prepare-release

prepare-release is a skill for Claude Code, Codex from greendwin/mcp-tasker. It costs 0 tokens per session (3,543 once invoked), scanned A, original, MIT.

A release-preparation routine for the mcp-tasker project. It updates the version and project documentation, refreshes dependencies, and runs checks.

In plain words
What is it for?
Preparing major, minor, patch, or explicitly numbered releases and reviewing the resulting file changes.
Why use it?
It organizes the steps needed for a release and stops when a required check fails. It leaves commits, tags, and pushing to the user.

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/greendwin/mcp-tasker/prepare-release
Any agent
npx skills add greendwin/mcp-tasker --skill prepare-release
Clone the repo
git clone --depth 1 https://github.com/greendwin/mcp-tasker

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 prepare-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/greendwin/mcp-tasker/prepare-release.svg)](https://agentmods.dev/skills/greendwin/mcp-tasker/prepare-release)
Your own site
<a href="https://agentmods.dev/skills/greendwin/mcp-tasker/prepare-release"><img src="https://agentmods.dev/badge/skills/greendwin/mcp-tasker/prepare-release.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,543 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 $0.00000 $0.03543
Opus 5 $0.00000 $0.01772
Sonnet 5 $0.00000 $0.00709
Haiku 4.5 $0.00000 $0.00354

Measured 3d ago against content hash ee6c61c5e627, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prepare-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 3d 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.

.claude/skills/prepare-release/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

prepare-release

A tier-1 release skill: mutate files, run checks, print next steps. Never run git commit, git tag, or git push. The user reviews the diff and ships manually.

Optional argument: major, minor, patch, or an explicit X.Y.Z — sets the version directly. If absent, the skill reasons about the bump from commits and picks automatically.


Flow overview

1. Pre-flight checks
2. Detect baseline tag
3. Read commits since baseline
4. Decide version
5. Draft README patch notes + check README & DESIGN.md doc drift
6. Write pyproject.toml, README.md, DESIGN.md
7. uv lock --upgrade
8. uv run tox (with one retry on skill-caused failures)
9. Print final output with suggested git commands

Every step has a stop condition. When a stop condition fires, leave whatever has been written on disk, print why, and exit. Do not attempt to roll back file changes — the user will review via git diff.


1. Pre-flight checks

Before mutating any files, verify the working state.

Check A — tracked-file cleanliness. Run git status --porcelain. If any line starts with M, A, D, R, or C (tracked file modifications), the tree is dirty. Untracked files (??) are ignored.

Check B — on main branch. Run git rev-parse --abbrev-ref HEAD. If not main, stop candidate.

On either failure, prompt the user interactively: show the specific problem (file list for dirty, branch name for wrong branch) and ask Proceed anyway? [y/N]. Default is no. Only proceed on explicit y.

No --force flag. The interactive prompt is the only override path.

2. Detect the baseline tag

The baseline tag defines "previous release" — the point from which commits are diffed.

Algorithm:

  1. Read the current version from pyproject.toml ([project] version = "X.Y.Z").
  2. Look for a tag vX.Y.Z matching that version. If found, that's the baseline.
  3. Otherwise, list all tags matching vX.Y.Z (stable only — exclude anything with a, b, rc suffixes) and find the highest one ≤ the pyproject version. That's the baseline.
  4. If multiple tags could plausibly match, or nothing is resolvable, ask the user which tag to use as baseline. Do not guess.

Read the full file on GitHub · 265 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. 3d ago First seen · 265 lines · 0 tokens per session scan A ee6c61c5e627

Subscribe to this mod's changes

prepare-release is a skill published in the GitHub repository greendwin/mcp-tasker (0 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,543 tokens. 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.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens