nexus-debugging

A troubleshooting guide for finding the root cause of failures in software projects, including code, tests, frameworks, and delivery pipelines.

In plain words
What is it for?
Use it to diagnose CI/CD failures, application errors, regressions, and framework problems, then verify the narrowest fix.
Why use it?
It structures the investigation around exact errors, recent changes, environment details, and reproduction steps before suggesting a fix.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/aayushostwal/nexus/debugging
Any agent
npx skills add aayushostwal/nexus --skill debugging
Clone the repo
git clone --depth 1 https://github.com/aayushostwal/nexus

Made for: Claude Code, Codex.

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,064 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00068 $0.01064
Opus 5 $0.00034 $0.00532
Sonnet 5 $0.00014 $0.00213
Haiku 4.5 $0.00007 $0.00106

Measured 2d ago against content hash 33fbb7c5b386, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nexus-debugging 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 2d 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.

skills/debugging/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nexus Debugging

Route to the correct sub-guide and follow it end-to-end.


Compatibility

  • Sub-guides: skills/debugging/ci-cd.md, skills/debugging/codebase.md, skills/debugging/frameworks.md
  • Shared rules and output formats: skills/debugging/common.md

Workflow

Step 1 — Classify the Failure

Pick exactly one track:

Track Failure origin Sub-guide
CI/CD GitHub Actions, Jenkins, CircleCI, or deployment pipeline log ci-cd.md
Codebase Failing test, runtime exception, or regression in application code codebase.md
Framework Django, FastAPI, Bazel, or other tooling misbehavior frameworks.md

If unsure: ask "Is the failure in pipeline logs, app code, or a framework?"

Step 2 — Gather Error Context

Before reading the sub-guide, collect:

  1. Full error message or stack trace — copy exact text, do not paraphrase
  2. What changed recently: last commit, dependency update, config change, environment change
  3. Environment details: local vs CI, OS, Python/Node/runtime version
  4. Steps to reproduce (minimum reproducible case if possible)

Step 3 — Read Sub-Guide & Execute

Read the appropriate sub-guide. Follow its steps in order. Do not skip steps. Read common.md for shared output format and checklists.

Step 4 — Search for Tool-Specific Errors

If the error is framework-specific or tool-specific:

  1. Search: "<exact error message>" <tool-name> <version> — use exact error text
  2. Check the official tool changelog for breaking changes in the version in use
  3. Check GitHub Issues for the tool repo filtered by the error keyword

Step 5 — Apply Fix & Verify

  1. Apply the narrowest fix that addresses the root cause — do not clean up unrelated code
  2. Run the exact verification command that confirms the fix (re-run the failing test or job)
  3. State what would prevent this from recurring

Output Format

## Debug Report
**Track:** [CI/CD | Codebase | Framework]
**Root Cause:** [one sentence — specific, not "something went wrong"]
**Fix:** [exact command or minimal code diff]
**Verification:** [command to run to confirm fix]
**Prevention:** [what change stops this from recurring]

Read the full file on GitHub · 111 lines

Files

What ships with it

6 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.

Changes

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.

  1. 2d ago First seen · 111 lines · 68 tokens per session scan A 33fbb7c5b386

Subscribe to this mod's changes

nexus-debugging is a skill published in the GitHub repository aayushostwal/nexus (18 stars, last pushed 23d ago), licensed MIT. It adds 68 tokens to every session and 1,064 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

fireworks-tech-graph

Create technical diagrams such as software architecture, data flow, flowcharts, sequence diagrams, C4 reviews, cloud deployments, event streams, observability investigations, agent/memory systems, UML, ER, network topology, timelines, and technical concept maps, then export SVG, PNG, focused semantic SVG-to-GIF…

yizhiyanhua-ai/fireworks-tech-graph · 128 tokens

cangjie-skill

Distill a book, long-video transcript, podcast, course, or interview into a coherent set of executable skills. Use when the user asks to "拆书" / "蒸馏一本书" / "把 XX 书做成 skill" / "把这个视频/播客/课程蒸馏成 skill" / "turn a book or video into skills" — i.e. wants the frameworks, principles, and methodologies in long-form content…

kangarooking/cangjie-skill · 143 tokens

wealth-structure

当用户问「怎么赚钱/如何致富/该不该要期权/如何判断一个生意的结构」时调用。 核心理念: 财富=睡觉时仍在赚钱的资产; 靠「责任(押上声誉)→产权(股权/知识产权)→杠杆(无需许可的代码媒体)→避免出局」构建, 无法靠出租时间致富。 不适用于: 具体投资标的分析、理财产品的选股建议。 Triggers: 致富/赚钱/股权/期权/杠杆/被动收入/ownership/leverage/equity.

kangarooking/cangjie-skill · 141 tokens

acceptance

当用户困在无法改变的处境(坏关系/讨厌的同事/不如意的事)里反复内耗、问「该忍还是该走」时调用。 核心理念: 面对任何情境只有三选项——改变它/接受它/离开它; 三者都不做是痛苦之源; 接受=快速适应, 用「积极方面是什么」重释训练。 不适用于: 可以改变的处境(应先改变), 以及涉及违法/人身安全的场景。 Triggers: 接受/忍/内耗/放不下/该走该留/acceptance/let go/change-accept-leave.

kangarooking/cangjie-skill · 153 tokens

decision-heuristics

当用户在重大选择上纠结(换工作/买房/搬城/合伙/结婚)、列了利弊表还是拿不定主意时调用。 核心理念: 无法决定就答否; 三个重大决定(住哪/和谁/做什么)值得花一两年; 两个均等选择选短期更痛苦的路。 不适用于: 日常琐碎选择(晚饭吃什么)、信息查询。 Triggers: 纠结/拿不定主意/要不要/该不该/利弊/decision/hesitate/should I.

kangarooking/cangjie-skill · 136 tokens

screen-detox

当用户刷手机/短视频/社交媒体上瘾、感觉空虚、想戒断多巴胺零食时调用。 核心理念: 所有屏幕活动与更少幸福相关(作者断言无例外); 屏幕=用长期后果换短期快感的多巴胺零食; 用习惯替换五步戒断。 不适用于: 工作需要屏幕的职业场景(区分工作屏幕与消费屏幕)。 Triggers: 刷手机/上瘾/短视频/社交媒体/多巴胺/戒断/屏幕时间/screen time/dopamine/addiction.

kangarooking/cangjie-skill · 148 tokens