agentmods.dev

optimizing-attention-flash

optimizing-attention-flash is a skill for Claude Code, Codex from KalarisLabs/research-agent-skills. It costs 154 tokens per session (3,470 once invoked), scanned A, original, no licence file.

Enables Flash Attention for transformer models using PyTorch native scaleddotproductattention (PyTorch 2.2+) or the flash-attn library, including multi-query attention, sliding window attention, and FP8 on H100 (FlashAttention-3). Covers profiling speedup, checking accuracy against a baseline, and troubleshooting…

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

not rated 105repo today A scan 154 tokens custom licence
Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kalarislabs/research-agent-skills/optimizing-attention-flash
View source ↗ KalarisLabs/research-agent-skills docs.kalarislabs.com
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 KalarisLabs/research-agent-skills --skill optimizing-attention-flash
Clone the repo
git clone --depth 1 https://github.com/KalarisLabs/research-agent-skills

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 optimizing-attention-flash

README.md
[![agentmods](https://agentmods.dev/badge/skills/kalarislabs/research-agent-skills/optimizing-attention-flash/github.svg)](https://agentmods.dev/skills/kalarislabs/research-agent-skills/optimizing-attention-flash)
Your own site
<a href="https://agentmods.dev/skills/kalarislabs/research-agent-skills/optimizing-attention-flash"><img src="https://agentmods.dev/badge/skills/kalarislabs/research-agent-skills/optimizing-attention-flash/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 optimizing-attention-flash

Your own site · 80×15
<a href="https://agentmods.dev/skills/kalarislabs/research-agent-skills/optimizing-attention-flash"><img src="https://agentmods.dev/badge/skills/kalarislabs/research-agent-skills/optimizing-attention-flash.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,470 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 unknown 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 $0.00154 $0.03470
Opus 5.5 $0.00062 $0.01388
Sonnet 5.5 $0.00031 $0.00694
Haiku 4.5 $0.00015 $0.00347

Measured today against content hash cb0da3d9f257, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

optimizing-attention-flash 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 today.

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/optimizing-attention-flash/SKILL.md · 396 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. today First seen · 396 lines · 154 tokens per session scan A cb0da3d9f257

Subscribe to this mod's changes

optimizing-attention-flash is a skill published in the GitHub repository KalarisLabs/research-agent-skills (105 stars, last pushed today), with no licence file. It adds 154 tokens to every session and 3,470 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 2026-11-07.

Data and AIDebuggingacademic-researchacademic-writingagent-skillsai-agentsbioinformaticscitation-verification
Related

optimizing-attention-flash compared with skills from other repositories

optimizing-attention-flash next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
optimizing-attention-flashKalarisLabs/research-agent-skillsSkill105todaynoneA154Claude Code, Codex
research-managerpoemswe/co-researcherSkill1354d agoMITA21Claude Code
alterlab-pyhealthAlterLab-IEU/AlterLab-Academic-SkillsSkill85yesterdayMITA132Claude Code
alterlab-timesfmAlterLab-IEU/AlterLab-Academic-SkillsSkill85yesterdayMITA150Claude Code
alterlab-esmAlterLab-IEU/AlterLab-Academic-SkillsSkill85yesterdayMITA101Claude Code
alterlab-deepchemAlterLab-IEU/AlterLab-Academic-SkillsSkill85yesterdayMITA127Claude Code
alterlab-pufferlibAlterLab-IEU/AlterLab-Academic-SkillsSkill85yesterdayMITA127Claude Code