release

release is a command for Claude Code from dork-labs/dorkos. It costs 0 tokens per session (11,873 once invoked), scanned A, original, MIT.

A command for preparing and publishing a software release from a project’s changes.

In plain words
What is it for?
The input does not provide enough detail to describe additional jobs safely.
Why use it?
It automates version updates, changelog work, tagging, package publishing, and optional GitHub release creation.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/assert-migrations-current.sh.

Part of the flow plugin — 41 skills, 44 commands, 5 agents, 4 hooks shipped together

Good fit The input does not provide enough detail to describe additional jobs safely.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos
agentmods
npx agentmods add commands/dork-labs/dorkos/release

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 41 skills, 44 commands, 5 agents, 4 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/dork-labs/dorkos/release/github.svg)](https://agentmods.dev/commands/dork-labs/dorkos/release)
Your own site
<a href="https://agentmods.dev/commands/dork-labs/dorkos/release"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/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.

agentmods 80×15 button for release

Your own site · 80×15
<a href="https://agentmods.dev/commands/dork-labs/dorkos/release"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,873 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.11873
Opus 5.5 $0.00000 $0.04749
Sonnet 5.5 $0.00000 $0.02375
Haiku 4.5 $0.00000 $0.01187

Measured today against content hash 6ad8c19da565, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. **The queue stays frozen until npm is curl-verified** (6.10:
.claude/commands/system/release.md · 685 lines

How it starts

The opening of the file, as written. The whole thing — 685 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Release Command

Create a new release: bump the version, update the changelog, run harness maintenance, create a git tag, publish to npm, and optionally create a GitHub Release. Quick pre-flight checks and all user interaction happen in the main context; the context-heavy changelog/commit analysis for auto-detect is delegated to a context-isolator subagent.

Arguments

  • $ARGUMENTS — Optional bump type or explicit version, plus optional flags:
    • (no argument) — Auto-detect version bump from changelog and commits
    • patch / minor / major — Force that bump type
    • X.Y.Z — Explicit version number (e.g., 0.2.0)
    • --dry-run — Show what would happen without making changes

Semantic Versioning

Bump Type When to Use Example
MAJOR Breaking changes to user config or workflows 0.1.0 -> 1.0.0
MINOR New features, backward compatible 0.1.0 -> 0.2.0
PATCH Bug fixes, documentation updates 0.1.0 -> 0.1.1

Phase 1: Parse Arguments

Determine the bump type (patch, minor, major, explicit version, or auto — the default) and whether --dry-run is present.


Phase 2: Pre-flight Checks

# Check 1: Working directory is clean
git status --porcelain

If output is not empty, STOP: report the uncommitted files and tell the user to commit or stash before releasing.

# Check 2: On main branch, up to date with origin
git branch --show-current
git pull --ff-only

If not main, STOP: releases are cut from current main.

Repo reality (learned across v0.59.0–v0.65.0): main is push-protected and merges only through the merge queue, so the release commit CANNOT be pushed directly, and all branch/commit work happens in a dedicated worktree — never by switching the shared main checkout's branch. Phase 6 below is written for that flow: edit → release worktree → PR → queue merges it → tag the MERGED squash SHA → publish npm last. Tagging your local pre-merge commit tags the wrong SHA (squash rewrites it), and pnpm publish before the merge fails pnpm's git-checks (ERR_PNPM_GIT_NOT_LATEST).

Read the full file on GitHub · 685 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. today Changed · +17 lines 6ad8c19da565
  2. yesterday Changed · +22 lines ea65d0c4674c
  3. 4d ago Changed · +2 lines b77c68b4b192
  4. 13d ago Changed · +4 lines 2257f8746abf
  5. 14d ago Changed · +14 lines c45fd42d289d
  6. 24d ago Changed 8ed93abab755
  7. 1mo ago Changed · +16 lines 809b9beeaa94
  8. 1mo ago Changed · +2 lines 62fa006f86bb
  9. 1mo ago Changed · +10 lines 5089913c67c8
  10. 1mo ago First seen · 598 lines · 0 tokens per session scan A 5989eb8e8d01

Subscribe to this mod's changes

release is a command published in the GitHub repository dork-labs/dorkos (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 11,873 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.