← Back to Skills Marketplace
155
Downloads
0
Stars
0
Active Installs
7
Versions
Install in OpenClaw
/install founderclaw
Description
FounderClaw — Multi-agent engineering team for OpenClaw. 29 skills, 6 agents (CEO + 5 departments), structured workspace, auto mode, vision sub-agent routing...
README (SKILL.md)
FounderClaw
Multi-agent engineering team for OpenClaw. 29 skills. 6 agents. One install.
IMPORTANT: Post-Install Setup Required
After installing this package (via ClawHub or git clone), you MUST run the installer to:
- Symlink individual skills to
~/.agents/skills/ - Create the workspace at
~/.openclaw/founderclaw/ - Apply multi-agent config (6 agents)
- Build the headless browser
Run from this directory:
bash install.sh
This is REQUIRED. Without it, only the package directory exists — skills won't be discovered by OpenClaw.
What FounderClaw Adds
Agents:
| Agent | Role |
|---|---|
| CEO (🎯) | Orchestrates everything |
| Strategy (📐) | Product thinking & design |
| Shipper (🚀) | Code review & deploy |
| Tester (🔍) | QA & browser testing |
| Safety (🛡️) | Security & guardrails |
| Observer (📊) | Debug & retrospectives |
Skills (29): Strategy: office-hours, plan-ceo-review, plan-eng-review, plan-design-review, design-consultation, design-review, design-shotgun, autoplan Shipping: review, ship, land-and-deploy, canary, benchmark, document-release Testing: qa, qa-only, browse, setup-browser-cookies, connect-chrome Safety: cso, careful, freeze, guard, unfreeze Debugging: investigate, retro, codex Setup: gstack-upgrade, setup-deploy, install-founderclaw, founderclaw-status
Links
- GitHub: https://github.com/ashish797/FounderClaw
- Landing: https://founderclaw.hashqy.com
License
MIT
Usage Guidance
Before installing or running anything from this package: 1) Inspect install.sh and uninstall.sh (don't run curl | bash without reviewing). 2) Review the install steps that will symlink into ~/.agents/skills/, create ~/.openclaw/founderclaw/, and modify OpenClaw config — back up current config first. 3) Audit the Chrome extension files and browse daemon code if you care about browser privacy: the tool reads Chromium cookie DBs and uses Keychain/secret stores to decrypt cookies (you will see OS prompts). 4) If you don't want proactive/autonomous behavior, avoid enabling 'proactive' features and consider disabling autonomous model invocation for this skill or only using user-invoked flows. 5) Only provide any LLM API keys (Anthropic, etc.) if you understand which tests or features require them. 6) If you are unsure, run the package in an isolated environment (VM or throwaway account) first and verify what install.sh does. These patterns can be legitimate for a browser-driven QA/agent system, but they carry sensitive side effects and merit manual review.
Capability Analysis
Type: OpenClaw Skill
Name: founderclaw
Version: 2.1.0
FounderClaw is a comprehensive multi-agent engineering system for OpenClaw that provides a persistent browser daemon, automated QA, security auditing, and design tools. The bundle includes a Playwright-based browser manager (browse/src/browser-manager.ts), a cookie import utility for authenticated testing (browse/src/cookie-import-browser.ts), and an installer (install.sh) that configures a multi-agent workspace. While the system possesses high-privilege capabilities such as reading local browser cookies and modifying OpenClaw configurations, these are documented features aligned with its purpose. The code implements security best practices, including bearer token authentication for the local daemon and redaction of sensitive data in activity logs (browse/src/activity.ts). No evidence of malicious intent, unauthorized data exfiltration, or hidden backdoors was found.
Capability Assessment
Purpose & Capability
The name/description (FounderClaw: multi-agent engineering team with a headless browser) lines up with the files and instructions: a browse daemon, 29 skills, install scripts, a Chrome extension, and many SKILL.md workflow docs. Access to local browser cookies, a local HTTP daemon, and symlinking skills into ~/.agents/skills/ are coherent with the described functionality.
Instruction Scope
Runtime instructions require running install.sh (symlinks skills, creates ~/.openclaw/founderclaw, builds the browser binary) and the README suggests a curl|bash install option. The SKILL.md and docs explicitly describe reading Chromium cookie DBs and invoking Keychain prompts for decryption — which is consistent with a browser-testing tool but is sensitive. The package also includes a proactive suggestion system (auto-suggesting skills) and language indicating injection of ETHOS into skill preambles; these behaviors broaden what the agent will do and merit review. No instructions (in metadata) declare external endpoints beyond localhost, but the repo contains code for a Chrome extension and tests that may call LLM APIs if configured.
Install Mechanism
There is no formal install spec in registry metadata, but the package includes install.sh, build scripts, and compiled-binary build instructions. README suggests a remote curl|bash install from GitHub which is high risk unless you trust the source and inspect the script. The repo contains many executables and a browser daemon; installing without reviewing install.sh/uninstall.sh and the extension source could write files, modify config, and register services.
Credentials
Registry metadata declares no required env vars or credentials. However, docs reference optional development/test flows that need ANTHROPIC_API_KEY and other model config; tests and LLM-eval tooling will require API keys if you run them. The code legitimately needs access to local browser cookie DBs and Keychain (decryption) for the browse skill — this is proportionate to the browse capability but sensitive. No unrelated cloud credentials are requested in metadata.
Persistence & Privilege
always:false (no forced presence). The installer intends to symlink skills into ~/.agents/skills/ and create ~/.openclaw/founderclaw/ workspace — this is expected for a multi-skill system but does grant persistent local footprint and will modify your OpenClaw configuration per README. The skill can run autonomously (model invocation not disabled) which is platform default; combine this with the proactive suggestion behavior if you want to limit autonomous actions.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install founderclaw - After installation, invoke the skill by name or use
/founderclaw - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.1.0
Improved install: interactive model selection, platform detection, channel setup, natural agent personalities.
v2.0.1
fix: SKILL.md instructs agent to run install.sh after package install
v2.0.0
v2.0: Clean publish, no fork. Multi-agent engineering team for OpenClaw.
v1.1.0
Security cleanup: removed test files, build scripts. Reduced from 301 to 215 files. Remaining patterns are all legitimate (headless browser, design tool API calls).
v1.0.2
Restored design tool with clean auth.ts. Full capability restored.
v1.0.1
Security cleanup: removed telemetry, API key refs, prompt injection patterns. Reduced suspicious patterns from 69 to 8 (all legitimate).
v1.0.0
Initial release: 29 skills, 6 agents, multi-agent engineering team for OpenClaw.
Metadata
Frequently Asked Questions
What is FounderClaw?
FounderClaw — Multi-agent engineering team for OpenClaw. 29 skills, 6 agents (CEO + 5 departments), structured workspace, auto mode, vision sub-agent routing... It is an AI Agent Skill for Claude Code / OpenClaw, with 155 downloads so far.
How do I install FounderClaw?
Run "/install founderclaw" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is FounderClaw free?
Yes, FounderClaw is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does FounderClaw support?
FounderClaw is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created FounderClaw?
It is built and maintained by ashish797 (@ashish797); the current version is v2.1.0.
More Skills