What is draft-release?

A release-drafting workflow for preparing a new software release. A release is a published version of a project, usually accompanied by notes describing its changes.

Use it to compare changes since the previous version, write release notes with changes and contributors, update the project version, run checks, and create a release branch.

It organizes the checks, version updates, release notes, commit, and push needed before publishing a release.

draft-release — Skill by dyoshikawa

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/dyoshikawa/rulesync/draft-release

Any agent

npx skills add dyoshikawa/rulesync --skill draft-release

Clone the repo

git clone --depth 1 https://github.com/dyoshikawa/rulesync

Made for: Claude Code, Codex.

Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 566 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.

Model	Per session	Once invoked
Fable 5	$0.00011	$0.00566
Opus 5	$0.00005	$0.00283
Sonnet 5	$0.00002	$0.00113
Haiku 4.5	$0.00001	$0.00057

Measured 2d ago against content hash 621580bab37d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft-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 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.

.rulesync/skills/draft-release/SKILL.md · 34 lines

What it actually says

First, let's work on the following steps.

Confirm that you are currently on the main branch and pull the latest changes. If not on main branch, switch to main branch.
Compare code changes between the previous version tag and the latest commit to prepare the release description.

Write in English.
Do not include confidential information.
Sections, What's Changed, Contributors and Full Changelog are needed.
./tmp/release-notes/*.md will be used as the release notes.

Then, from $ARGUMENTS, get the new version without v prefix, and assign it to $new_version. For example, if $ARGUMENTS is "v1.0.0", the new version is "1.0.0".

If $ARGUMENTS is empty, determine the new version automatically by performing the release-dry-run skill.

Let's resume the release process.

Run git pull.
Run git checkout -b release/v${new_version}.
Update getVersion() function to return the ${new_version} in src/cli/index.ts, and run pnpm cicheck. If the checks fail, fix the code until pass. Then, execute git add, git commit and git push.
Update the version with pnpm version ${new_version} --no-git-tag-version.
Since package.json will be modified, execute git commit and git push.
As a precaution, verify that getVersion() in src/cli/index.ts is updated to the ${new_version}.
Run gh pr create to the main branch.
Create a draft release using gh release create v${new_version} --draft --title v${new_version} --notes-file ./tmp/release-notes/*.md command on the github.com/dyoshikawa/rulesync repository. This creates a draft release so that the publish-assets workflow can upload assets later.

Note: the Homebrew tap formula (Formula/rulesync.rb) is NOT updated here. It embeds sha256 checksums of the release binaries, which only exist after the release PR merges and the Publish Assets workflow uploads them. The goal-release skill performs that update as its post-merge step (regenerate with scripts/generate-homebrew-formula.ts from the release's SHA256SUMS and land it via an immediately merged PR). When releasing manually without the goal-release skill, run that step yourself after the assets are published.

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.

2d ago First seen · 34 lines · 11 tokens per session scan A 621580bab37d

Subscribe to this mod's changes

draft-release is a skill published in the GitHub repository dyoshikawa/rulesync (1,362 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 566 once invoked, about $0.0001 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.

Data and AI Git and workflow LLM Productivity ai ai-agents ai-coding mcp rules

deep-clean

Full-spectrum consolidation of AI agent configuration files. Goes beyond memory-only dream skills: audits and optimizes context files (AGENTS.md/AGENTS.md/GEMINI.md/.cursorrules), rules, skills, and memory. Detects stale references, dead file paths, duplicated rules, stack mismatches, contradictions, vague directives…

opencue/cuecards · 87 tokens

turborepo

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines…

Bosh-Kuo/awesome-agent-toolkit · 111 tokens

skill-creator-openai

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Bosh-Kuo/awesome-agent-toolkit · 48 tokens

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…

Bosh-Kuo/awesome-agent-toolkit · 90 tokens

skill-creator-anthropic

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.