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 skills/spillwavesolutions/agent-brain/installing-localnpx skills add SpillwaveSolutions/agent-brain --skill installing-localgit 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 | $0.00000 | $0.03678 |
| Opus 5 | $0.00000 | $0.01839 |
| Sonnet 5 | $0.00000 | $0.00736 |
| Haiku 4.5 | $0.00000 | $0.00368 |
Grade D, and why
installing-local scanned grade D with 3 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
echo "Plugin version: $(grep version ~/.claude/plugins/agent-brain/.claude-plugin/plugin.json 2>/dev/null || echo 'N/A')" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.local/share/uv/tools/agent-brain-cli ~/.local/share/uv/tools/agent-brain-server Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "$ACTUAL_URL/index/jobs" | head -20 How it starts
The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Install Skill
Builds and installs Agent Brain CLI/Server locally for rapid development and testing.
When to Use
- After making code changes to agent-brain-server or agent-brain-cli
- When you need to test the plugin in another Claude instance
- When setting up a fresh development environment
- When the user says "local install", "install locally", "build and install", or "deploy for testing"
Prerequisites
uvinstalled (brew install uvorpip install uv)poetryinstalled for building packages- Python 3.11 available (required for chromadb compatibility - 3.12+ fails)
Execution Steps
Step 0: Full Reset (before fresh plugin tests)
Use this when you need a truly clean environment (no cached wheels, no stale plugins, no lingering state).
Use the dedicated removal script:
# Standard removal (kills servers, uninstalls tools, clears caches, removes plugin)
.claude/skills/installing-local/remove.sh
# With PyPI dependency restoration
.claude/skills/installing-local/remove.sh --restore-pypi
# Zero-state cleanup (also removes ~/.claude/agent-brain and ./.claude/agent-brain)
.claude/skills/installing-local/remove.sh --restore-pypi --zero-state
Or use the /ag-remove-local-install command which runs this script.
# Stop any running servers
pkill -9 -f "agent_brain_server" 2>/dev/null || true
pkill -9 -f "uvicorn" 2>/dev/null || true
for p in $(seq 8000 8010); do kill -9 "$(lsof -i :$p -t 2>/dev/null)" 2>/dev/null || true; done
# Remove tool installs and caches
uv tool uninstall agent-brain-cli agent-brain-server 2>/dev/null || true
pipx uninstall agent-brain-cli 2>/dev/null || true
pipx uninstall agent-brain-server 2>/dev/null || true
rm -rf ~/.local/share/uv/tools/agent-brain-cli ~/.local/share/uv/tools/agent-brain-server
rm -rf ~/.cache/uv ~/.cache/pip
# Clear plugin caches/deploys
rm -rf ~/.claude/plugins/cache/agent-brain-marketplace ~/.claude/plugins/agent-brain
# Optional: wipe runtime/state for a zero-carryover test (back up first if needed)
# rm -rf ~/.claude/agent-brain ./.claude/agent-brain
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 416 lines · 0 tokens per session scan D bcb3cf08bc21
installing-local is a skill published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,678 tokens. A static security scan graded it D with 3 findings (reads agent configuration directories, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…