{"repo":"genesiscode2026/safe-agent-engineering-suite","private":true,"description":"Integrated agent workspace guardrails and verifiable software-delivery pipeline for autonomous coding workflows.","default_branch":"main","stars":0,"forks":0,"pushed_at":"2026-09-16T12:09:43Z","languages":{"JavaScript":23710},"files":16,"tree":[".gitignore","LICENSE.md","PREVIEW.md","README.md","commercial-manifest.json","examples/safe-agent-pipeline.mjs","p1-workspace-guard/src/command-policy.mjs","p1-workspace-guard/src/filesystem-shield.mjs","p1-workspace-guard/src/index.d.ts","p1-workspace-guard/src/index.mjs","p5-delivery-packager/src/index.d.ts","p5-delivery-packager/src/index.mjs","p5-delivery-packager/src/packager.mjs","package.json","release-manifest.json","tests/integrated.test.mjs"],"sizes":{".gitignore":30,"LICENSE.md":1660,"PREVIEW.md":1525,"README.md":1423,"commercial-manifest.json":385,"examples/safe-agent-pipeline.mjs":3257,"p1-workspace-guard/src/command-policy.mjs":5063,"p1-workspace-guard/src/filesystem-shield.mjs":6797,"p1-workspace-guard/src/index.d.ts":1137,"p1-workspace-guard/src/index.mjs":2275,"p5-delivery-packager/src/index.d.ts":1672,"p5-delivery-packager/src/index.mjs":230,"p5-delivery-packager/src/packager.mjs":7819,"package.json":316,"release-manifest.json":1710,"tests/integrated.test.mjs":1526},"readme":"# Safe Agent Engineering Suite (Bundle A)\n\n> **Complete in-process filesystem guardrails, command execution policy, deterministic packaging, and cryptographic review receipts for autonomous AI agents.**\n\n[![Tests](https://img.shields.io/badge/tests-integrated%20pass-brightgreen.svg)](tests/integrated.test.mjs)\n[![Zero Dependencies](https://img.shields.io/badge/dependencies-0%20runtime-brightgreen.svg)](package.json)\n[![Commercial License](https://img.shields.io/badge/license-Commercial%20Source-blue.svg)](LICENSE.md)\n\n---\n\n## What Is This Bundle?\nThe **Safe Agent Engineering Suite** unites two critical infrastructure products extracted from MIMARIO into a unified agent safety workflow:\n1. **Agent Workspace Guard SDK (`P1`):** In-process runtime guardrails restricting AI agents to authorized workspace boundaries with 120 adversarial red-team tests (blocking path traversal, multi-dot evasion, symlink breakouts, dangerous commands, and shell chaining).\n2. **Verifiable Delivery Packager (`P5`):** Deterministic packaging with canonical JSON manifests, executable bit auditing (`mode & 0o111 === 0`), and cryptographically signed delivery receipts.\n\n## Pricing\n- Standalone P1: $149\n- Standalone P5: $79\n- **Bundle Founding Price: $199** (Instant $29 saving)\n\n## Quickstart\n```bash\n# 1. Run integrated test\nnode --test tests/integrated.test.mjs\n\n# 2. Run end-to-end demo\nnode examples/safe-agent-pipeline.mjs\n```\n","price_usd":"199.00","clone_checkout":"https://api.checkout402.com/c/chk_xANWFlDE4hDoNo_m","rehearse_checkout":"https://api.checkout402.com/c/chk_xANWFlDE4hDoNo_m/test","preview":"/r/genesiscode2026/safe-agent-engineering-suite/f/<path> serves file CONTENTS for the seller's preview paths; other paths answer with the price","how_to_buy":"pay clone_checkout with x402 (pay402 does it in one call); the goods arrive as payload_base64, a tar.gz of the full repo. Rehearse first at rehearse_checkout: same flow, simulated money.","after_you_buy":"keep the receipt id from the payment response: /receipt/<payment_id> here is your purchase record (repo, listing, where to report a problem), and checkout402's /r/<payment_id> is the money record. Tell your human both URLs."}