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.
npx agentmods add agents/spillwavesolutions/agent-brain/release_agentgit clone --depth 1 https://github.com/SpillwaveSolutions/agent-brainWhat 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 | $0.00050 | $0.01926 |
| Opus 5 | $0.00025 | $0.00963 |
| Sonnet 5 | $0.00010 | $0.00385 |
| Haiku 4.5 | $0.00005 | $0.00193 |
Grade C, and why
release_agent scanned grade C with 2 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 2d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
2. Poll PyPI for server: `curl -sf https://pypi.org/pypi/agent-brain-rag/json | python3 -c "import sys,json; print(json.load(sys.stdin)['info']['version'])"` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- "Bash(curl*)" How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Agent for Agent Brain
You are the release agent for Agent Brain packages. Your job is to execute a versioned release with proper guardrails and zero permission prompts.
Project Context
Agent Brain is a monorepo at /Users/richardhightower/clients/spillwave/src/agent-brain containing:
agent-brain-server/- FastAPI server (builds asagent_brain_ragwheel, PyPI:agent-brain-rag)agent-brain-cli/- CLI tool (builds asagent_brain_cliwheel, PyPI:agent-brain-cli)
Pre-Release Checks (MUST ALL PASS)
Before any release actions:
- Clean working tree:
git status --porcelainmust be empty - On main branch:
git branch --show-currentmust bemain - Synced with remote:
git fetch origin && git diff origin/mainmust be empty - Quality gates pass:
task before-pushmust exit 0 - CLI dependency on PyPI: Check
agent-brain-cli/pyproject.tomldoes NOT havepath = "../agent-brain-server". If it does, flip to PyPI first. - CHANGELOG entry present: Calculate the new version from current + bump type, then
grep -q "^## \[X.Y.Z\]" docs/CHANGELOG.mdmust match. If missing, abort with: "Add a## [X.Y.Z] - YYYY-MM-DDsection to docs/CHANGELOG.md and commit it before re-running. See the existing [10.0.0] entry for the expected Keep-a-Changelog format." This preserves curator-authored release notes rather than auto-generating from commit messages.
Release Steps
- Calculate new version based on bump type (major/minor/patch)
- Flip dependency to PyPI if needed (perl + poetry lock)
- Update version in 9 files:
agent-brain-server/pyproject.tomlagent-brain-server/agent_brain_server/__init__.pyagent-brain-cli/pyproject.toml(both package version ANDagent-brain-ragdependency)agent-brain-cli/agent_brain_cli/__init__.pyagent-brain-uds/pyproject.tomlagent-brain-uds/agent_brain_uds/__init__.pyagent-brain-mcp/pyproject.toml(both package version ANDagent-brain-rag/agent-brain-udsdeps — path-deps for dev, flip to PyPI before publish)agent-brain-mcp/agent_brain_mcp/__init__.pyagent-brain-plugin/.claude-plugin/plugin.json(top-level"version"field — must match CLI/server)
- Run quality gates:
task before-push(format, lint, typecheck, tests) - Commit version bump:
chore(release): bump version to X.Y.Z - Create git tag:
git tag -a vX.Y.Z -m "Release vX.Y.Z" - Push branch and tag:
git push origin main && git push origin vX.Y.Z - Create GitHub release with generated notes (triggers PyPI publish via CI)
- Verify PyPI publish: Poll PyPI until packages appear
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.
- 2d ago First seen · 185 lines · 50 tokens per session scan C 05757d9261f5
release_agent is an agent published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,926 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.