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/swoelffel/claw-pilot/overviewgit clone --depth 1 https://github.com/swoelffel/claw-pilotWrote 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/agents/swoelffel/claw-pilot/overview)<a href="https://agentmods.dev/agents/swoelffel/claw-pilot/overview"><img src="https://agentmods.dev/badge/agents/swoelffel/claw-pilot/overview.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 | $0.00000 | $0.01106 |
| Opus 5 | $0.00000 | $0.00553 |
| Sonnet 5 | $0.00000 | $0.00221 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
overview 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 4d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Concepts Overview
An agent is an AI entity within a ClawPilot instance, defined by its model, tools, persistence mode, archetype, and workspace files. This document covers all key agent properties and concepts.
What Is an Agent
Each agent is a configured AI persona that lives inside an instance. An instance can host multiple agents with different roles. Agents can communicate with each other, share workspace files, and be targeted by specific channels.
Agent Properties
| Property | Description | Values |
|---|---|---|
id |
Unique identifier within the instance | kebab-case (e.g. code-reviewer) |
name |
Display name | Free text |
model |
Primary AI model | e.g. claude-sonnet-4-20250514 |
fallbackModels |
Ordered list of fallback models | Used if primary model is unavailable |
toolProfile |
Which tools the agent can access | minimal, messaging, coding, full, pilot |
persistence |
Session lifetime | permanent or ephemeral |
archetype |
Behavioral archetype | orchestrator, generator, analyst, planner, coder |
promptMode |
How much context is injected | full or minimal |
kind |
Agent visibility | primary or system |
isDefault |
Receives unaddressed messages | true or false |
Tool Profiles
Tool profiles control what capabilities an agent has access to:
| Profile | Description | Example Use |
|---|---|---|
minimal |
Basic text generation only | Simple Q&A agent |
messaging |
Can send messages to other agents and channels | Coordinator agent |
coding |
File read/write, shell commands, git operations | Developer agent |
full |
All available tools including web search, MCP | Research agent |
pilot |
Full tools plus instance management capabilities | System-pilot, admin agents |
Persistence Modes
| Mode | Behavior |
|---|---|
permanent |
Shared conversation session across all channels. History persists between interactions. Agent remembers previous conversations. |
ephemeral |
Task-scoped session. Each new task or conversation starts fresh. No memory of prior interactions. |
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.
- 4d ago First seen · 100 lines · 0 tokens per session scan A c214013e79c8
overview is an agent published in the GitHub repository swoelffel/claw-pilot (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,106 tokens. 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 agents, from other repositories
Explore
Fast read-only codebase & docs exploration. Returns structured findings, never raw file dumps.
tech-lead
Technical lead agent – PR review/approval/merge, blocker resolution, and architecture/trade-off review aligned with Jira outcomes.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
DocScribe
Write docs/ prose for a completed change, in caveman style, per the repo's Documentation Update Protocol. Use after a change lands to update docs/architecture.md, docs/ .md, README, or docs/AGENTS.md — the Rule-6 delegation target (main agent must NOT edit docs/ directly). Self-contained — give it the diff + target…
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
nodejs-expert
Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.