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. [](https://github.com/markoblogo/AGENTS.md_generator/actions/workflows/ci.yml) [](https://github.com/markoblogo/AGENTS.md_generator/actions/workflows/pages/pages-build-deployment) [](https://github.com/markoblogo/AGENTS.md_generator/releases) [](LICENSE) [](pyproject.toml) 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
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.