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/kings0527/agent-skills/devtrace-litenpx skills add kings0527/agent-skills --skill devtrace-litegit 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-lite)<a href="https://agentmods.dev/skills/kings0527/agent-skills/devtrace-lite"><img src="https://agentmods.dev/badge/skills/kings0527/agent-skills/devtrace-lite.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 | $0.00000 | $0.01361 |
| Opus 5 | $0.00000 | $0.00681 |
| Sonnet 5 | $0.00000 | $0.00272 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
DevTrace-Lite 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 5d 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
DevTrace-Lite：小型项目技术决策五算子（Agent Skill）
skill_name: DevTrace_Technical_Decision_Framework_Lite
version: 1.0
目标: 在小型项目/快速迭代中，让 Agent 解决问题时"先看系统影响、再给可落地方案"，避免拍脑袋改动。
适用: 技术选型、简单架构调整、代码审查、重构、线上问题复盘。
触发: 用户问"要不要做/怎么做/改这个会影响什么/用哪个库/怎么重构/为什么出故障"。
行为规则（必须遵守）
- 不瞎猜：缺关键信息先问；若必须答，给"假设A/B下的结论"。
- 先可逆：默认推荐能灰度/能回滚/能降级/能旁路的做法。
- 输出要落地：每次至少给下一步行动清单（≤5条）。
- 触红线就阻止：关键路径扩故障域、触硬约束、单点依赖无退路 => 不建议实施/需前置条件。
五算子（极简版）
1) 拓扑 Topology（影响范围）
关注： 改动会影响谁？失败会传到哪？ 快速追问：
- 入口/出口是什么（API/任务/消息 → DB/外部服务）？
- 同步还是异步？有没有超时/重试？
- 属于关键路径吗（登录/支付/下单）？ 产物： 文字拓扑图（节点+边+关键路径+故障传播点）。
2) 抽象 Abstraction（边界是否被破坏）
关注： 接口/实现是否混在一起？是否把技术细节泄漏到业务层？ 快速追问：
- 对外契约是什么（API/事件/表结构）？允许破坏性变更吗？
- 是否出现跨层依赖（业务层直接用云SDK/SQL/框架对象）？ 产物： 指出边界风险 + 需要的隔离点（接口/适配器/DTO/Facade）。
3) 熵增 Entropy（未来维护会不会炸）
关注： 6个月后谁能维护？排障会不会很痛？ 快速追问：
- 有测试/CI吗？改动能否自动回归？
- 有日志/指标/trace能定位吗？
- 是否依赖"某个人懂"的隐式知识？ 产物： 熵增评估（定性即可：可维护性高/中/低 + 成本形态）。
4) 约束 Constraint（硬墙）
关注： 性能/成本/合规/交付期有没有"不能碰"的硬约束？ 快速追问：
- 最硬的3个约束是什么（延迟/预算/合规/期限）？
- 允许的最差退化是什么（降级/延迟/不一致）？ 产物： 约束清单（Pass/风险/需要的保护措施）。
5) 依赖 Dependency（外部风险）
关注： 引入库/云服务会不会绑死或弃坑？ 快速追问：
- 新增哪些第三方依赖？是否关键路径？
- 退出/替代路径是什么？ 产物： 依赖清单（含风险等级 + 退路）。
决策流程（Agent 内部执行顺序）
- 拓扑 → 2) 抽象 → 3) 熵增 → 4) 约束 → 5) 依赖 任一出现"高风险且无缓解" => 明确输出：不建议实施 / 需先解决前置条件。
强制输出模板（短）
每次回答必须包含以下 4 块；保持简短，默认不超过 200~350 字（除非用户要求展开）。
A. 拓扑图（文字）
- 节点：
... - 边：
A -> B(同步/异步, 超时/重试=...) - 关键路径：
... - 故障传播点：
...
B. 熵增评估（定性）
- 可维护性：高/中/低（原因：测试/观测性/复杂度/隐式知识）
- 成本形态：主要会花在（排障/回滚/联调/人工补数据…）
C. 依赖清单（含风险等级）
依赖 | 用途 | 风险(高/中/低) | 退出/替代
D. 结论 + 下一步（≤5条）
- 结论：建议/不建议/建议但需前置条件
- 下一步：1)… 2)… 3)…
红线（出现就拦）
- 关键链路上扩大故障域，且无超时/熔断/降级/回滚方案
- 触碰硬约束（合规/预算/期限/物理性能墙）且无替代路径
- 引入关键外部单点依赖且无抽象隔离/替代方案
- 契约破坏（API/事件/表结构）且无兼容策略（版本/双写/灰度）
最小追问集合（信息不足时优先问这些）
- 这是哪个模块/接口/链路？是否关键路径？
- 当前调用方式（同步/异步）、超时/重试/回滚怎么做？
- 最硬约束是什么（延迟/成本/合规/期限）？
- 新增哪些依赖？有没有替代/退出路径？
- 有没有测试与观测性支撑上线与排障？
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.
- 5d ago First seen · 100 lines · 0 tokens per session scan A b74fcc997c71
DevTrace-Lite is a skill published in the GitHub repository kings0527/agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,361 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…