rattler-build

rattler-build is a skill for Claude Code, Codex from pavelzw/skill-forge. It costs 54 tokens per session (1,187 once invoked), scanned A, original, BSD-3-Clause.

Instructions for building and inspecting Conda packages with rattler-build, a tool that turns package recipes into installable packages. It covers recipes, builds, patches, and package checks.

In plain words
What is it for?
Use it to create recipes, build existing recipes, debug build errors, make patches from build-directory changes, and inspect finished .conda packages.
Why use it?
It gives developers a workflow for handling common package-building tasks and investigating why a build fails.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create recipes, build existing recipes, debug build errors, make patches from build-directory changes, and inspect finished .conda packages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pavelzw/skill-forge/rattler-build
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 pavelzw/skill-forge --skill rattler-build
Clone the repo
git clone --depth 1 https://github.com/pavelzw/skill-forge

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 rattler-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/pavelzw/skill-forge/rattler-build/github.svg)](https://agentmods.dev/skills/pavelzw/skill-forge/rattler-build)
Your own site
<a href="https://agentmods.dev/skills/pavelzw/skill-forge/rattler-build"><img src="https://agentmods.dev/badge/skills/pavelzw/skill-forge/rattler-build/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 rattler-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/pavelzw/skill-forge/rattler-build"><img src="https://agentmods.dev/badge/skills/pavelzw/skill-forge/rattler-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00054 $0.01187
Opus 5 $0.00027 $0.00593
Sonnet 5 $0.00011 $0.00237
Haiku 4.5 $0.00005 $0.00119

Measured 10d ago against content hash 97a295e3540e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rattler-build scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Requires rattler-build, curl, jq, and standard Unix tools; some workflows also
recipes/rattler-build/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rattler-build Operations

Determine which workflow applies based on the task:

Task Workflow
Create a new recipe for a package references/new-recipe.md
Build an existing recipe references/build-recipe.md
Debug a failed build references/debug-build.md
Create a patch from build dir changes references/create-patch.md
Inspect a built .conda package references/inspect-package.md

Recipe Format Reference

A rattler-build recipe (recipe.yaml) has these key sections:

context:
  name: mypackage
  version: "1.0.0"

package:
  name: ${{ name }}
  version: ${{ version }}

source:
  url: https://example.com/source-${{ version }}.tar.gz
  sha256: <hash>

build:
  number: 0
  script:
    - cmake -B build -G Ninja -DCMAKE_INSTALL_PREFIX=${{ PREFIX }}
    - cmake --build build
    - cmake --install build

requirements:
  build:
    - ${{ compiler('c') }}
    - ${{ compiler('cxx') }}
    - cmake
    - ninja
  host:
    - zlib
  run:
    - zlib

tests:
  - package_contents:
      bin:
        - myprogram
  - script:
      - myprogram --version

about:
  homepage: <url>
  license: <SPDX-license>
  license_file: LICENSE
  summary: <one-line summary>

Multi-output recipe

A single recipe can produce multiple packages using outputs. When using outputs, replace the top-level package with recipe and define each output separately:

context:
  version: "1.0.0"

recipe:
  name: mylib-split
  version: ${{ version }}

source:
  url: https://example.com/mylib-${{ version }}.tar.gz
  sha256: <hash>

build:
  number: 0

outputs:
  - package:
      name: libmylib
    requirements:
      build:
        - ${{ compiler('c') }}
        - cmake
        - ninja
      host:
        - zlib
      run:
        - zlib
    build:
      script:
        - cmake -B build -G Ninja -DCMAKE_INSTALL_PREFIX=${{ PREFIX }}
        - cmake --build build
        - cmake --install build
    tests:
      - package_contents:
          lib:
            - mylib

  - package:
      name: mylib-dev
    requirements:
      run:
        - ${{ pin_subpackage('libmylib', exact=True) }}
    build:
      script:
        - mkdir -p $PREFIX/include
        - cp -R include/* $PREFIX/include/
    tests:
      - package_contents:
          include:
            - mylib.h

Read the full file on GitHub · 172 lines

Files

What ships with it

7 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. 10d ago First seen · 172 lines · 54 tokens per session scan A 97a295e3540e

Subscribe to this mod's changes

rattler-build is a skill published in the GitHub repository pavelzw/skill-forge (24 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 54 tokens to every session and 1,187 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens