Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/release-prep/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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.
[](https://agentmods.dev/skills/smart-ai-memory/attune-ai/release-prep)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/release-prep"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/release-prep.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.00964 |
| Opus 5 | $0.00022 | $0.00482 |
| Sonnet 5 | $0.00009 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
release-prep 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 2d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Prep
IMPORTANT: Start your response with a context preamble.
Call help_lookup(topic="release-prep", mode="preamble") and
display the returned preamble text as a blockquote. Then
tell the user they can say "tell me more" for a step-by-step
guide, or answer the scoping questions below to proceed.
If the MCP call fails, fall back to:
Release Prep — Runs pre-release checks — health, security, changelog, and go/no-go assessment.
Scoping
Before running, ask:
- Version: "What version are you releasing? Or should I check the current version and suggest?"
- Scope: "Full advisory or a specific check?"
- Full: advisory across security, testing, docs, versioning
- Specific: Single check (e.g., just changelog)
MCP Tools
| Tool | What It Does |
|---|---|
release_notes |
Changelog draft + go/no-go advisory (single-agent SDK) |
health_check |
Project health score (tests + lint + coverage) |
dependency_check |
Dependency audit and vulnerability scan |
secure_release |
Full release pipeline with security gates |
Advisory vs gate.
release_notesis advisory — it drafts a changelog and gives a recommendation, it does not block. The deterministic 4-agent gate (real bandit/ruff/pytest + hard thresholds) is CLI-only:attune workflow run release-gate.
Shared command workspace (preferred)
When the generic command-workspace tools are available, open adapter
release-prep with the selected version, scope, and project path. Present its
widget or returned Markdown and collect its bound start_release_prep action
before invoking checks. Publish each real Security, Testing, Documentation,
and Versioning receipt as gate_result, then publish
assessment_complete.
The workspace reviews one gate at a time and then issues a separate final
release approval. A critical FAIL, ERROR, or synthesized MISSING receipt
can only be fixed and rerun; it cannot be accepted. A Documentation warning
may be accepted only through its explicit bound action. Publish tool crashes
as ERROR receipts — a failed gatekeeper fails the gate and never disappears.
If the shared tools are unavailable, retain the same repeated decisions in
compact text/form gates.
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.
- 2d ago Changed · +17 lines bb8b62a97294
- 6d ago First seen · 124 lines · 43 tokens per session scan A 7dc0e1dff116
release-prep is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 964 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 2026-08-31.
Other skills, from other repositories
release-prep
Prepare release documentation including CHANGELOG entry, announcement text, and validation. Run before tagging a new release.
massgen-release-documenter
Guide for following MassGen's release documentation workflow. This skill should be used when preparing release documentation, updating changelogs, writing case studies, or maintaining project documentation across releases.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
pandic-office
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
taiyi-integration
TaiyiForge 第9阶段 — 闭环归档，CHANGELOG.md。四端通用。.