Safe-by-default CLI that generates and updates AGENTS.md / RUNBOOK.md for AI coding agents using marker-based patches, diff-first workflow, and conservative repo auto-detect.

AGENTS.md Generator (agentsgen)

Safe repo docs + PR Guard + AI docs bundle for coding agents.

Landing: https://agentsmd.abvx.xyz/ Manifest: https://github.com/markoblogo/AGENTS.md_generator/blob/main/docs/manifest.md ID integration: https://github.com/markoblogo/ID/blob/main/docs/AGENTSGEN_INTEGRATION.md Listed on ABVX Lab: https://lab.abvx.xyz/ Orchestrated with SET: https://github.com/markoblogo/SET Human context with ID: https://github.com/markoblogo/ID

agentsgen is the repo-intelligence runtime in the ABVX ecosystem: use it directly in a repo, or call it through SET when you want one thin orchestration entrypoint. Pair it with ID when you also need portable human-AI context and repo-local integration hooks across tools: agentsgen pack now emits a repo-local handoff manifest at docs/ai/id-context.json for that bridge. ID remains the human/profile layer: https://github.com/markoblogo/ID

Small, production-grade CLI to generate and safely update:

• AGENTS.md (strict repo contract for coding agents)
• RUNBOOK.md (human-friendly command/run cheatsheet)
• proof-loop task artifacts under docs/ai/tasks/

References

• https://arxiv.org/abs/2602.11988
• https://arxiv.org/abs/2602.20478

Safety Model

The tool is safe-by