dev-rc

dev-rc is a skill for Claude Code from ToruAI/toru-claude-agents. It costs 25 tokens per session (957 once invoked), scanned A, original, MIT.

A final release-check skill for software changes that runs quality checks, security review, final code review, and changelog work before merging. A release candidate is a version considered nearly ready to ship.

In plain words
What is it for?
Use it as the last gate after implementation, especially when preparing a branch for merge and verifying that tests pass, serious security issues are absent, and the change is ready to release.
Why use it?
It catches failed tests, security problems, unmet requirements, and missing release notes before code reaches the main branch. It also checks the branch’s current state and recent validation results.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the toru-claude-agents plugin — 15 skills, 7 agents, 1 MCP server shipped together

Good fit Use it as the last gate after implementation, especially when preparing a branch for merge and verifying that tests pass, serious security issues are absent, and the change is ready to release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/toruai/toru-claude-agents/dev-rc
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.

Any agent
npx skills add ToruAI/toru-claude-agents --skill dev-rc
Clone the repo
git clone --depth 1 https://github.com/ToruAI/toru-claude-agents

Made for: Claude Code.

Or install toru-claude-agents, the plugin that ships this one along with the rest of its 15 skills, 7 agents, 1 MCP server.

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 dev-rc

README.md
[![agentmods](https://agentmods.dev/badge/skills/toruai/toru-claude-agents/dev-rc.svg)](https://agentmods.dev/skills/toruai/toru-claude-agents/dev-rc)
Your own site
<a href="https://agentmods.dev/skills/toruai/toru-claude-agents/dev-rc"><img src="https://agentmods.dev/badge/skills/toruai/toru-claude-agents/dev-rc.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 957 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00025 $0.00957
Opus 5 $0.00013 $0.00478
Sonnet 5 $0.00005 $0.00191
Haiku 4.5 $0.00003 $0.00096

Measured 8d ago against content hash 3a3a7437a3e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dev-rc 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 8d 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.

skills/dev-rc/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev RC - Release Candidate

The final gate. QA passed? Security clean? Ready to ship.

Philosophy

"A release candidate is a promise. Don't make promises you can't keep."

Prerequisites

Before running /dev-rc, you should have:

  • ✓ Code complete
  • ✓ Tests passing (/dev-qa)
  • ✓ Security audit clean (/dev-security)

If not done, we'll run them.

Flow

1. Pre-flight Check

# Current state
git status
git log --oneline -5

# What's the diff from main?
git diff main...HEAD --stat

Show the user:

Release Candidate Check

Branch: {branch}
Commits: {N} ahead of main
Files: {N} changed
Lines: +{added} -{removed}

Proceeding with RC checks...

2. Run QA (if not recent)

Check if QA was run in last hour:

  • If yes: Skip, show previous results
  • If no: Run /dev-qa quick

Must pass to continue.

3. Run Security (if not recent)

Check if security audit was run in last hour:

  • If yes: Skip, show previous results
  • If no: Run /dev-security quick

Must pass (CRITICAL/HIGH = 0) to continue.

4. Final Code Review

Delegate to Garry:

"Garry, final review before release.

This is going to main. Check:
1. All requirements met from the dev-cycle session
2. No debug code left behind
3. No TODO/FIXME that should block release
4. Documentation updated if needed
5. Breaking changes documented

Diff: {git diff main...HEAD}

Give me a go/no-go."

5. Changelog Entry

Ask the user:

Generate changelog entry?

Based on commits:
{git log main...HEAD --oneline}

Options:
1. Yes, generate for me
2. Yes, I'll write it
3. Skip changelog

If generating:

## [Unreleased]

### Added
- {new features from commits}

### Changed
- {modifications from commits}

### Fixed
- {bug fixes from commits}

6. RC Summary

## Release Candidate Summary

### Checks
- QA: ✓ PASSED
- Security: ✓ PASSED
- Review: ✓ APPROVED

### Changes
{git diff main...HEAD --stat summary}

### Commits
{git log main...HEAD --oneline}

### Changelog
{generated or provided entry}

---

RC Status: READY

Next steps:
1. /dev-finish - Commit, PR, close cycle
2. Manual review - Look at the diff yourself
3. Hold - Not ready yet

Read the full file on GitHub · 195 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. 8d ago First seen · 195 lines · 25 tokens per session scan A 3a3a7437a3e9

Subscribe to this mod's changes

dev-rc is a skill published in the GitHub repository ToruAI/toru-claude-agents (15 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 957 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.