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 skills add larsboes/Axon --skill attention-controlgit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/attention-control)<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.
<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>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 | $0.00041 | $0.00807 |
| Opus 5 | $0.00020 | $0.00404 |
| Sonnet 5 | $0.00008 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00081 |
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 8d 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 — 74 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.
Shape Rules
- Lead with the next action. The first line is a command, path, or fact.
- Do the work you own. Do not hand back work you can finish.
- Number multi-step work. One bounded action per step.
- End with one concrete next action. A task the reader can do in <2 mins.
- Suppress tangents. Finish the current issue before offering another.
- Restate state every turn. "Step X of Y done: [result]. Next: [action]."
- Use concrete time units. "15 minutes", not "some time".
- Show what now works. Name the result: "Login works. Run
npm run dev." - State errors flat. Provide location, cause, and fix. No "Uh oh".
- Cap lists at 5 items. Split larger lists into categories.
- No preamble, no recap, no closer. Start with the answer. Stop when complete.
Language Rules
Words
- One word, one meaning.
- One action, one verb. Do not rotate synonyms.
- Use standard verbs:
check,make sure,start,stop,use,show,find,change,remove,need. - Keep technical terms verbatim.
Grammar
- Use the active voice.
- Use simple tenses only (present, past, future, imperative).
- No perfect tenses ("I have changed" $\to$ "I changed").
- No auxiliary verb constructions ("would have been").
- Use the imperative for instructions ("Run the tests").
- Avoid "-ing" forms where simple forms work ("before you commit").
Sentences & Structure
- Instructions: Max 20 words/sentence. One instruction per sentence.
- Explanations: Max 25 words/sentence.
- Noun clusters: Max 3 words.
- Paragraphs: Max 6 sentences. One topic per paragraph.
- Lists: Use numbered lists for sequences; bullets for parallel items.
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.
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.
- 8d ago First seen · 74 lines · 41 tokens per session scan A 85d1c11b1d2f
attention-control is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 807 once invoked, about $0.0002 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…
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
frame-light-leak-cinema
Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.