护它的痛苦程度"。
需要关注的工程问题（不强制量化）
- 可维护性半衰期：新成员6个月后能否理解？是否依赖隐式知识？
- Bug Surface：复杂度、影响范围、新颖度叠加后的缺陷暴露面
- 技术债利息：现在省下的时间，将来以排障/返工/上线风险的形式偿还
- Bus Factor：关键知识是否集中在少数人？
默认追问
- 这段改动是否有自动化测试覆盖？（单测/集成/回归）
- 可观测性如何：日志、指标、trace 是否能定位问题？
- 是否存在 TODO/FIXME、临时开关、手工步骤、隐式约定？
- 谁维护/谁值班？关键人是否单点？
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.
- 1mo ago First seen · 216 lines · 0 tokens per session scan A cf101ceb9ec8
DevTrace is a skill published in the GitHub repository kings0527/agent-skills (6 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,498 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 skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…