release-dry-run

release-dry-run is a skill for Claude Code, Codex from dyoshikawa/rulesync. It costs 20 tokens per session (602 once invoked), scanned A, original, MIT.

A release dry run that reviews changes since the latest version tag and suggests a semantic-version increase. Semantic versioning uses major, minor, and patch numbers to communicate the size of a release.

In plain words
What is it for?
For listing commits and changed files, grouping changes, spotting breaking changes, and proposing the next version level.
Why use it?
It lets a team inspect a possible release before changing version numbers or publishing anything.

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/dyoshikawa/rulesync/release-dry-run
Any agent
npx skills add dyoshikawa/rulesync --skill release-dry-run
Clone the repo
git clone --depth 1 https://github.com/dyoshikawa/rulesync

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 release-dry-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/dyoshikawa/rulesync/release-dry-run.svg)](https://agentmods.dev/skills/dyoshikawa/rulesync/release-dry-run)
Your own site
<a href="https://agentmods.dev/skills/dyoshikawa/rulesync/release-dry-run"><img src="https://agentmods.dev/badge/skills/dyoshikawa/rulesync/release-dry-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 602 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 $0.00020 $0.00602
Opus 5 $0.00010 $0.00301
Sonnet 5 $0.00004 $0.00120
Haiku 4.5 $0.00002 $0.00060

Measured 4d ago against content hash c48929602f54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release-dry-run 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 4d 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/release-dry-run/SKILL.md · 70 lines

What it actually says

This is a dry run command for release. It will summarize the changes since the last release and suggest the appropriate version bump based on semantic versioning.

Steps

  1. Get the latest release tag.

    • Run git fetch --tags to ensure all tags are available.
    • Run git describe --tags --abbrev=0 to get the latest tag.
    • Assign the result to $latest_tag.
  2. Compare code changes between the latest tag and the current HEAD.

    • Run git log ${latest_tag}..HEAD --oneline to get the commit list.
    • Run git diff ${latest_tag}..HEAD --stat to get the file change statistics.
  3. Analyze the changes and create a summary in the following format:

    ## Changes Summary
    
    ### Commits since ${latest_tag}
    - List of commits with their messages
    
    ### Changed Files
    - Summary of file changes (added, modified, deleted)
    
    ### Change Categories
    - **Breaking Changes**: List any breaking changes (API changes, removed features, etc.)
    - **New Features**: List new features added
    - **Bug Fixes**: List bug fixes
    - **Other Changes**: List other changes (refactoring, documentation, tests, etc.)
    
  4. Based on the analysis, suggest the appropriate version bump following semantic versioning rules:

    • MAJOR (X.0.0): Breaking changes that are not backward compatible
      • Removed or renamed public APIs
      • Changed behavior of existing features
      • Dropped support for older Node.js versions
    • MINOR (x.Y.0): New features that are backward compatible
      • New CLI commands or options
      • New configuration options
      • New tool support
    • PATCH (x.y.Z): Bug fixes and minor improvements
      • Bug fixes
      • Documentation updates
      • Internal refactoring without API changes
      • Dependency updates (unless they cause breaking changes)

    Important: Whenever the changes include any feature removal or a change in the behavior of an existing feature, do not hesitate to choose a MAJOR version bump. Prioritize protecting users from unexpected breakage over keeping the version number low.

  5. Output the final recommendation in the following format:

    ## Version Bump Recommendation
    
    Current version: ${latest_tag}
    Recommended bump: MAJOR / MINOR / PATCH
    Suggested new version: vX.Y.Z
    
    ### Reasoning
    - Explain why this version bump is recommended based on the changes.
    

Note: This is a dry run only. No files will be modified and no commits will be made.

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. 4d ago First seen · 70 lines · 20 tokens per session scan A c48929602f54

Subscribe to this mod's changes

release-dry-run is a skill published in the GitHub repository dyoshikawa/rulesync (1,379 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 602 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.

Related

Other skills, from other repositories

snip

You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.

edouard-claude/snip · 0 tokens

opensrc

Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…

vercel-labs/opensrc · 103 tokens

building-agents

Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…

ericrisco/rsc-harness · 85 tokens

agent-eval

Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…

ericrisco/rsc-harness · 79 tokens

linked-intent-dev

Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…

jszmajda/lid · 87 tokens

update-lid

Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…

jszmajda/lid · 105 tokens