Rivet Actors are long-running processes that keep application state in memory while persisting it automatically. They support workloads such as AI agents, user sessions, collaborative applications, and durable multi-step operations with queues, scheduling, and WebSockets. Catalogue add-ons help operate and develop Rivet Actors.
Borrowing it
Nothing to install: this file belongs to rivet-dev/actors. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rivet-dev/actors/main/.claude/commands/release.mdgit clone --depth 1 https://github.com/rivet-dev/actorsWrote 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/commands/rivet-dev/actors/release)<a href="https://agentmods.dev/commands/rivet-dev/actors/release"><img src="https://agentmods.dev/badge/commands/rivet-dev/actors/release/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/commands/rivet-dev/actors/release"><img src="https://agentmods.dev/badge/commands/rivet-dev/actors/release.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 | $0.00000 | $0.01833 |
| Opus 5.5 | $0.00000 | $0.00733 |
| Sonnet 5.5 | $0.00000 | $0.00367 |
| Haiku 4.5 | $0.00000 | $0.00183 |
Grade A, and why
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 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Agent
You are a release agent for the Rivet project. Your job is to cut a new release by running the release script, monitoring the GitHub Actions workflow, and fixing any failures until the release succeeds.
Step 1: Gather Release Information
Ask the user what type of release they want to cut:
- patch - Bug fixes (e.g., 2.1.5 -> 2.1.6)
- minor - New features (e.g., 2.1.5 -> 2.2.0)
- major - Breaking changes (e.g., 2.1.5 -> 3.0.0)
- rc - Release candidate (e.g., 2.1.6-rc.1)
For rc releases, also ask:
- What base version the RC is for (e.g., 2.1.6). If the user doesn't specify, determine it by bumping the patch version from the current version.
- What RC number (e.g., 1, 2, 3). If the user doesn't specify, check existing git tags to auto-determine the next RC number:
git tag -l "v<base_version>-rc.*" | sort -V
If no prior RC tags exist for that base version, use rc.1. Otherwise, increment the highest existing RC number.
The final RC version string is <base_version>-rc.<number> (e.g., 2.1.6-rc.1).
If the user has already provided all these details in their initial message, skip the questions and proceed directly.
Step 2: Confirm Release Details
Before proceeding, display the release details to the user and ask for explicit confirmation:
- Current version (from latest git tag via
git tag -l "v*" | sort -V | tail -1) - New version
- Current branch
- Whether it will be tagged as "latest" (RC releases are never tagged as latest)
Do NOT proceed without user confirmation.
Step 3: Run the Release Script
The release script (scripts/publish/src/local/cut-release.ts) handles version bumping, local checks, committing, pushing, and triggering the publish workflow. It's a linear script with no phases or --only-steps — on failure, fix the issue and re-run, or comment out already-completed steps locally.
For major, minor, or patch releases:
pnpm --filter=publish release --<type> --yes
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 · 181 lines · 0 tokens per session scan A aba61ad95c53
release is a command published in the GitHub repository rivet-dev/actors (6,271 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,833 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 2026-08-30.
Other commands, from other repositories
prepare-release
Release readiness review with project-steward (commits, version sync, changelog, updater).
bump-template-version
Bumps the template repository's own internal version — the version tracked in .template/CHANGELOG-TEMPLATE.md's link footer. This is the SOLE place where the template's version lives, by design — VERSION, CHANGELOG.md, Cargo.toml [workspace.package].version, and the README.md version badge are all kept free of any…
instinct-import
Import a portable YAML instinct pack with confidence-gated merge (Instinct Engine).
acos-checkpoint
Create checkpoints before risky operations. Rollback if things go wrong.
status
Warm mid-session check — git detail, last session note, and in-progress backlog. Use when you still have mental context loaded and want a quick pulse. Not for cold starts (use /tools:brief) or planning (use /tools:overview).
wrap
You are closing a Claude Code session. Execute all steps below in order.