Nerve is a self-hosted runtime for AI agents built around the Claude Agent SDK, providing persistent memory, scheduled execution, task management, skills, and communication channels. It supports personal assistants for individuals and autonomous workers for tasks such as CI monitoring, pull request review, and flaky-test fixes. The catalogue skills extend its agent workflows.
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-workspacenpx skills add ClickHouse/nerve --skill nerve-workspacegit clone --depth 1 https://github.com/ClickHouse/nerveWrote 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/skills/clickhouse/nerve/nerve-workspace)<a href="https://agentmods.dev/skills/clickhouse/nerve/nerve-workspace"><img src="https://agentmods.dev/badge/skills/clickhouse/nerve/nerve-workspace.svg" alt="Measured on agentmods" 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 | $0.00117 | $0.01995 |
| Opus 5 | $0.00059 | $0.00997 |
| Sonnet 5 | $0.00023 | $0.00399 |
| Haiku 4.5 | $0.00012 | $0.00199 |
Grade A, and why
Nerve Workspace Config 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 5d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing Your Own Configuration
Your configuration lives in the workspace. It contains:
config/settings.yaml— shareable settingsconfig/cron/jobs.yaml,config/cron/system.yaml,config/cron/gates/— cronskills/<id>/SKILL.md— skillsSOUL.md,IDENTITY.md,USER.md,AGENTS.md,TOOLS.md— your standing instructions
This is not the Nerve application source code (that's the nerve-dev skill).
First: is this workspace shared?
The answer decides how you change config, so establish it before you start.
The workspace may be a git repository synced from a shared remote (a config repo), in which case config is something a human reviews and merges, and your job is to propose rather than to edit. It may equally be a plain local directory that belongs to this instance alone — that is what an ordinary install looks like.
- Locked instance (lockdown / remote-only) — a PR is the only thing that works. Direct edits to tracked config are blocked, and would be overwritten by the next sync even if they weren't.
- Workspace has a remote, not locked — route every change to the reviewed
surface through
propose_config_change, even though nothing forces you to. A direct write leaves the workspace diverged from the reviewed revision, and sync refuses to merge while anything in that surface —config/,skills/, and the root instruction files — has uncommitted local state (untracked, modified, staged or deleted). So the edit also stops every later config change from reaching this instance until someone commits or drops it.propose_config_changestages in an isolated worktree, so it leaves the live workspace clean — only a direct write dirties it. That covers every route that writes those files, not just an editor:skill_createandskill_update, thePOST/PUT/DELETE /api/skillsendpoints, and a shell command. - No remote, not locked — there is nothing to open a PR against and no
review to route through. Edit the files directly and tell the user what you
changed.
propose_config_changewill refuse, and it is right to.
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.
- 5d ago First seen · 169 lines · 117 tokens per session scan A 56499ced8f58
Nerve Workspace Config is a skill published in the GitHub repository ClickHouse/nerve (78 stars, last pushed yesterday), licensed Apache-2.0. It adds 117 tokens to every session and 1,995 once invoked, about $0.0006 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.
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.
n8n:reproduce-bug
Reproduce a bug from a Linear ticket with a failing test. Expects the full ticket context (title, description, comments) to be provided as input.