release

release is a command for Cursor from bahulneel/agent-brain-trust. It costs 49 tokens per session (513 once invoked), scanned A, original, MIT.

A command workflow for creating a Git Flow release, a structured way to prepare a software version from the develop branch. It infers the version change from commit messages, updates workspace versions, pushes the release, and publishes a GitHub release.

In plain words
What is it for?
Use it to check release prerequisites, choose a major, minor, or patch version, update package versions, finish the Git Flow release, push branches and tags, and publish the GitHub release.
Why use it?
It removes repetitive release steps and applies the repository's versioning and branch rules consistently.

Command for Cursor

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 commands/bahulneel/agent-brain-trust/release
Clone the repo
git clone --depth 1 https://github.com/bahulneel/agent-brain-trust

Made for: Cursor.

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/bahulneel/agent-brain-trust/release.svg)](https://agentmods.dev/commands/bahulneel/agent-brain-trust/release)
Your own site
<a href="https://agentmods.dev/commands/bahulneel/agent-brain-trust/release"><img src="https://agentmods.dev/badge/commands/bahulneel/agent-brain-trust/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 513 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 5.1 $0.00049 $0.00513
Opus 5 $0.00024 $0.00257
Sonnet 5 $0.00010 $0.00103
Haiku 4.5 $0.00005 $0.00051

Measured 5d ago against content hash 0e3dc93bfddd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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 5d 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.

.cursor/commands/release.md · 31 lines

What it actually says

Relase

Workflow

  1. Verify the repo is on develop and the worktree is clean. Stop if there are uncommitted changes, missing git flow, or missing gh.
  2. Find the latest semver tag with git tag --sort=version:refname. Use the highest tag that looks like 0.4.0 or v0.4.0.
  3. Inspect commits since that tag with git log <last-tag>..HEAD --pretty=format:%s%n%b%x00.
  4. Select the version bump from those commits:
    • major if any commit subject contains !: or any body contains BREAKING CHANGE
    • minor if any commit subject starts with feat
    • patch otherwise
  5. Read the current version from the root package.json, compute the next semver version, and keep the repo's plain numeric tag style unless the latest tag clearly establishes a different convention.
  6. Start the release with git flow release start <next-version>.
  7. Bump versions with npm version <next-version> --no-git-tag-version --workspaces --include-workspace-root.
  8. Stage the version files and commit them with chore: update package versions to <next-version> across all modules.
  9. Finish the release with git flow release finish -m <next-version> <next-version>.
  10. Push the main branch, develop branch, and tags to origin. If git flow release finish already pushed them, verify that state instead of duplicating unnecessary pushes.
  11. Create the GitHub release with gh release create <next-version> --verify-tag --generate-notes --latest --title <next-version>.
  12. Report the last tag inspected, the chosen bump, the new version, and the GitHub release URL.

Notes

  • For a preview-only request, gather the last tag, commit range, and computed next version, then stop before git flow release start.
  • Stop on any dirty worktree, branch mismatch, or missing git flow / gh.
  • Do not force-push or bypass failures.
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. 5d ago First seen · 31 lines · 49 tokens per session scan A 0e3dc93bfddd

Subscribe to this mod's changes

release is a command published in the GitHub repository bahulneel/agent-brain-trust (5 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 513 once invoked, about $0.0002 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 2026-08-31.