agentleFS
os-factoryos-factory/har/control/AGENTS.md

har / control

AGENTS.md133 starsChanged 3 months agoApache-2.0View on GitHub

Next.js App Router dashboard for harness runs, repositories, and agent slots. Part of the har monorepo — this app has its own harness (control/.har/). For work on the CLI, the docs site, or the index of all harnesses in this repo, see the root AGENTS.md. This repository uses a .har/ harness. It is how you run and verify this project — launch a slot for live apps, browsers and screenshots; never hand-roll docker or dev-server startup. If a harness command…

  • Reads credentials

The file

Files
AGENTS.md

HAR Mission Control — Agent Development Guide

Next.js App Router dashboard for harness runs, repositories, and agent slots.

Part of the har monorepo — this app has its own harness (control/.har/). For work on the CLI, the docs site, or the index of all harnesses in this repo, see the root AGENTS.md.

Stack

  • Prisma + SQLite, Zod (@har/schemas)

Layout

src/app/           routes and API handlers
src/components/    UI (shadcn + domain components)
src/server/        business logic
prisma/            schema
<!-- har:agent-environment:start -->

HAR / agent environment

This repository uses a .har/ harness. It is how you run and verify this project — launch a slot for live apps, browsers and screenshots; never hand-roll docker or dev-server startup. If a harness command fails, fix the harness or report it; do not fall back to ad-hoc commands.

  1. Launch first — har_launch_environment / har env launch <id>. Make ALL edits under the returned work dir, never the main checkout. Bind tracker work with --work-id / --work-url when the task names an issue.
  2. Verify before done — har_run_verification (full: true) / har env verify <id> --full. Commit in the session worktree.
  3. Stop at handoff — report summary, session branch and preview URLs, then wait. Never autonomously complete, teardown, push, or open a PR.
  4. All slots taken? Occupied slots always block a launch, and you never free one yourself. Run har env status, then show the user every slot — branch, work unit, what it achieves, last verify, and whether its commits are merged, pushed or unpushed — and recommend which to close: merged or abandoned work with nothing left to do first; never one with unpushed commits. On approval: complete / teardown <id>, then launch.

Customize the harness only through harness.env, stages.json + .har/stages/, .har/hooks/ and .har/plugins/ — there is no generated .har/*.sh entry-point surface.

Full detail — slot environment, readiness, definition of done, project commands, commit gate: .har/README.md and .har/stages.json.

<!-- har:agent-environment:end -->

Project-specific notes

  • Primary app: Next.js Mission Control (HARNESS_PRIMARY_APP=web) on slot ports (slot 1 → 3847).
  • Database: per-slot SQLite prisma/agent_<id>.db — no shared Postgres.
  • Other harnesses: root .har/ (CLI) · docs/.har/ (docs site). See the root AGENTS.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.