SOC 2 Policies (Policyseed)
Interviews you and writes your 22 SOC 2 policies offline from open-source templates. Same answers, same text, no account.
Free
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsSOC 2 Policies (Policyseed)
Example session with this skill installed
We need SOC 2 policies. We're 8 people on AWS and GitHub, Google Workspace for login, MFA is on.
- Read your context and instructions
- Compiled the soc 2 policies
Summary
After a short interview, the skill wrote intake.yaml and rendered 22 SOC 2 policies into policies/.
Questions it asked first (the ones the prompt didn't answer): company and product name, security owner, policy approver, incident contact, data types, and scope.
Intake (excerpt)
headcount: 1-10
cloud:
- AWS
scm: GitHub
idp: Google Workspace
mfa: true
Command
npx -y policyseed@1 build --intake intake.yaml
Files written
| # | File |
|---|---|
| 01 | information-security-policy.md |
| 02 | acceptable-use-policy.md |
| 03 | access-control-policy.md |
| 04 | authentication-and-password-policy.md |
| 05 | asset-management-policy.md |
| 06 | data-classification-and-handling-policy.md |
| 07 | data-retention-and-disposal-policy.md |
| 08 | encryption-and-key-management-policy.md |
| 09 | change-management-policy.md |
| 10 | secure-software-development-policy.md |
| 11 | vulnerability-and-patch-management-policy.md |
| 12 | logging-and-monitoring-policy.md |
| 13 | incident-response-policy.md |
| 14 | business-continuity-and-disaster-recovery-policy.md |
| 15 | backup-and-recovery-policy.md |
| 16 | vendor-and-third-party-risk-policy.md |
| 17 | risk-assessment-and-management-policy.md |
| 18 | human-resources-security-policy.md |
| 19 | endpoint-and-workstation-security-policy.md |
| 20 | network-and-infrastructure-security-policy.md |
| 21 | physical-and-remote-work-security-policy.md |
| 22 | privacy-and-data-protection-policy.md |
Reply to the user
22 policies are in policies/. Because you're a 1-10 person team, incident response uses small-team targets. Next: read them, change anything that doesn't match how you work, and have the approver sign the Revision History table in each.
Next steps
- Management reviews, edits and approves the set.
- Commit
intake.yamlnext topolicies/and add the weeklyodedmoshe/policyseed@v1check so review dates don't slip.
Connects securely to your tools. The creator never sees your data.
About this skill
This skill turns your agent into a SOC 2 policy writer that doesn't make things up. It asks 23 questions about your company (hosting, identity provider, source control, MFA, team size, data types, owners), writes them to an intake file, and renders 22 policies with the open-source Policyseed templates: information security, access control, incident response, vendor risk, backup, change management and more.
The policy text comes from reviewed templates, not from the model, so the same answers always give the same policies, and the wording follows your answers. If MFA isn't enforced everywhere yet, the policies require a dated rollout plan instead of claiming it's in place. A team of 1-10 people gets incident response targets it can actually meet.
Everything runs locally with npx policyseed (Node 18+) or the Policyseed MCP server. Nothing is uploaded. It can also check whether policies in a repo are overdue for review, and set up a weekly GitHub Action for it.
Policies are a starting point that your management reviews and adopts. The CPA firm performs the SOC 2 examination. Templates: Apache-2.0, https://github.com/odedmoshe/policyseed. Made by the maintainer of policyseed.io.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
Requires
Node.js