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

Factory Deferred Repositories

by warpdotdev in warpdotdev/warp

Check out a Factory's deferred repository on demand with environment-checkout, without overwriting existing checkouts or exposing credentials

AGPL-3.0Auto-check passed

Install Factory Deferred Repositories

skills CLI
$ npx skills add warpdotdev/warp --skill factory-deferred-repositories -a claude-code

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

GitHub CLI
$ gh skill install warpdotdev/warp factory-deferred-repositories --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/warpdotdev/warp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/bundled/skills/factory-deferred-repositories .claude/skills/factory-deferred-repositories && 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
factory-deferred-repositories
GitHub stars
65k
Token cost
~765 tokens
SKILL.md length
396 words
Files
1
Skills in repo
47
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Check out a Factory's deferred repository on demand with environment-checkout, without overwriting existing checkouts or exposing credentials

  • Works in 6 steps: Select only repositories the task needs.… → Create a private scratch directory… → Invoke the inventory's shell-quoted… → …
  • Calls git

What it does

Factory Deferred Repositories is an agent skill from warpdotdev/warp. Check out a Factory's deferred repository on demand with environment-checkout, without overwriting existing checkouts or exposing credentials

Its SKILL.md is about 770 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: Warp is an agentic development environment, born out of the terminal. The licence is AGPL-3.0.

Example prompts

  • “/factory-deferred-repositories”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Select only repositories the task needs. Copy their inventory checkout request objects, preserving each source identity. If the inventory…
  2. Create a private scratch directory outside the checkout targets. Write a fresh JSON requests file with exactly {"working_dir": ""…
  3. Invoke the inventory's shell-quoted absolute executable using its command_template. Replace each entire quoted placeholder argument (''…
  4. Run in the existing agent shell, retaining its HOME, environment and preconfigured Git credential helper. Never replace credentials…
  5. Capture the command's exit status and inspect the complete fresh report before treating any checkout as successful. Require one outcomes…
  6. Never retry into a partially created target or automatically delete, reset, or remove an origin from a checkout target. Inspect a failed…

What it can do on your machine

Read from SKILL.md and the folder at commit 2055f0f. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Factory Deferred Repositories loads about 765 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 396 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~765

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 warpdotdev/warp at commit 2055f0f, republished under its AGPL-3.0 licence (© warpdotdev). 396 words, ~765 tokens.

Download SKILL.mdSave it as .claude/skills/factory-deferred-repositories/SKILL.md (or your agent's skills folder).
name
factory-deferred-repositories
description
Check out a Factory's deferred repository on demand with environment-checkout, without overwriting existing checkouts or exposing credentials

Deferred Factory repositories

The run's initial repository inventory supplies a checkout runtime and typed checkout requests for repositories attached to this Factory but not cloned yet. Use that inventory, not the current working directory or a guessed forge.

  1. Select only repositories the task needs. Copy their inventory checkout request objects, preserving each source identity. If the inventory marks a target-name collision, change checkout_name to an unused single directory name under the workspace root. Never replace or write inside an existing checkout, directory, file, or symlink.
  2. Create a private scratch directory outside the checkout targets. Write a fresh JSON requests file with exactly {"working_dir": "<inventory runtime working_dir>", "repositories": [<selected request objects>]}. Use the inventory's absolute working_dir, even when the shell has automatically changed into the sole eager repository. Do not invent extra fields.
  3. Invoke the inventory's shell-quoted absolute executable using its command_template. Replace each entire quoted placeholder argument ('<requests-file>' and '<report-file>', including its quotes) with a shell-quoted absolute path in the private scratch directory. The command is top-level environment-checkout, not agent-driver environment-checkout. Keep --fail-if-target-exists; do not use --remove-origins-only or substitute another executable found on PATH.
  4. Run in the existing agent shell, retaining its HOME, environment and preconfigured Git credential helper. Never replace credentials, disable authentication, or put an access token in a prompt, command, URL, log, or file. Do not fall back to raw git clone if the helper is unavailable; report the blocked checkout.
  5. Capture the command's exit status and inspect the complete fresh report before treating any checkout as successful. Require one outcomes entry for every submitted request_index, no missing or duplicate indices, and failure: null for each successful checkout. On nonzero exit, missing/malformed report, or a Clone, Checkout, or RemoveOrigin failure, identify the affected request and its redacted diagnostics. A failed batch may still have created successful checkouts; inspect them rather than replaying the entire batch.
  6. Never retry into a partially created target or automatically delete, reset, or remove an origin from a checkout target. Inspect a failed target first; choose an unused checkout_name if a retry is needed. Remove only the private scratch request/report files you created, after inspecting the report.
Show full SKILL.md (36 more words)Show less

An on-demand checkout creates a Git working tree only. It does not automatically load repository skills, discover file-based MCP servers, run environment setup commands, initialize the build cache, or register the repository with Oz codebase indexing.

© warpdotdev, AGPL-3.0. 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 resources/bundled/skills/factory-deferred-repositories of warpdotdev/warp.

Open the folder on GitHubat commit 2055f0f

Compare with similar skills

Factory Deferred Repositories 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.

Factory Deferred Repositories compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Factory Deferred Repositories this skillwarpdotdev/warp65k—~765Automated safety check: PassAGPL-3.0
Factorial AutomationComposioHQ/awesome-claude-skills77k3 repos~738Automated safety check: PassNone
Defer Asyncthedaviddias/Front-End-Checklist74k—~494Automated safety check: PassMIT
FactoryBuilderIO/skills4.6k—~1kAutomated safety check: PassMIT
Theme Factoryanthropics/skills180k47 repos~781Automated safety check: PassApache-2.0
Factory Planmastra-ai/mastra29k—~1.5kAutomated safety check: PassCustom licence

Similar skills

  • Factorial Automation

    ComposioHQ/awesome-claude-skills

    Automate Factorial tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~738 tokens
    Productivity & AutomationAuto-check passed

  • Defer Async

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Load scripts with defer, async, or type=module.

    74k GitHub stars~494 tokensUpdated 4 days ago
    Auto-check passed

  • Factory

    BuilderIO/skills

    Experimental workflow for configuring an autonomous software delivery factory.

    4.6k GitHub stars~1k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Theme Factory

    anthropics/skills

    Official

    Applies one of ten preset color and font themes to slide decks, documents or HTML pages, or creates a new theme on the fly after you choose from a showcase.

    180k GitHub starsUsed in 47 repos~781 tokens
    Frontend & DesignAuto-check passed

  • Factory Plan

    mastra-ai/mastra

    Produce a phased implementation plan for a Factory work item, then advance it to execute

    29k GitHub stars~1.5k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Factory Triage

    mastra-ai/mastra

    Triage a Factory work item's issue — trace history, understand architecture, diagnose root cause, then advance the stage

    29k GitHub stars~4.5k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from warpdotdev/warp

All 47 skills in this repo

  • Figma Design System Builder

    warpdotdev/warp

    Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.

    65k GitHub starsUsed in 2 repos~4.4k tokens
    Auto-check passed

  • Figma use_figma Plugin API Rules

    warpdotdev/warp

    Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Auto-check passed

  • Warp Factory Files

    warpdotdev/warp

    Authors and edits file-based Warp software factory definitions rooted at factory.yaml, covering agents, automations, scorers and webhooks, and validates them before a pull request.

    65k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed

  • Figma Design to Code

    warpdotdev/warp

    Turns a Figma frame or component into production code that matches the design, using the Figma MCP server and the project's own design system.

    65k GitHub starsUsed in 4 repos~2.9k tokens
    Auto-check passed

  • Warp GUI to Agent CLI Migration

    warpdotdev/warp

    Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check passed

  • Figma Design System Rules Generator

    warpdotdev/warp

    Creates project-specific design system rules from your codebase so coding agents implement Figma designs with your components, naming and tokens.

    65k GitHub starsUsed in 3 repos~4.6k tokens
    Auto-check passed

Questions about Factory Deferred Repositories

What does Factory Deferred Repositories do?

Check out a Factory's deferred repository on demand with environment-checkout, without overwriting existing checkouts or exposing credentials. Factory Deferred Repositories is an agent skill from warpdotdev/warp.

How do I install Factory Deferred Repositories in Claude Code?

Run `npx skills add warpdotdev/warp --skill factory-deferred-repositories -a claude-code`. Or copy the skill folder (resources/bundled/skills/factory-deferred-repositories in warpdotdev/warp) into .claude/skills/factory-deferred-repositories in your project. Claude Code loads it when a task matches its description.

How do I install Factory Deferred Repositories in Codex?

Run `npx skills add warpdotdev/warp --skill factory-deferred-repositories -a codex`. Or copy the skill folder (resources/bundled/skills/factory-deferred-repositories in warpdotdev/warp) into .agents/skills/factory-deferred-repositories in your project. Codex loads it when a task matches its description.

Can I use Factory Deferred Repositories 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 warpdotdev/warp --skill factory-deferred-repositories -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/factory-deferred-repositories, .gemini/skills/factory-deferred-repositories, .github/skills/factory-deferred-repositories and .opencode/skills/factory-deferred-repositories in your project.

What does Factory Deferred Repositories need to run?

Going by SKILL.md and its folder, Factory Deferred Repositories needs the command-line tools its instructions call (git).

Does Factory Deferred Repositories access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Factory Deferred Repositories 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 Factory Deferred Repositories use?

Factory Deferred Repositories is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Factory Deferred Repositories use?

About 765 tokens (SKILL.md is roughly 3.1k 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 Factory Deferred Repositories?

Skills that share tags, products or a category with Factory Deferred Repositories: Factorial Automation (ComposioHQ/awesome-claude-skills, 77k stars), Defer Async (thedaviddias/Front-End-Checklist, 74k stars), Factory (BuilderIO/skills, 4.6k stars) and Theme Factory (anthropics/skills, 180k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Factory Deferred Repositories?

warpdotdev (a GitHub organization) maintains it in warpdotdev/warp, which has 65,406 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on October 10, 2026.

Source: warpdotdev/warp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.