audit-attention

audit-attention is a skill for Claude Code, Codex from tomzx/agents. It costs 57 tokens per session (1,185 once invoked), scanned A, original, MIT.

A personal time-use review that classifies activities as compounding or depreciating using the two-year test. Compounding work keeps creating value, while depreciating work becomes less valuable as circumstances change.

In plain words
What is it for?
Use it to review time from notes, calendars, Git or Slack activity, weekly summaries, or memory, then decide what work to protect and what to hand off.
Why use it?
It helps show where your time is being spent and which routine tasks may be delegated, reduced, or protected from interruption.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/tomzx/agents/audit-attention
Any agent
npx skills add tomzx/agents --skill audit-attention
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

Made for: Claude Code, Codex.

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 audit-attention

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/audit-attention.svg)](https://agentmods.dev/skills/tomzx/agents/audit-attention)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/audit-attention"><img src="https://agentmods.dev/badge/skills/tomzx/agents/audit-attention.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,185 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 5.1 $0.00057 $0.01185
Opus 5 $0.00028 $0.00593
Sonnet 5 $0.00011 $0.00237
Haiku 4.5 $0.00006 $0.00119

Measured 6d ago against content hash ce5c73855f9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

audit-attention 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 6d 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.

skills/audit-attention/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Attention

Classifies the activities on your plate as compounding or depreciating using the two-year test, so you can delegate depreciating work ruthlessly and ring-fence compounding work ferociously. The number that matters is not how much AI you use, nor how much you keep in human hands; it is how much of your time lands on compounding work.

Prerequisites

  • A list of the activities that filled the period (a day, a week, or a longer stretch). Source this from any of:
    • daily notes, calendars, git and Slack activity,
    • the weekly review/summary artifacts under {NOTES_DIR}/{YEAR}/weekly/{WEEK}/,
    • or the user's own recall when prompted.
  • No codebase access required; this is a personal-attention audit, not a service audit.

The Distinction

  • Compounding activities gain value the more you do them and feed back into everything else: deciding what to build, judging whether a design is right, reading a hard paper with the intent of being able to teach it, debugging a subtle failure by reasoning about the system, holding taste about what to ship.
  • Depreciating activities lose value as the environment changes: boilerplate, scaffolding, routine tests, formatting, summarizing a known pattern, re-deriving an answer a model can produce.

The Two-Year Test

For each activity, ask: If I let the model do this for the next two years, will the me that emerges be more valuable, or less, than the me that kept doing it by hand?

  • More valuable if delegated -> depreciating; delegate next cycle and route the freed time to compounding work.
  • Less valuable if delegated -> compounding; protect ferociously, do not delegate even when a model offers to.

Steps

  1. Gather the activity list for the period (see Prerequisites). If no list is provided, ask the user to enumerate the significant activities of the period before proceeding.
  2. Apply the two-year test to each significant activity and classify it compounding or depreciating.
  3. Estimate the fraction of the period that landed on compounding work.
  4. Note boundary moves since the last audit: activities that shifted category, and which direction.
  5. Produce the report using the format below.

Read the full file on GitHub · 98 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. 6d ago First seen · 98 lines · 57 tokens per session scan A ce5c73855f9b

Subscribe to this mod's changes

audit-attention is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 1,185 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 2026-08-31.