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.
npx skills add ToruAI/toru-claude-agents --skill dev-rcgit clone --depth 1 https://github.com/ToruAI/toru-claude-agentsWrote 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/toruai/toru-claude-agents/dev-rc)<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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00957 |
| Opus 5.5 | $0.00010 | $0.00383 |
| Sonnet 5.5 | $0.00005 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
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 1mo 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 — 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
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.
- 1mo ago First seen · 195 lines · 25 tokens per session scan A 3a3a7437a3e9
dev-rc is a skill published in the GitHub repository ToruAI/toru-claude-agents (15 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 957 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
ln-62-release-publisher
Prepares and publishes an explicitly requested tagged GitHub release; does not deploy applications.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
babysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.