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.
git clone --depth 1 https://github.com/bahulneel/agent-brain-trustWrote 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/bahulneel/agent-brain-trust/release)<a href="https://agentmods.dev/commands/bahulneel/agent-brain-trust/release"><img src="https://agentmods.dev/badge/commands/bahulneel/agent-brain-trust/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/bahulneel/agent-brain-trust/release"><img src="https://agentmods.dev/badge/commands/bahulneel/agent-brain-trust/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 | $0.00049 | $0.00513 |
| Opus 5.5 | $0.00020 | $0.00205 |
| Sonnet 5.5 | $0.00010 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00051 |
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 2mo 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.
What it actually says
Relase
Workflow
- Verify the repo is on
developand the worktree is clean. Stop if there are uncommitted changes, missinggit flow, or missinggh. - Find the latest semver tag with
git tag --sort=version:refname. Use the highest tag that looks like0.4.0orv0.4.0. - Inspect commits since that tag with
git log <last-tag>..HEAD --pretty=format:%s%n%b%x00. - Select the version bump from those commits:
majorif any commit subject contains!:or any body containsBREAKING CHANGEminorif any commit subject starts withfeatpatchotherwise
- 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. - Start the release with
git flow release start <next-version>. - Bump versions with
npm version <next-version> --no-git-tag-version --workspaces --include-workspace-root. - Stage the version files and commit them with
chore: update package versions to <next-version> across all modules. - Finish the release with
git flow release finish -m <next-version> <next-version>. - Push the main branch, develop branch, and tags to
origin. Ifgit flow release finishalready pushed them, verify that state instead of duplicating unnecessary pushes. - Create the GitHub release with
gh release create <next-version> --verify-tag --generate-notes --latest --title <next-version>. - 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.
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.
- 2mo ago First seen · 31 lines · 49 tokens per session scan A 0e3dc93bfddd
release is a command published in the GitHub repository bahulneel/agent-brain-trust (5 stars, last pushed 5d ago), licensed MIT. It adds 49 tokens to every session and 513 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
land
Resolve and squash merge one named, currently authorized pull request.
quality
A command for temporarily clearing a release quality gate or one named check, while recording the reason and expiry time. A quality gate is a required check that normally blocks completion or release.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
release-manager
Automated release coordination and deployment with ruv-swarm orchestration for seamless version management, testing, and deployment across multiple packages.
create-pr
Push the current branch and open a pull request into main with a structured description derived from the branch's commits and the open issues it resolves.
release-plan
A release-planning command for a software change. It documents the release scope, rollback plan, gradual or full rollout, and monitoring before waiting for human approval.