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/clickhouse/nerve/nerve-devnpx skills add ClickHouse/nerve --skill nerve-devgit clone --depth 1 https://github.com/ClickHouse/nerveWhat 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 | $0.00096 | $0.03184 |
| Opus 5 | $0.00048 | $0.01592 |
| Sonnet 5 | $0.00019 | $0.00637 |
| Haiku 4.5 | $0.00010 | $0.00318 |
Grade A, and why
Nerve Development 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nerve Development Skill
Changing your own config (skills, cron, settings), not the app code? Use the
nerve-workspaceskill instead — that covers the workspace, and which of a pull request or a direct edit applies to this instance. This skill is for developing the Nerve application codebase.
Repository
Nerve lives under the ClickHouse organization on GitHub.
- Upstream:
[email protected]:ClickHouse/nerve.git - Issues & PRs: https://github.com/ClickHouse/nerve
All changes go through PRs — never push directly to main.
Getting Started (Contributors)
# 1. Fork on GitHub, then clone your fork
git clone [email protected]:<your-username>/nerve.git
cd nerve
# 2. Add upstream remote
git remote add upstream [email protected]:ClickHouse/nerve.git
# 3. Set up Python environment (uv sync creates .venv from uv.lock)
uv sync --extra test
source .venv/bin/activate
# 4. Set up frontend
cd web && npm install && cd ..
# 5. Verify
.venv/bin/pytest tests/ -v
cd web && npm run build
Project Layout
nerve/
├── nerve/ # Python backend (FastAPI + Claude Agent SDK)
│ ├── cli.py # Click CLI (start/stop/restart/status/logs/doctor)
│ ├── config.py # YAML config loader
│ ├── db/ # SQLite async database package
│ │ ├── base.py # Database class (connection, _atomic, FTS, mixin composition)
│ │ ├── migrations/ # File-based migration system (numbered .py files + runner.py)
│ │ ├── sessions.py # SessionStore mixin
│ │ ├── messages.py # MessageStore mixin
│ │ ├── tasks.py # TaskStore mixin
│ │ ├── plans.py # PlanStore mixin
│ │ ├── notifications.py # NotificationStore mixin
│ │ ├── sources.py # SourceStore mixin (inbox, sync/consumer cursors)
│ │ ├── cron.py # CronStore mixin
│ │ ├── skills.py # SkillStore mixin
│ │ ├── mcp.py # McpStore mixin
│ │ └── audit.py # AuditStore mixin
│ ├── bootstrap.py # Self-configuring onboarding (personal/worker mode)
│ ├── workspace.py # Workspace directory management
│ ├── agent/ # Agent engine, tools, sessions, streaming
│ ├── gateway/ # FastAPI server, WebSocket, auth
│ │ ├── server.py # App factory, lifespan, WebSocket, static serving
│ │ ├── auth.py # JWT auth, password verification
│ │ └── routes/ # Domain-specific REST API route modules
│ │ ├── __init__.py # register_all_routes() assembler
│ │ ├── _deps.py # RouteDeps container (engine, db, notification_service)
│ │ ├── sessions.py # /api/sessions/*, /api/chat
│ │ ├── tasks.py # /api/tasks/*
│ │ ├── plans.py # /api/plans/*, /api/tasks/{id}/plans
│ │ ├── skills.py # /api/skills/*
│ │ ├── mcp_servers.py # /api/mcp-servers/*
│ │ ├── memory.py # /api/memory/*
│ │ ├── diagnostics.py # /api/diagnostics
│ │ ├── cron.py # /api/cron/*
│ │ ├── sources.py # /api/sources/*
│ │ ├── notifications.py # /api/notifications/*
│ │ └── workflow_runs.py # /api/workflow-runs/*
│ ├── channels/ # Telegram bot, web UI channel adapters
│ ├── cron/ # APScheduler job runner
│ ├── sources/ # Data source adapters (Telegram, Gmail, GitHub)
│ ├── memory/ # Markdown files + memU semantic indexing
│ ├── skills/ # Filesystem-based skill loader
│ ├── tasks/ # Task markdown files + SQLite index
│ ├── notifications/ # Fire-and-forget + async question delivery
│ ├── proxy/ # CLIProxyAPI daemon (Docker/worker mode)
│ ├── workflows/ # Budget-capped workflow runs (workflow_run_* tools)
│ └── templates/ # Mode templates for nerve init (personal/, worker/)
├── web/ # React + TypeScript + Vite frontend
│ ├── src/
│ │ ├── components/ # React components
│ │ ├── pages/ # Route pages (ChatPage.tsx, WorkflowRunsPage.tsx, ...)
│ │ ├── stores/ # Zustand state stores
│ │ │ ├── chatStore.ts # Chat state + thin WS dispatcher
│ │ │ ├── handlers/ # Domain-specific WS message handlers
│ │ │ └── helpers/ # Stateless helpers (block ops, buffer replay)
│ │ ├── api/ # API client utilities
│ │ └── types/ # TypeScript definitions
│ └── package.json
├── tests/ # pytest suite
├── docs/ # Architecture, config, API docs
├── config.yaml # Main config (committed)
├── config.local.yaml # Secrets (gitignored)
└── pyproject.toml # Python project metadata + entry point
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 · 300 lines · 96 tokens per session scan A c60a3e6280e8
Nerve Development is a skill published in the GitHub repository ClickHouse/nerve (78 stars, last pushed 2d ago), licensed Apache-2.0. It adds 96 tokens to every session and 3,184 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
experiment-tracking-swanlab
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.
n8n:create-pr
Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.