trace

A method for explaining why an observed software result happened by comparing competing possible causes and gathering evidence. It ranks explanations and suggests focused checks to distinguish between them.

In plain words
What is it for?
Use it for causal debugging, evidence-heavy investigations, hypothesis testing, and choosing the next check that will reduce uncertainty fastest.
Why use it?
It helps investigate ambiguous failures without committing too early to one cause or jumping straight to 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/bobbyjohnstx/tinycode/trace
Any agent
npx skills add bobbyjohnstx/tinycode --skill trace
Clone the repo
git clone --depth 1 https://github.com/bobbyjohnstx/tinycode

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,241 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 $0.00017 $0.02241
Opus 5 $0.00009 $0.01120
Sonnet 5 $0.00003 $0.00448
Haiku 4.5 $0.00002 $0.00224

Measured 2d ago against content hash 13c83df8b682, 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.

packages/tinycode/src/skill/defaults/trace/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trace Skill

Use this skill for ambiguous, causal, evidence-heavy questions where the goal is to explain why an observed result happened, not to jump directly into fixing or rewriting code.

Use the tracer agent as the lane worker when available. If the tracer agent is unavailable, each lane should be run as a focused subagent (or as a sequential investigation pass) — the lane structure, evidence contract, and rebuttal round still apply. The goal is to make tracing a reusable operating lane: restate the observation, generate competing explanations, gather evidence in parallel, rank the explanations, and propose the next probe that would collapse uncertainty fastest.

Good entry cases

Use /trace when:

  • Two or more genuinely different explanations could account for the observation AND you cannot yet determine which is correct from available evidence — this is the core entry gate
  • The problem is causal: you need to explain why an observed result happened, not just fix it
  • The failure is ambiguous enough that a single-lane diagnosis would miss real alternatives
  • The analysis benefits from parallel evidence-gathering across competing hypotheses

Examples:

  • runtime bugs and regressions
  • performance / latency / resource behavior
  • architecture / premortem / postmortem analysis
  • scientific or experimental result tracing
  • config / routing / orchestration behavior explanation
  • "given this output, trace back the likely causes"

When Not to Use

  • The root cause is already known and the task is to implement the fix — use executor
  • The goal is to confirm a change works, not explain why something happened — use verify
  • A single most-likely cause exists and competing hypotheses add no value — use debug
  • The user explicitly wants code written or changed, not a causal explanation
  • The failure is a straightforward error message with a single obvious cause (e.g. a missing import, a typo in a config key)

Examples

Good: "Auth works in dev but silently fails in prod — trace why" → Competing explanations: config mismatch vs. env-specific auth service vs. measurement error in the prod log query. Spawn 3 lanes.

Read the full file on GitHub · 262 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 · 262 lines · 17 tokens per session scan A 13c83df8b682

Subscribe to this mod's changes

trace is a skill published in the GitHub repository bobbyjohnstx/tinycode (11 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 2,241 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

system-prompts

Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.

can1357/oh-my-pi · 40 tokens

tool-prompt-optimization

Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…

can1357/oh-my-pi · 0 tokens

agent-browser

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

coleam00/Archon · 51 tokens

archon-cli

Drive Archon through its CLI: run AI workflows on a repo, manage those runs (inspect, approve, reject, cancel, resume), set up Archon or change its config, author new workflows, and improve workflow prompts. Use when the user says "use archon", "run archon", "archon workflow", "fix issue #N with archon", "have archon…

coleam00/Archon · 165 tokens

semantic-compression

Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…

can1357/oh-my-pi · 77 tokens

greet

A greeting skill for testing.

can1357/oh-my-pi · 8 tokens