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 seed-forge/harness-ai-kit --skill devlab-tech-debt-opsgit clone --depth 1 https://github.com/seed-forge/harness-ai-kitWrote 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/seed-forge/harness-ai-kit/devlab-tech-debt-ops)<a href="https://agentmods.dev/skills/seed-forge/harness-ai-kit/devlab-tech-debt-ops"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/devlab-tech-debt-ops/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/seed-forge/harness-ai-kit/devlab-tech-debt-ops"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/devlab-tech-debt-ops.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00105 | $0.02012 |
| Opus 5.5 | $0.00042 | $0.00805 |
| Sonnet 5.5 | $0.00021 | $0.00402 |
| Haiku 4.5 | $0.00011 | $0.00201 |
Grade A, and why
devlab-tech-debt-ops 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
devlab-tech-debt-ops
用途
技术债全生命周期运维：从审计发现、分级建议，到确认后的安全重构（微观/宏观），再到回归验证。不只是"怎么拆"，还回答"该不该拆、先拆哪里、拆到什么程度"。
边界：只处理技术债（可维护性/结构/复杂度），不改变业务语义；业务需求变更走外层 SDD 框架（trellis/comet/mattpocock，见 devlab-harness-ops Step 7）。
适用场景
- 审计场景：项目需要盘点技术债分布、严重度、优先级，产出审计报告供决策。
- 微观重构：单文件/单类内部整理（提取方法、消除重复、简化条件分支）。
- 宏观重构：跨模块/架构级拆分（god-class 拆解、引擎解耦、分层重构）。
- 引用清零：大范围重命名/搬迁/删除旧实现，需安全地"引用清零"。
不适用场景
- 加新功能（走外层 SDD 框架，见
devlab-harness-opsStep 7）。 - 业务逻辑本身要变（那是业务债，不是技术债）。
- 一次性小改动（直接改即可，不必起编排）。
输入
- 目标代码单元（类/模块/引擎/整个项目）与痛点描述。
- 现有测试覆盖情况。
- 约束：是否允许破坏性变更、时间盒、微观/宏观/混合。
输出
- 审计报告（债务分布图 + P0-P3 分级 + 建议优先序 + ROI 评估）。
- 现状固化文档（架构/流程/组件职责/问题分层）。
- 拆分设计（目标模块划分 + 职责边界 + 迁移映射）。
- 分步重构任务清单（小步、每步可回退、可验证）。
- 回归结果（行为不变的证据）。
工作流
Phase 0: 审计（Audit）
[微观] 扫描代码坏味道（长方法/重复/复杂条件/过深嵌套）
[宏观] 扫描架构债（循环依赖/god-class/分层违规/耦合度）+ 深化机会（浅模块/抽象泄漏，见 references/REFERENCE-DEEP-MODULE-DESIGN.md）
-> 产出审计报告：债务清单 + P0-P3 分级 + 建议优先序 + ROI 估算
-> ⛔ Gate G0：审计报告确认，用户决定处理范围
Phase 1: 现状梳理与固化（不改代码）
[微观] 记录当前方法/类内部结构与职责
[宏观] 梳理目标单元的架构/执行流程/模块间依赖
-> 形成固化 md 作为重构依据
-> ⛔ Gate G1：现状与问题清单确认
Phase 2: 建立安全网
[微观] 补齐单元测试/行为快照测试
[宏观] 补齐集成测试/端到端表征测试（characterization tests）
-> 无测试的高风险路径先补测试再动
-> ⛔ Gate G2：安全网是否覆盖将要改动的行为
Phase 3: 拆分设计
[微观] 提取方法/变量/参数对象/Guard Clause 设计
[宏观] 目标模块划分 + 职责边界 + 从旧到新的迁移映射
-> 按需选用设计模式（见 references/REFERENCE-DESIGN-PATTERNS.md），切勿过度设计
-> ⛔ Gate G3：拆分方案确认
Phase 4: 小步重构 + 引用清零安全移除
[微观] 逐个提取/重命名/简化 -> 单元测试通过 -> 提交
[宏观] 抽取/搬迁模块 -> 更新调用侧 -> 集成测试通过 -> 提交
-> 删除旧实现前，先把旧引用"清零"（搜索确认零引用）再删
-> 破坏性变更必须同步所有调用侧
Phase 5: 回归验证
[微观] 单元测试全量通过 + 行为快照对比
[宏观] 集成/端到端回归 + 行为对比，证明"行为不变、结构变好"
关键原则
- 行为不变：技术债重构不改可观察行为；用测试锁住行为再动结构。
- 小步可回退：每一步都是一次可独立提交/回滚的最小变更，避免大爆炸式重构。
- 引用清零再删除：删旧代码前先搜索确认零引用（含 tests/tools），清零->删除->跑测试三步走。
- 按需用模式，不过度：设计模式是手段不是目的；具体选型让 AI 结合场景给选项。
- 审计先行：不确定该不该拆时，先跑 Phase 0 审计，用数据说话。
- 深模块优先：拆分不只“把大的拆小”，更要“把浅的做深”——大量行为藏在小接口之后、落在可测接缝（见 references/REFERENCE-DEEP-MODULE-DESIGN.md）。
reference
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.
- 1mo ago First seen · 123 lines · 105 tokens per session scan A a0a35e8fd916
devlab-tech-debt-ops is a skill published in the GitHub repository seed-forge/harness-ai-kit (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 2,012 once invoked, about $0.0004 per session on Opus 5.5. 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
ast-grep
Searches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.
debugging
Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.
lcx-doctor
Diagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, says LazyCodex, lazycodex-ai, omo-codex, or Codex behaves oddly after an install, update, or config change, suspects a stale, drifted, or broken setup, or wants the local install…
lcx-report-bug
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.
watch
Observe actual video and sound over the whole file or named ranges, with timestamped evidence and honest coverage. Use complementary playback, listening and targeted frames; return observations without edits or verdicts.