trace

Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for /fix handoff.

272 stars

Best use case

trace is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for /fix handoff.

Teams using trace should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/trace/SKILL.md --create-dirs "https://raw.githubusercontent.com/automagik-dev/genie/main/skills/trace/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/trace/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How trace Compares

Feature / AgenttraceStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for /fix handoff.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# /trace — Investigation and Root Cause Analysis

Investigate unknown failures. Dispatch a trace subagent to reproduce, trace, and isolate root cause — then hand the report to `/fix`.

## When to Use
- A failure exists but the cause is unknown
- Stack traces or error messages don't point to an obvious defect
- Multiple files or systems may be involved
- Orchestrator needs a diagnosis before dispatching a fix
- `/review` encounters a failure with unclear root cause and invokes `/trace` for investigation

## Flow
1. **Collect symptoms:** gather error messages, stack traces, logs, and expected vs actual behavior from the wish or reporter.
2. **Dispatch tracer:** the spawned agent IS the tracer — it performs a read-only inline investigation. Send symptoms + relevant context (files, recent changes, environment).
3. **Investigate:** the tracer autonomously reproduces, hypothesizes, traces, and isolates root cause.
4. **Signal findings:** tracer reports findings back to the leader via `genie send '<diagnosis summary>' --to <leader>`.
5. **Receive report:** structured diagnosis with root cause, evidence, recommended correction, and affected scope.
6. **Hand off:** pass the report to `/fix` or escalate to the orchestrator.

## Report Format

```
Root cause: <what's actually broken — file, line, condition>
Evidence: <reproduction steps, traces, proof>
Causal chain: <root cause → intermediate effects → observed symptom>
Recommended correction: <what to change, where, why>
Affected scope: <other files or features impacted>
Confidence: <high / medium / low>
```

## Dispatch

Trace must run in **isolation** — the subagent must not modify any source files.

```bash
# Spawn a tracer subagent (read-only investigation)
genie spawn tracer
```

## Rules
- Never fix during trace — investigation only, always separate from correction.
- Always reproduce before theorizing — if the failure can't be reproduced, the report must say so.
- Evidence required — every root cause claim must include file paths, line numbers, and a causal chain.
- Hand off to `/fix` — trace produces a report, `/fix` applies the correction. Never combine them.
- Read-only tools — trace subagent uses Read, Bash, Glob, Grep. No Write, no Edit.
- If root cause spans multiple systems, report each separately with confidence levels.

Related Skills

work

272
from automagik-dev/genie

Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.

wish

272
from automagik-dev/genie

Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for /work.

review

272
from automagik-dev/genie

Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.

report

272
from automagik-dev/genie

Investigate bugs comprehensively — cascade through /trace, capture browser evidence, extract observability data, and auto-create a GitHub issue with all findings.

refine

272
from automagik-dev/genie

Transform a brief or prompt into a structured, production-ready prompt via prompt-optimizer. File or text mode.

learn

272
from automagik-dev/genie

Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.

genie

272
from automagik-dev/genie

Transform any Claude Code session into an Automagik Genie orchestrator — guide users through brainstorm, wish, team, and PR lifecycle.

fix

272
from automagik-dev/genie

Dispatch fix subagent for FIX-FIRST gaps from /review, re-review, and escalate after 2 failed loops.

dream

272
from automagik-dev/genie

Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.

docs

272
from automagik-dev/genie

Dispatch docs subagent to audit, generate, and validate documentation against the codebase.

council

272
from automagik-dev/genie

Brainstorm and critique with 10 specialist viewpoints. Use for architecture, plan reviews, or tradeoffs.

brainstorm

272
from automagik-dev/genie

Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for /wish.