release

A release procedure for publishing a new version of the atomic-agents Python package to PyPI and creating a GitHub release.

In plain words
What is it for?
Use it when releasing a major, minor, or patch version of atomic-agents from a clean main branch.
Why use it?
It organizes version changes, package building, publishing, and release creation into one documented process.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/eigenwise/atomic-agents/release
Any agent
npx skills add Eigenwise/atomic-agents --skill release
Clone the repo
git clone --depth 1 https://github.com/Eigenwise/atomic-agents

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 672 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.00672
Opus 5 $0.00022 $0.00336
Sonnet 5 $0.00009 $0.00134
Haiku 4.5 $0.00004 $0.00067

Measured yesterday against content hash 20e7c455a718, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release 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 yesterday.

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.

.claude/skills/release/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Process for atomic-agents

Overview

This skill guides the release process for atomic-agents, including version bumping, PyPI publishing, and GitHub release creation.

Prerequisites

  • Must be on main branch with clean working directory
  • .env file must contain PYPI_TOKEN environment variable
  • Must have push access to the repository

Release Types

Type When to Use Example
major Breaking changes 2.5.0 → 3.0.0
minor New features (backwards compatible) 2.5.0 → 2.6.0
patch Bug fixes only 2.5.0 → 2.5.1

Step-by-Step Process

1. Prepare the Branch

git checkout main
git pull
git status  # Ensure clean working directory

2. Run Build and Deploy Script

Important: The script bumps versions, so if it fails partway through, reset to main before retrying.

powershell -ExecutionPolicy Bypass -File build_and_deploy.ps1 <major|minor|patch>

This script will:

  • Read current version from pyproject.toml
  • Increment version based on release type
  • Update pyproject.toml with new version
  • Run uv sync to update dependencies
  • Run uv build to create distribution packages
  • Run uv publish to upload to PyPI

3. If Script Fails - Reset and Retry

git checkout main
git reset --hard origin/main
# Fix the issue, then run script again

4. Commit and Push Version Bump

git add pyproject.toml uv.lock
git commit -m "Release vX.Y.Z"
git push

5. Create GitHub Release

gh release create vX.Y.Z --title "vX.Y.Z" --notes "RELEASE_NOTES_HERE"

Release Notes Template

## What's New

### Feature Name
Brief description of the feature.

#### Features
- Feature 1
- Feature 2

#### Improvements
- Improvement 1

#### Bug Fixes
- Fix 1

### Full Changelog
https://github.com/eigenwise/atomic-agents/compare/vOLD...vNEW

Checklist

  • On main branch with clean working directory
  • .env file has PYPI_TOKEN
  • Determined correct release type (major/minor/patch)
  • Build and deploy script completed successfully
  • Version bump committed and pushed
  • GitHub release created with release notes

Read the full file on GitHub · 107 lines

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. yesterday First seen · 107 lines · 43 tokens per session scan A 20e7c455a718

Subscribe to this mod's changes

release is a skill published in the GitHub repository Eigenwise/atomic-agents (6,213 stars, last pushed 7d ago), licensed MIT. It adds 43 tokens to every session and 672 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 2026-08-30.

Related

Other skills, from other repositories

pr-test

E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls. TRIGGER when user asks to manually test a PR, test a feature end-to-end, or run integration tests against a running system.

Significant-Gravitas/AutoGPT · 51 tokens

pr-address

Address PR review comments and loop until CI green and all comments resolved. TRIGGER when user asks to address comments, fix PR feedback, respond to reviewers, or babysit/monitor a PR.

Significant-Gravitas/AutoGPT · 42 tokens

synalinks

Use for anything involving the Synalinks neuro-symbolic LM framework (Keras-inspired) — DataModel/Field/Input, JSON operators (+ & | ^ ), synalinks.ops, LanguageModel/EmbeddingModel and provider prefixes (openai/anthropic/ollama/groq/openrouter/bedrock/...); the Program class and its four building APIs…

SynaLinks/synalinks-skills · 290 tokens

pr-polish

Alternate /pr-review and /pr-address on a PR until the PR is truly mergeable — no new review findings, zero unresolved inline threads, zero unaddressed top-level reviews or issue comments, all CI checks green, and two consecutive quiet polls after CI settles. Use when the user wants a PR polished to merge-ready…

Significant-Gravitas/AutoGPT · 77 tokens

alfworld-device-operator

Operates a device or appliance (like a desklamp, microwave, or fridge) to interact with another object. Use when the task requires using a tool on a target item (e.g., "look at laptop under the desklamp", "heat potato with microwave"). Locates both the device and target object, co-locates them, and executes the…

zjunlp/SkillNet · 93 tokens

alfworld-inventory-management

Use when the agent must collect and track multiple instances of the same object type in ALFWorld (e.g., "put two cellphone in bed"). This skill maintains a count of collected versus needed objects, guides systematic searching through receptacles, and ensures each found object is placed at the target before searching…

zjunlp/SkillNet · 70 tokens