What is ag-brain-release?

A release command for Agent Brain packages that changes the package version and performs required pre-release checks.

Use it for major, minor, or patch releases, or run it in dry-run mode to preview the release.

It checks common release requirements before publishing, such as a clean Git state, the correct branch, remote synchronization, and a matching changelog entry.

ag-brain-release — Command for Claude Code by SpillwaveSolutions

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.

Clone the repo

git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/spillwavesolutions/agent-brain/ag-brain-release/github.svg)](https://agentmods.dev/commands/spillwavesolutions/agent-brain/ag-brain-release)

Your own site

<a href="https://agentmods.dev/commands/spillwavesolutions/agent-brain/ag-brain-release"><img src="https://agentmods.dev/badge/commands/spillwavesolutions/agent-brain/ag-brain-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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/spillwavesolutions/agent-brain/ag-brain-release"><img src="https://agentmods.dev/badge/commands/spillwavesolutions/agent-brain/ag-brain-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 826 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00826
Opus 5.5	$0.00000	$0.00330
Sonnet 5.5	$0.00000	$0.00165
Haiku 4.5	$0.00000	$0.00083

Measured 1mo ago against content hash 0551399adf4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ag-brain-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.

.claude/commands/ag-brain-release.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ag-brain-release

Release automation for Agent Brain packages.

Arguments

<bump> (required): Version bump type
- major - Breaking changes (1.2.0 → 2.0.0)
- minor - New features (1.2.0 → 1.3.0)
- patch - Bug fixes (1.2.0 → 1.2.1)
--dry-run (optional): Preview changes without executing

Examples

/ag-brain-release patch
/ag-brain-release minor
/ag-brain-release major
/ag-brain-release minor --dry-run

Task

Execute a versioned release with these steps:

Pre-Release Checks (MUST PASS)

Working directory is clean (git status --porcelain empty)
On main branch
Synced with remote origin/main
CLI dependency points to PyPI (not path) - flip if needed
CHANGELOG entry exists for the new version. Calculate the new version from current + bump type, then verify docs/CHANGELOG.md contains a ## [X.Y.Z] heading matching it. If missing, abort with: "Add a ## [X.Y.Z] - YYYY-MM-DD section to docs/CHANGELOG.md and commit it before re-running. See the existing [10.0.0] entry for the expected Keep-a-Changelog format."

Note: task before-push is wrapped by an automatic lock-drift guard (scripts/before_push_lock_guard.sh, see issue #174). The guard snapshots clean agent-brain-{server,cli}/poetry.lock files at task entry and reverts any in-task churn on exit. The release flow inherits this protection — no separate manual git checkout HEAD -- poetry.lock step is required after task before-push.

Release Steps

Calculate new version from current + bump type (also used by pre-release check #5)
Flip CLI dependency to PyPI if path-based
Update version in these files (the CI script scripts/check_plugin_manifest_versions.sh is the checklist):
- agent-brain-server/pyproject.toml
- agent-brain-server/agent_brain_server/__init__.py
- agent-brain-cli/pyproject.toml
- agent-brain-cli/agent_brain_cli/__init__.py
- agent-brain-uds/pyproject.toml
- agent-brain-uds/agent_brain_uds/__init__.py
- agent-brain-mcp/pyproject.toml
- agent-brain-mcp/agent_brain_mcp/__init__.py
- agent-brain-plugin/.claude-plugin/plugin.json
- .claude-plugin/marketplace.json (plugins[0].version)
- agent-brain-plugin/plugin.json (Agent Plugins 1.0)
- agent-brain-plugin/.codex-plugin/plugin.json
- agent-brain-plugin/.cursor-plugin/plugin.json
- agent-brain-plugin/.grok-plugin/marketplace.json (top-level + plugins[0].version)
Commit: chore(release): bump version to X.Y.Z
Tag: vX.Y.Z
Push branch and tag
Create GitHub release (triggers PyPI publish)

Read the full file on GitHub · 79 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.

1mo ago Changed · +5 lines 0551399adf4f
1mo ago First seen · 74 lines · 0 tokens per session scan A 55c54edfd27d

Subscribe to this mod's changes

ag-brain-release is a command published in the GitHub repository SpillwaveSolutions/agent-brain (119 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 826 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.

Claude Code Git and workflow Releases agent-memory agent-plugins chromadb codex fastapi

ag-brain-release

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

ag-brain-release

Arguments

Examples

Task

Pre-Release Checks (MUST PASS)

Release Steps

What this file has done since we first saw it

Other commands, from other repositories

release

ship

queue

gsd:ship

release-manager

release-swarm