release

A procedure for publishing stable versions of Agent Lightning, a toolkit for optimizing coding agents. It covers version changes, pull-request checks, merging, tags, PyPI publishing, and versioned documentation.

In plain words
What is it for?
Use it when planning, creating, checking, or explaining an Agent Lightning release. Nightly TestPyPI builds follow a separate process.
Why use it?
A merged pull request alone does not publish a stable release. The procedure helps verify the repository and follow the steps that make the package and its documentation public.

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/microsoft/agent-lightning/release
Any agent
npx skills add microsoft/agent-lightning --skill release
Clone the repo
git clone --depth 1 https://github.com/microsoft/agent-lightning

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,661 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 $0.00063 $0.02661
Opus 5 $0.00032 $0.01331
Sonnet 5 $0.00013 $0.00532
Haiku 4.5 $0.00006 $0.00266

Measured yesterday against content hash 44be3b95bec6, 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.

.agents/skills/release/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Agent Lightning

Merging a pull request does not publish a stable release. Stable publication is triggered only by pushing a v* tag to the canonical repository; the tagged commit is what gets tested, built, and uploaded. That same tag push also deploys versioned documentation and moves the public stable alias, so a release has two public side effects, not one.

Establish the release state

  1. Confirm the repository root, clean working tree, current branch, and remotes.
  2. Resolve the canonical OWNER/REPO, its default branch, and its permitted merge methods with gh repo view OWNER/REPO --json nameWithOwner,defaultBranchRef,mergeCommitAllowed,rebaseMergeAllowed,squashMergeAllowed. Identify the local remotes for that repository and the contributor fork by their URLs; do not assume particular remote names or merge settings.
  3. Inspect the release contract in:
    • .github/workflows/pypi-release.yml
    • .github/workflows/docs.yml
    • .github/workflows/tests.yml
    • scripts/bump_version.sh
    • pyproject.toml
    • agentlightning/__init__.py
  4. Confirm the canonical default branch is already green before branching from it. Resolve its current commit with gh api repos/OWNER/REPO/commits/<default-branch> and inspect that commit's check runs; a general recent-run listing can omit or mix commits. A release branch inherits every failure that main is carrying.
  5. Query the canonical repository's tags and compare them with the versions published at https://pypi.org/pypi/agentlightning/json. Confirm the target version exists in neither place, and stop for an explicit release decision when either of these holds:
    • A tag exists with no matching PyPI version. A published version is immutable, and its tag must never be reused or moved. A tag that never published is a different situation and still needs a human decision, informed by why it did not publish. See "Recovering a tag that never published" below.
    • The proposed bump would skip a version that was tagged but never published.
  6. Treat verified PyPI trusted-publisher configuration for the canonical repository and pypi-release.yml as a prerequisite. If it cannot be inspected directly, require confirmation from an authorized PyPI project owner before pushing the release tag.

Read the full file on GitHub · 239 lines

Files

What ships with it

1 file 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. yesterday First seen · 239 lines · 63 tokens per session scan A 44be3b95bec6

Subscribe to this mod's changes

release is a skill published in the GitHub repository microsoft/agent-lightning (17,926 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 2,661 once invoked, about $0.0003 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

AudioCraft

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.

agentic-in/elephant-agent · 49 tokens

LM Evaluation Harness

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

agentic-in/elephant-agent · 81 tokens

Weights & Biases

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform.

agentic-in/elephant-agent · 38 tokens

llama.cpp

Run LLM inference with llama.cpp on CPU, Apple Silicon, AMD/Intel GPUs, or NVIDIA — plus GGUF model conversion and quantization (2–8 bit with K-quants and imatrix). Covers CLI, Python bindings, OpenAI-compatible server, and Ollama/LM Studio integration. Use for edge deployment, M1/M2/M3/M4 Macs, CUDA-less…

agentic-in/elephant-agent · 90 tokens

Obliteratus

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament…

agentic-in/elephant-agent · 103 tokens

Segment Anything

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

agentic-in/elephant-agent · 43 tokens