squadra
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
No outside reports on file
Using Squadra safely depends on keeping your local machine secure, limiting which projects share the dashboard, and reviewing all automated suggestions before accepting them.
Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachFetches arbitrary web URLsREVIEW
- CredentialsNo API token requiredLOW
- Package sourceGitHub (dagoSte/squadra)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/dagoSte/squadra ↗
About Squadra
Squadra helps you coordinate work across multiple AI coding assistants (Claude, Codex, Cursor) by sharing tasks and tracking progress in a shared dashboard. It includes features like skill recall, code simplification, work forecasting, and verification tools that aim to keep different AI windows working together safely.
Who it’s for
Developers or teams using multiple AI coding assistants who want to coordinate them on the same projects. People interested in organizing AI-assisted work with built-in safety checks and audit trails.
Alternatives
- LangChain agents: Open-source framework for coordinating multiple AI models with defined tools and oversight
- Anthropic Workbench: Built-in Claude features for managing conversations and Claude Desktop integrations
- Custom MCP implementations: Create your own model control protocol setups for specific multi-AI workflows
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/dagoSte/squadra (opens external site) for installation and configuration instructions, as the setup process may vary depending on your AI assistant setup.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 970
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Multiple AI window access: The tool coordinates several AI assistants simultaneously, so compromising one assistant or the shared dashboard could expose work across all connected windows
- Shared task data: Tasks, decisions, and evidence stored in the local dashboard could contain sensitive code, prompts, or project details if not properly secured
- Skill recall and automation: Built-in skills that recall lessons and simplify code automatically might apply unsafe patterns or outdated fixes without human review
- File and browser integration: The tool can browse skills and security audits, meaning malicious web pages or crafted audit files could trick the AI into unsafe actions
- Local dashboard security: A bilingual local dashboard storing all progress and decisions is only as secure as your machine and local file permissions
How to lower the risk
Least-privilege permissions
- Only connect AI assistants that need to see the specific project
- Restrict dashboard access to your user account only
Network isolation
- Keep the local dashboard offline or on a trusted network
- Review MCP plugins before installing them
Monitoring
- Check the audit trail regularly for unexpected decisions or actions
- Watch for tasks assigned to the wrong assistant or unusual skill recalls
Red flags to watch for
- Automated simplifications that remove safety checks or validation
- Dashboard data syncing to cloud services you didn't authorize
- Skills or audits from untrusted sources being loaded automatically
Questions
How do I install Squadra?
Squadra does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/dagoSte/squadra.
Are there security reports about Squadra?
No reports found for this package in our research (last checked 2026-10-29). Squadra currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include multiple ai window access, shared task data, skill recall and automation.
Is Squadra actively maintained?
Squadra has 970 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/dagoSte/squadra before pinning it in production.
What are alternatives to Squadra?
Notable alternatives to Squadra include LangChain agents (Open-source framework for coordinating multiple AI models with defined tools and oversight), Anthropic Workbench (Built-in Claude features for managing conversations and Claude Desktop integrations), Custom MCP implementations (Create your own model control protocol setups for specific multi-AI workflows). You can also compare Squadra side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Squadra? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/dagoste-squadra)HTML embed:
<a href="https://agentarmorhq.com/skills/dagoste-squadra"><img src="https://agentarmorhq.com/api/badge/dagoste-squadra" alt="AgentArmorHQ Risk Grade for Squadra" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "dagoste-squadra"Share with your security lead
Need sign-off to use squadra? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: squadra
- **Listing URL:** https://agentarmorhq.com/skills/dagoste-squadra
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 970 GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Fetches arbitrary web URLs
- **Credentials:** No API token required
- **Package source:** GitHub (dagoSte/squadra)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/dagoSte/squadra
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- dagoSte
- Source code
- github.com/dagoSte/squadra
- Est. context load
- ~113 tokens idle · ~500 tokens when active (on-demand skill)
- Popularity
- 970 GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-27
Community
Discussions for Squadra
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude