trace

A trace skill for investigating failures whose causes are unclear. It reproduces the problem, follows its path through the relevant code or systems, and reports the root cause without changing anything.

In plain words
What is it for?
Use it to investigate complex failures and hand the findings to a separate fix step.
Why use it?
It separates diagnosis from implementation when logs or errors do not clearly identify the defect.

Skill for Claude CodeCodex

Part of the genie plugin — 22 skills, 11 commands, 7 agents, 1 hook shipped together

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/automagik-dev/genie/trace
Any agent
npx skills add automagik-dev/genie --skill trace
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/genie

Made for: Claude Code, Codex.

Or install genie, the plugin that ships this one along with the rest of its 22 skills, 11 commands, 7 agents, 1 hook.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 795 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 $0.00025 $0.00795
Opus 5 $0.00013 $0.00398
Sonnet 5 $0.00005 $0.00159
Haiku 4.5 $0.00003 $0.00080

Measured 3d ago against content hash d1e32a5198d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trace 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 3d 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.

plugins/genie/skills/trace/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

trace — Investigation and Root Cause Analysis

Runtime syntax: invoke the plugin copy through the active runtime's owner-qualified skill selector; use a bare selector only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active runtime.

Investigate unknown failures: dispatch a trace subagent to reproduce, trace, and isolate root cause, then hand the report to fix. The deliverable is findings only — report and stop; never apply fixes, however obvious.

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
  • review hit a failure with unclear root cause and needs a diagnosis before fix

Flow

  1. Collect symptoms: error messages, stack traces, logs, and expected vs actual behavior from the wish or reporter.
  2. Dispatch tracer: native delegation surface → trace subagent, briefed with the symptoms, relevant context (files, recent changes, environment), and read-only stop conditions (see Dispatch).
  3. Investigate: the tracer reproduces, hypothesizes, traces, and isolates root cause autonomously.
  4. Receive report: the tracer's final message is the diagnosis (format below); the native team notifies you on completion — no polling.
  5. 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>

Include file paths and line numbers in every root-cause claim so fix can act without re-investigating. If root cause spans multiple systems, report each separately with its own confidence level.

Read the full file on GitHub · 57 lines

Files

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.

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. 3d ago First seen · 57 lines · 25 tokens per session scan A d1e32a5198d2

Subscribe to this mod's changes

trace is a skill published in the GitHub repository automagik-dev/genie (334 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 795 once invoked, about $0.0001 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

electron-pro

Expert in building cross-platform desktop applications using web technologies (HTML/CSS/JS) with the Electron framework.

fathah/hermes-desktop · 25 tokens

hive.worker-delegation

Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.

aden-hive/hive · 58 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens

develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.

netease-youdao/LobsterAI · 64 tokens

pr-feedback

Fetches PR review feedback and inline comments, categorizes them, and presents options to the user. Use when the user asks to get, read, address, or fix review comments on a pull request.

strands-agents/harness-sdk · 44 tokens

stock-explorer

A Yahoo Finance (yfinance) powered financial analysis tool. Get real-time quotes, generate technical indicator reports (RSI/MACD/Bollinger/VWAP/ATR), summarize fundamentals, and run a one-shot report that outputs a text summary.

netease-youdao/LobsterAI · 55 tokens