trace

A record of an agent's actions, decisions, timing, and results while it works on a task.

In plain words
What is it for?
Use it to debug orchestration, inspect decision flow, troubleshoot failures, and measure performance at summary, standard, or detailed levels.
Why use it?
It makes agent behaviour easier to understand when a workflow fails, behaves unexpectedly, or runs slowly.

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/junghwayang/oh-my-codex/trace
Any agent
npx skills add junghwaYang/oh-my-codex --skill trace
Clone the repo
git clone --depth 1 https://github.com/junghwaYang/oh-my-codex

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 884 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 $0.00000 $0.00884
Opus 5 $0.00000 $0.00442
Sonnet 5 $0.00000 $0.00177
Haiku 4.5 $0.00000 $0.00088

Measured 2d ago against content hash ae43693e55f9, 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 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.

.codex/skills/trace/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trace Skill

Execution tracing and debugging for orchestration.

When to Use

  • Debugging agent behavior
  • Understanding decision flow
  • Performance profiling
  • Troubleshooting failures

Trace Levels

Level 1: Summary

[15:30:01] Task started: "Build auth system"
[15:30:05] Plan created: 5 subtasks
[15:35:22] All tasks completed
[15:35:23] Session ended: SUCCESS

Level 2: Standard

[15:30:01] PM: Received task "Build auth system"
[15:30:02] PM: Analyzing requirements...
[15:30:05] PM: Created plan with 5 subtasks
[15:30:06] PM: Delegating to Frontend (subtask 1)
[15:30:06] PM: Delegating to Backend (subtask 2)
[15:31:15] Frontend: Completed "Login form"
[15:32:30] Backend: Completed "Auth API"
...

Level 3: Verbose

[15:30:01.234] PM: Received task
  Input: "Build auth system"
  Context: {session: "abc123", mode: "autopilot"}
  
[15:30:02.456] PM: Calling model
  Model: o3
  Tokens: 1,234 (prompt) + 567 (completion)
  Latency: 2.3s
  
[15:30:05.789] PM: Plan generated
  Plan: {
    tasks: [
      {id: 1, description: "Login form", agent: "frontend"},
      ...
    ]
  }

Trace Output

Console

Real-time output to terminal

File

Written to ~/.codex/traces/{session_id}.log

Structured (JSON)

{
  "timestamp": "2026-02-13T15:30:01.234Z",
  "agent": "pm",
  "event": "task_received",
  "data": {
    "task": "Build auth system",
    "mode": "autopilot"
  }
}

Trace Events

Event Description
task_received Agent received a task
task_delegated Task assigned to another agent
task_started Agent began work
task_completed Agent finished work
task_failed Agent encountered error
model_call LLM API called
tool_used Tool executed
decision Agent made decision

Analysis

Timeline View

PM          ████░░░░░░░░░░░░░░░░░░░░░░
Frontend    ░░░░████████░░░░░░░░░░░░░░
Backend     ░░░░████████████░░░░░░░░░░
Tester      ░░░░░░░░░░░░░░░░████░░░░░░
            0s  5s  10s 15s 20s 25s 30s

Read the full file on GitHub · 132 lines

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 · 132 lines · 0 tokens per session scan A ae43693e55f9

Subscribe to this mod's changes

trace is a skill published in the GitHub repository junghwaYang/oh-my-codex (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 884 tokens. 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens