Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add VoidTechnology/voidtech-claude-plugins/plugin install voidtech-engineeringWrote 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/voidtechnology/voidtech-claude-plugins/debug)<a href="https://agentmods.dev/skills/voidtechnology/voidtech-claude-plugins/debug"><img src="https://agentmods.dev/badge/skills/voidtechnology/voidtech-claude-plugins/debug/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/voidtechnology/voidtech-claude-plugins/debug"><img src="https://agentmods.dev/badge/skills/voidtechnology/voidtech-claude-plugins/debug.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 | $0.00044 | $0.02506 |
| Opus 5.5 | $0.00018 | $0.01002 |
| Sonnet 5.5 | $0.00009 | $0.00501 |
| Haiku 4.5 | $0.00004 | $0.00251 |
Grade A, and why
debug scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
当反馈循环足够快速、稳定且能捕获当前缺陷时,阶段 1 完成。此时应给出**一条已经至少运行过一次的命令**,可以是脚本、测试调用或 curl,并附上调用方式及输出。它必须满足: How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vendored from mattpocock/skills · MIT © 2026 Matt Pocock · upstream 6eeb81b · 已汉化并完成 VoidTech 插件内自包含适配。LICENSE 见 ../_vendor-licenses/mattpocock-LICENSE
诊断缺陷
一套针对疑难缺陷的纪律。只有在有明确理由时才跳过某个阶段。
探查代码库时,读取 CONTEXT.md(若存在),先弄清相关模块、业务词汇和边界,再查看改动区域内的 ADR。
阶段 1 — 构建反馈循环
本阶段的目标是建立一个快速、稳定且针对当前缺陷的通过或失败信号。它必须在缺陷存在时失败,在缺陷修复后通过。二分定位、假设检验和诊断信息都依赖这个信号;没有可靠信号时,继续阅读代码很容易产生无法验证的猜测。
优先投入时间建立这个反馈循环。常规方法无效时,再尝试更小的测试环境、请求重放或差分对比。
构建它的若干途径——大致按此顺序尝试
- 失败的测试,放在任何能触发该缺陷的可测试位置,例如单元测试、集成测试或端到端测试(e2e)。
- Curl / HTTP 脚本,打向一个运行中的开发服务器。
- CLI 调用,提供一份固定测试输入,把 stdout 与已知正确的快照对比。
- 无头浏览器脚本(Playwright / Puppeteer)——驱动 UI,对 DOM/console/network 做断言。
- 重放已捕获的轨迹。 把一个真实的网络请求 / 载荷 / 事件日志存到磁盘;隔离地让它重新走一遍代码路径。
- 一次性测试环境。 启动系统的最小子集(例如只启动一个服务,并 mock 外部依赖),用单次函数调用覆盖缺陷路径。
- 随机输入测试。 如果缺陷表现为“偶尔输出错误”,运行大量随机输入并记录失败样本。
- 二分定位脚本。 如果缺陷出现在两个已知状态(commit、数据集、版本)之间,自动执行“在指定状态启动、检查、重复”,以便使用
git bisect run。 - 版本对比测试。 用同一输入分别运行旧版与新版(或两套配置),然后比较输出。
- HITL bash 脚本。 最后手段。如果必须有人点击,Claude Code 从
${CLAUDE_PLUGIN_ROOT}/skills/debug/scripts/hitl-loop.template.sh读取模板;OMP 从skill://debug/scripts/hitl-loop.template.sh读取同一模板。把内容复制到操作系统临时目录,在副本中填写步骤后运行;不要修改插件安装目录中的模板。捕获的输出回流给你。
正确的反馈循环会显著降低后续定位和验证的成本。
改进反馈循环
建立初始循环后,继续缩短运行时间并提高信号质量:
- 能更快吗?(缓存初始化、跳过无关的 init、收窄测试范围。)
- 能让信号更锐利吗?(断言具体症状,而不是"没崩"。)
- 能更确定吗?(固定时间、给 RNG 播种、隔离文件系统、冻结网络。)
一个耗时 30 秒且结果不稳定的循环难以使用;一个耗时 2 秒且结果确定的循环更适合反复验证。
偶发缺陷
目标不是干净的复现,而是更高的复现率。把触发器循环跑 100 次、并行化、加压、收窄时序窗口、注入 sleep。一个 50% 概率出错的缺陷可调试;1% 则不行——持续提高复现率,直到可调试为止。
当你确实无法构建循环时
停下并明确说明当前限制,列出已经尝试的方法。向用户索取:(a) 能复现问题的环境访问权限,(b) 已捕获的材料(HAR 文件、日志转储、core dump、带时间戳的屏幕录像),或 (c) 在生产环境增加临时诊断日志或指标的许可。没有反馈循环时,不进入假设阶段。
完成判据 — 反馈循环能够捕获缺陷
当反馈循环足够快速、稳定且能捕获当前缺陷时,阶段 1 完成。此时应给出一条已经至少运行过一次的命令,可以是脚本、测试调用或 curl,并附上调用方式及输出。它必须满足:
- 能够捕获缺陷 — 它覆盖真实的缺陷代码路径,并断言用户报告的确切症状;缺陷存在时失败,修复后通过。仅验证“运行不报错”不够。
- 确定 — 每次运行结论相同(不稳定缺陷:按上文,固定一个高复现率)。
- 快 — 以秒计,而非以分钟计。
- 可由 agent 运行 — 你能无人值守地跑它;只有通过插件随附的 HITL 模板副本才允许人介入循环。
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 · 136 lines · 44 tokens per session scan A 27570103c1b1
debug is a skill published in the GitHub repository VoidTechnology/voidtech-claude-plugins (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 44 tokens to every session and 2,506 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.