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.
npx agentmods add skills/tomzx/agents/audit-attentionnpx skills add tomzx/agents --skill audit-attentiongit clone --depth 1 https://github.com/tomzx/agentsWrote 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.
[](https://agentmods.dev/skills/tomzx/agents/audit-attention)<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>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.
| Model | Per session | Once 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 |
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.
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
- 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.
- Apply the two-year test to each significant activity and classify it compounding or depreciating.
- Estimate the fraction of the period that landed on compounding work.
- Note boundary moves since the last audit: activities that shifted category, and which direction.
- Produce the report using the format below.
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.
- 6d ago First seen · 98 lines · 57 tokens per session scan A ce5c73855f9b
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.