# Trace

Use when encountering bugs, test failures, runtime errors, broken builds, or "this...

- Repository: https://github.com/jeremylongshore/tons-of-skills-marketplace (2890 stars)
- Category: Testing
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add jeremylongshore/tons-of-skills-marketplace --skill trace -g -a claude-code -y`
Codex: `npx skills add jeremylongshore/tons-of-skills-marketplace --skill trace -g -a codex -y`
Cursor: `npx skills add jeremylongshore/tons-of-skills-marketplace --skill trace -g -a cursor -y`
Gemini CLI: `npx skills add jeremylongshore/tons-of-skills-marketplace --skill trace -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add jeremylongshore/tons-of-skills-marketplace`

## Description

Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch, never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why is this failing", "this test is broken".

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Trace

Root cause, not symptom. Never patch over a bug without understanding why it happened.

All agents inherit the session model. Reviewers and Debuggers bold-labeled; Workers plain.

## Per-Step Agent Map (DOCTRINE rule 12)

Every substantive step dispatches at least one Agent. Atomic steps (per DOCTRINE 12.2.8) are a single Worker → Reviewer pair with no independent angles to fan out.

| Step | Status | Workers | Reviewers | Notes |
|---|---|---|---|---|
| 1, Reproduce | Atomic (12.2.8) | Searcher | **Reviewer** | Runs if repro missing; single Worker→Reviewer pair |
| 2, Gather evidence | Atomic (12.2.8) | `searcher` specialist × 3 | **Reviewer** | 3 parallel Searchers → single Reviewer; one Worker-group→Reviewer pair |
| 3, Hypothesize | Atomic (12.2.8) | **`debugger` specialist** | **Reviewer** | Single Debugger (5 Whys + ranked hypotheses); may fan out Step 4 across hypotheses (rule 18) |
| 4, Verify | 2 sub-phases | Implementer × N | **Debugger** · **Reviewer** | 4a: parallel Implementers → Reviewer; 4b: Debugger re-evaluation → Reviewer |
| 5, Fix at root | Atomic (12.2.8) | Implementer × N | **Reviewer** | N Implementers (one per file) → Reviewer; single Worker-group→Reviewer pair |
| 6, Regression test | Atomic (12.2.8) | Writer | **Reviewer** | Single Writer → single Reviewer; no parallel angle |
| 7, Memory + final | Atomic (12.2.8) | Writer | **Reviewer** | Single Writer → integration Reviewer; no parallel angle |

## Step 1, Reproduce

Atomic, single Searcher → Reviewer pair (DOCTRINE 12.2.8). No parallel angles: artifact retrieval is a single-scope search when the symptom is unknown.

If the user supplied a stack trace, test name, or log snippet, skip the Worker dispatch entirely (Step 1 is then trivially fulfilled by existing input; proceed to Step 2).

Otherwise dispatch `Searcher, locating bug reproduction in recent changes/tests`.

The rest: https://github.com/jeremylongshore/tons-of-skills-marketplace/blob/HEAD/plugins/ai-agency/hyperflow/skills/trace/SKILL.md