trace

trace is a skill for Claude Code, Codex from ai-analyst-lab/ai-analyst-plugin. It costs 69 tokens per session (607 once invoked), scanned A, original, MIT.

A source-tracking skill for reported numbers. It connects each number to the query or calculation and the file or table that supplied the data.

In plain words
What is it for?
Creating trace tables for analyses, briefs, charts, and other deliverables with numerical claims.
Why use it?
It removes the guesswork from checking where a figure came from and helps reveal unsupported numbers before sharing a report.

Skill for Claude CodeCodex

Part of the ai-analyst-plus plugin — 44 skills, 1 command, 13 agents 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/ai-analyst-lab/ai-analyst-plugin/trace
Any agent
npx skills add ai-analyst-lab/ai-analyst-plugin --skill trace
Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-plugin

Made for: Claude Code, Codex.

Or install ai-analyst-plus, the plugin that ships this one along with the rest of its 44 skills, 1 command, 13 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for trace

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst-plugin/trace.svg)](https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plugin/trace)
Your own site
<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plugin/trace"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst-plugin/trace.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 607 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 $0.00069 $0.00607
Opus 5 $0.00034 $0.00303
Sonnet 5 $0.00014 $0.00121
Haiku 4.5 $0.00007 $0.00061

Measured 4d ago against content hash 0c49824d1ccb, 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 4d 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.

ai-analyst-plus/skills/trace/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/trace: tie every number to its source

Purpose

Answer "where did that number come from?" with evidence, not memory. Every number in a brief or readout gets linked to the exact computation and source data that produced it.

When to Use

  • The user asks where a number came from, or to show the work.
  • Before any deliverable leaves the session (analyst-core rule: trace numbers to source).
  • Reviewing an analysis produced earlier in the session or found in .knowledge/analyses/.

Instructions

  1. Collect the findings. List every specific number in the deliverable being traced: headline figures, table cells that carry the argument, chart values called out in text.

  2. Collect the computations. Gather the queries and code run this session (re-read your own steps; if the analysis logged queries to .knowledge/query-log.md, read that too).

  3. Build the trace table and include it in the output (or save as trace.md next to the deliverable if the user wants a file):

    # Number Where it appears Produced by Source data Confidence
    1 $1.2M brief, headline SUM(amount) over Q2 orders query orders.csv cited

    Confidence labels:

    • cited: the computation for this number was run this session and is shown.
    • value-match: a run computation produced this value, but the deliverable did not name it.
    • inferred: no run computation produced it; state where it came from (an input doc, an assumption) or mark it unverified.
  4. Surface the gaps loudly. Unverified numbers and orphan queries (run but unused) are the most important rows. Never hide them. If a headline number is inferred or unverified, say so at the top of the trace, not in a footnote.

  5. Offer the fix. For any unverified number, offer to recompute it live from the source data so it can be promoted to cited.

Notes

  • This is a reading-and-reporting skill: no scripts, no extra infrastructure. The evidence is the session's own work plus the files in the working folder.
  • Pairs with the reconcile check (parts sum to totals) and the reliability skill (run it again).

Read the full file on GitHub · 53 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. 4d ago First seen · 53 lines · 69 tokens per session scan A 0c49824d1ccb

Subscribe to this mod's changes

trace is a skill published in the GitHub repository ai-analyst-lab/ai-analyst-plugin (32 stars, last pushed 8d ago), licensed MIT. It adds 69 tokens to every session and 607 once invoked, about $0.0003 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

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

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

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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