picoclaw-agent

picoclaw-agent is a skill for Claude Code, Codex from sipeed/picoclaw. It costs 79 tokens per session (7,143 once invoked), scanned A, original, MIT.

A guide for configuring, extending, debugging, and contributing to PicoClaw, a lightweight personal AI assistant and agent framework with a command line, chat gateway, app connections, scheduled jobs, and installable skills.

In plain words
What is it for?
Use it to set up PicoClaw, sign in to model providers, choose models, run the agent, start its chat gateway, inspect health, and change its routing, sessions, skills, or integrations.
Why use it?
It keeps work aligned with PicoClaw’s actual commands, configuration files, workspace structure, and internal design instead of relying on generic agent instructions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Codex.

Good fit Use it to set up PicoClaw, sign in to model providers, choose models, run the agent, start its chat gateway, inspect health, and change its routing, sessions, skills, or integrations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sipeed/picoclaw/picoclaw-agent
About the project

PicoClaw is a lightweight personal AI assistant written in Go and designed to run on compact, resource-constrained hardware. People use it as a deployable assistant for automating everyday tasks, with development still in an early stage. The catalogue skills extend how coding agents work with PicoClaw.

sipeed/picoclaw · 29,942 stars · on GitHub · picoclaw.io

Install

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.

Any agent
npx skills add sipeed/picoclaw --skill picoclaw-agent
Clone the repo
git clone --depth 1 https://github.com/sipeed/picoclaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for picoclaw-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/sipeed/picoclaw/picoclaw-agent/github.svg)](https://agentmods.dev/skills/sipeed/picoclaw/picoclaw-agent)
Your own site
<a href="https://agentmods.dev/skills/sipeed/picoclaw/picoclaw-agent"><img src="https://agentmods.dev/badge/skills/sipeed/picoclaw/picoclaw-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for picoclaw-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/sipeed/picoclaw/picoclaw-agent"><img src="https://agentmods.dev/badge/skills/sipeed/picoclaw/picoclaw-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,143 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 121
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 122
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Rogue Agent · line 659
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.07143
Opus 5 $0.00039 $0.03571
Sonnet 5 $0.00016 $0.01429
Haiku 4.5 $0.00008 $0.00714

Measured 9d ago against content hash 3972f9ae9036, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

picoclaw-agent 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 9d 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.

workspace/skills/picoclaw-agent/SKILL.md · 874 lines

How it starts

The opening of the file, as written. The whole thing — 874 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PicoClaw Agent

PicoClaw is a lightweight personal AI assistant and agent framework with a native CLI, chat gateway, MCP integration, installable skills, session routing, scheduled jobs, and self-evolution.

Use this skill when the job is about PicoClaw itself: onboarding, configuration, debugging, adding features, extending the CLI, changing routing/session behavior, working on skills or MCP support, or contributing to this repository.

Operating Stance

When this skill is active, stay fully subordinate to PicoClaw's real architecture:

  • Prefer PicoClaw commands, config keys, workspace layout, and docs.
  • Follow PicoClaw source and docs for behavior, naming, and workflows.
  • Treat repository code and checked-in docs as the source of truth.

Quick Start

# Initialize ~/.picoclaw/config.json and ~/.picoclaw/workspace
picoclaw onboard

# Authenticate a provider
picoclaw auth login --provider openai

# Inspect or switch the default model
picoclaw model
picoclaw model my-default-model

# One-shot prompt
picoclaw agent -m "Hello"

# Interactive CLI chat
picoclaw agent

# Start the gateway for chat channels
picoclaw gateway

# Inspect runtime/config health
picoclaw status

# Explore installed skills and MCP servers
picoclaw skills list
picoclaw mcp list

Command Surface

Core CLI

picoclaw onboard
picoclaw agent [-m MESSAGE] [--session KEY] [--model MODEL] [--debug]
picoclaw gateway [--debug] [--no-truncate] [--allow-empty] [--host HOST]
picoclaw status
picoclaw version
picoclaw migrate

Configuration and Models

# Show or change the default configured model alias
picoclaw model
picoclaw model <model_name>

# Add a model from an OpenAI-compatible endpoint
picoclaw model add --api-base URL --api-key KEY
picoclaw model add -b http://localhost:8000/v1 -k dummy -m my-model -n local

# Reset config to factory defaults (preserves sensitive keys)
picoclaw config reset
picoclaw config reset --force

Notes:

  • There is no general picoclaw config edit or picoclaw config set.
  • Advanced edits are usually done by editing ~/.picoclaw/config.json directly.

Read the full file on GitHub · 874 lines

Changes

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.

  1. 9d ago First seen · 874 lines · 79 tokens per session scan A 3972f9ae9036

Subscribe to this mod's changes

picoclaw-agent is a skill published in the GitHub repository sipeed/picoclaw (29,942 stars, last pushed 5d ago), licensed MIT. It adds 79 tokens to every session and 7,143 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens