New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Winnow

by VKirill in VKirill/claude-lane-stack

How to read winnow stubs in tool results. An agent skill from VKirill/claude-lane-stack.

MITAuto-check passed

Install Winnow

skills CLI
$ npx skills add VKirill/claude-lane-stack --skill winnow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install VKirill/claude-lane-stack winnow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/lane-stack/skills/winnow .claude/skills/winnow && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
winnow
GitHub stars
122
Used in
1 other repo
Token cost
~550 tokens
SKILL.md length
248 words
Files
1
Skills in repo
49
Repo updated
First seen
Licence
MIT

At a glance

How to read winnow stubs in tool results. An agent skill from VKirill/claude-lane-stack.

  • A tool result contains [winnow] lines
  • SKILL.md covers What a stub looks like, How to treat it and Tools
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Winnowrecall / winnowstats tools are available

What it does

Winnow is an agent skill from VKirill/claude-lane-stack. How to read winnow stubs in tool results. A block marked "[winnow] ... hidden" was judged unlikely to matter for the current task and replaced with a short summary plus a recall key; call winnowrecall to restore it. Use when a tool result contains "[winnow]" lines or when winnowrecall / winnowstats tools are available.

Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Multi-agent AI coding factory for one person — Claude Code PM + Codex/Qwen/Grok/Kimi/AGY writers, durable conveyor, auto-merge to main. The licence is MIT.

When your agent uses it

  • A tool result contains [winnow] lines
  • Winnowrecall / winnowstats tools are available

Example prompts

  • “[winnow] ... hidden”
  • “[winnow]”
  • “/winnow”

What it can do on your machine

Read from SKILL.md and the folder at commit 45fa19e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Winnow loads about 550 tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 248 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~550

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from VKirill/claude-lane-stack at commit 45fa19e, republished under its MIT licence (© VKirill). 248 words, ~550 tokens.

Download SKILL.mdSave it as .claude/skills/winnow/SKILL.md (or your agent's skills folder).
name
winnow
description
How to read winnow stubs in tool results. A block marked "[winnow] ... hidden" was judged unlikely to matter for the current task and replaced with a short summary plus a recall key; call winnow_recall to restore it. Use when a tool result contains "[winnow]" lines or when winnow_recall / winnow_stats tools are available.

winnow

winnow sits between Claude Code's tools and your context. After Read, Bash, or Grep returns a large result, winnow splits it into blocks, asks a System One model (TypeSafe's Jev, or an LLM-backed adapter) one yes/no question per block ("is this block needed for the current task?"), and replaces the low-probability blocks with a stub.

What a stub looks like

[winnow] Lines 41-188 (148 lines) hidden: judged unlikely to matter for the current task (relevance <= 0.22).
[winnow] Summary: Boilerplate license header and the argparse setup for flags that are not part of this task.
[winnow] Full text cached as key a1b2c3d4e5f6. Call winnow_recall(key="a1b2c3d4e5f6", start=41, end=188) if you need it.

How to treat it

  • The summary is written by a cheap model and preserves identifiers, paths, numbers and error text. Trust it for orientation, not for exact values.
  • If the hidden lines might matter after all, call the winnow_recall tool with the key. Add start and end to fetch only part of the cached text. Do not re-run the original command just to see the hidden part; recall is cheaper and does not re-trigger side effects.
  • Outputs that show an error are never pruned. If you see a stub, the judge believed the output was clean.
  • Line numbers in a stub refer to the original file or output. Claude Code renumbers the rewritten result from 1, so the numbers you see in the margin of a pruned Read do not match the file; use the stub's range with Read offset/limit or winnow_recall to reach the original lines. Edit is unaffected because it matches on text, not line numbers.

Tools

  • winnow_recall(key, start?, end?): return the cached full text for a key.
  • winnow_stats(): tokens saved, outputs rewritten, and the regret rate (how often a pruned key was later recalled).

© VKirill, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/lane-stack/skills/winnow of VKirill/claude-lane-stack.

Open the folder on GitHubat commit 45fa19e

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in VKirill/claude-lane-stack, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Winnow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Winnow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Winnow this skillVKirill/claude-lane-stack1221 repos~550Automated safety check: PassMIT
Block Kitopenclaw/openclaw392k—~624Automated safety check: PassMIT
Render Blockingthedaviddias/Front-End-Checklist74k—~430Automated safety check: PassMIT
Blocking IO Guardbytedance/deer-flow84k—~1.7kAutomated safety check: PassMIT
Color Blockingsickn33/agentic-awesome-skills47k1 repos~2.4kAutomated safety check: PassMIT
Add Block Previewsimstudioai/sim30k—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Block Kit

    openclaw/openclaw

    Use proactively for structured or interactive Slack replies, and when asked to author or validate native Slack Block Kit JSON.

    392k GitHub stars~624 tokensUpdated today
    Auto-check passed

  • Render Blocking

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Eliminate render-blocking resources.

    74k GitHub stars~430 tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed

  • Blocking IO Guard

    bytedance/deer-flow

    Adds a runtime test anchor for backend async code that could block the asyncio event loop, and proves the anchor fails when the blocking call returns.

    84k GitHub stars~1.7k tokensUpdated today
    DevelopmentAuto-check passed

  • Color Blocking

    sickn33/agentic-awesome-skills

    Web and App implementation guide for Color Blocking. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~2.4k tokens
    MobileAuto-check passed

  • Add Block Preview

    simstudioai/sim

    Gate a block's visibility — ship an unreleased block as a preview (hidden until revealed via AppConfig/env), reveal it to admins/orgs, GA it, or kill-switch a shipped block

    30k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Add Block

    simstudioai/sim

    Create or update a Sim integration block with correct subBlocks, conditions, dependsOn, modes, canonicalParamId usage, outputs, and tool wiring.

    30k GitHub stars~10k tokensUpdated today
    Backend & APIsAuto-check passed

More from VKirill/claude-lane-stack

All 49 skills in this repo

  • UI UX Pro Max

    VKirill/claude-lane-stack

    Lane-stack design + brand intelligence (vendored ui-ux-pro-max).

    122 GitHub stars~4.7k tokensUpdated today
    Auto-check passed

  • App Architect

    VKirill/claude-lane-stack

    Owner-facing architect for a new app or service. An agent skill from VKirill/claude-lane-stack.

    122 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Browser QA

    VKirill/claude-lane-stack

    Live browser QA + Playwright-compatible replay. An agent skill from VKirill/claude-lane-stack.

    122 GitHub stars~2.1k tokensUpdated today
    Auto-check passed

  • Copy Project Life

    VKirill/claude-lane-stack

    Карта файлов копирайта в .agents/copy/: шаблоны, статусы, цепочка audience→headlines→ux.

    122 GitHub stars~534 tokensUpdated today
    Auto-check passed

  • Copy Research

    VKirill/claude-lane-stack

    Dispatch copy-lead helpers: Tavily, Codex luna/terra, grok/X, OpenCode DeepSeek, Cursor Grok 4.6 medium-fast.

    122 GitHub stars~827 tokensUpdated today
    Auto-check passed

  • Docs Maintain

    VKirill/claude-lane-stack

    Keep living docs/ honest after code changes. An agent skill from VKirill/claude-lane-stack.

    122 GitHub stars~459 tokensUpdated today
    Auto-check passed

Questions about Winnow

What does Winnow do?

How to read winnow stubs in tool results. An agent skill from VKirill/claude-lane-stack. Winnow is an agent skill from VKirill/claude-lane-stack. How to read winnow stubs in tool results.

When should I use Winnow?

Winnow fits situations like: A tool result contains [winnow] lines; winnowrecall / winnowstats tools are available.

How do I install Winnow in Claude Code?

Run `npx skills add VKirill/claude-lane-stack --skill winnow -a claude-code`. Or copy the skill folder (plugins/lane-stack/skills/winnow in VKirill/claude-lane-stack) into .claude/skills/winnow in your project. Claude Code loads it when a task matches its description.

How do I install Winnow in Codex?

Run `npx skills add VKirill/claude-lane-stack --skill winnow -a codex`. Or copy the skill folder (plugins/lane-stack/skills/winnow in VKirill/claude-lane-stack) into .agents/skills/winnow in your project. Codex loads it when a task matches its description.

Can I use Winnow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VKirill/claude-lane-stack --skill winnow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/winnow, .gemini/skills/winnow, .github/skills/winnow and .opencode/skills/winnow in your project.

What does Winnow need to run?

SKILL.md names no scripts, command-line tools or credentials: Winnow is instructions for the agent only.

Does Winnow access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Winnow safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Winnow use?

Winnow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Winnow use?

About 550 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Winnow?

Skills that share tags, products or a category with Winnow: Block Kit (openclaw/openclaw, 392k stars), Render Blocking (thedaviddias/Front-End-Checklist, 74k stars), Blocking IO Guard (bytedance/deer-flow, 84k stars) and Color Blocking (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Winnow?

VKirill (a GitHub user) maintains it in VKirill/claude-lane-stack, which has 122 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 9, 2026.

Source: VKirill/claude-lane-stack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.