agentmods.dev

attention-control

attention-control is a skill for Claude Code from larsboes/Axon. It costs 150 tokens per session (968 once invoked), scanned A, original, MIT.

A writing guide that shapes responses for readers with ADHD, using clear language, action-first structure, active voice, and short steps. It applies to prose while leaving code, commands, paths, errors, and quotations unchanged.

In plain words
What is it for?
Use it when writing answers, summaries, instructions, or other prose that should be easier to scan and act on.
Why use it?
It reduces the effort needed to find the next action and follow instructions. It also limits tangents and keeps wording precise when brevity would risk accuracy.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cognitive-load plugin — 2 skills shipped together

not rated 1repo changed 1mo ago A scan 150 tokens original MIT

Good fit Use it when writing answers, summaries, instructions, or other prose that should be easier to scan and act on.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/larsboes/axon/attention-control
View source ↗ larsboes/Axon larsboes.github.io
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.

Any agent
npx skills add larsboes/Axon --skill attention-control
Clone the repo
git clone --depth 1 https://github.com/larsboes/Axon

Made for: Claude Code.

Or install cognitive-load, the plugin that ships this one along with the rest of its 2 skills.

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 attention-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/larsboes/axon/attention-control/github.svg)](https://agentmods.dev/skills/larsboes/axon/attention-control)
Your own site
<a href="https://agentmods.dev/skills/larsboes/axon/attention-control"><img src="https://agentmods.dev/badge/skills/larsboes/axon/attention-control/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for attention-control

Your own site · 80×15
<a href="https://agentmods.dev/skills/larsboes/axon/attention-control"><img src="https://agentmods.dev/badge/skills/larsboes/axon/attention-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 968 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00150 $0.00968
Opus 5.5 $0.00060 $0.00387
Sonnet 5.5 $0.00030 $0.00194
Haiku 4.5 $0.00015 $0.00097

Measured 1mo ago against content hash 8e64d7bb334f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

attention-control 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 1mo 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.

Packs/cognitive-load/skills/attention-control/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Attention Control

Scope

Apply to prose you write yourself — answers, summaries, instructions. Reproduce code, commands, paths, identifiers, error messages, and quotes verbatim. Accuracy wins over style. Never sacrifice precision for brevity.

Persistence

These rules apply to every response until "stop attention control" is invoked. Say so in one line when the skill engages, because a style that outlives the turn it was asked for is otherwise indistinguishable from a bug.

Shape rules

  1. Lead with the next action. The first line is a command, path, or fact.
  2. Do the work you own. Do not hand back work you can finish.
  3. Number multi-step work. One bounded action per step.
  4. End with one concrete next action. A task the reader can do in under two minutes.
  5. Suppress tangents. Finish the current issue before offering another.
  6. Restate state every turn. "Step X of Y done: [result]. Next: [action]."
  7. Use concrete time units. "15 minutes", not "some time".
  8. Show what now works. Name the result: "Login works. Run npm run dev."
  9. State errors flat. Give location, cause, and fix. No "Uh oh".
  10. Cap lists at 5 items. Split larger lists into categories.
  11. No preamble, no recap, no closer. Start with the answer. Stop when complete.

The reasoning behind these — small working memory, starting being the hard step, scarce dopamine — is in references/doctrine.md. Worked before/after pairs are in references/examples.md.

Language rules

Not restated here. Word choice, voice, tense, sentence length, noun clusters and clause structure are asd-ste100's, and it is the only place those rules live — they used to be duplicated in this file with the same numbers, which is how two skills drift.

Read asd-ste100 when the text must be parsed rather than read: tool descriptions, error strings, inter-agent instructions. This skill is about shape under cognitive load; that one is about ambiguity for a reader with no human in the loop.

Read the full file on GitHub · 80 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago Changed · +6 lines · +109 tokens per session 8e64d7bb334f
  2. 2mo ago First seen · 74 lines · 41 tokens per session scan A 85d1c11b1d2f

Subscribe to this mod's changes

attention-control is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 968 once invoked, about $0.0006 per session on Opus 5.5. 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.

Writing and docsagent-skillsai-agentsbazelclaudeintegration-platformlocal-first
Related

attention-control compared with skills from other repositories

attention-control next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
attention-controllarsboes/AxonSkill11mo agoMITA150Claude Code
ligandmpnnaipoch/open-scienceSkill5.5ktodayApache-2.0A100Claude Code, Codex
evo2aipoch/open-scienceSkill5.5ktodayApache-2.0A83Claude Code, Codex
create-agentPM-Shawn/Abu-CoworkSkill4193d agoApache-2.0A13Claude Code
content-monitorCoWork-OS/CoWork-OSSkill537todayMITA16Claude Code, Codex
llm-wikiCoWork-OS/CoWork-OSSkill537todayMITA27Claude Code, Codex
simplifyCoWork-OS/CoWork-OSSkill537todayMITA24Claude Code, Codex