A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at any repository.
# Add to your Claude Code skills
git clone https://github.com/VisionForge-OU/foremanforeman is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by VisionForge-OU. A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at any repository. It has 73 GitHub stars.
foreman's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/VisionForge-OU/foreman" and add it to your Claude Code skills directory (see the Installation section above).
foreman is primarily written in Python. It is open-source under VisionForge-OU on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh foreman against similar tools.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at any repository.
plan → ADR/PRD → issues → TDD build → e2e
Why Foreman? · Demo · Quickstart · Guide · How it works · Roadmap · Contributing
"I don't prompt Claude anymore; I have loops that prompt Claude."
Foreman spawns the locally-installed claude CLI in headless stream-json mode,
parses its event stream, enforces budgets, and drives your delivery workflow with
a human-in-the-loop review gate for the design phases and guardrailed autonomy for
the build. All state is human-readable files committed inside the target repo —
no database; kill it and restart and it fully recovers from disk.
Running a coding agent in a while loop is easy. Running one you can trust to
merge is not. Foreman is the supervisor in between: it keeps a human at the design
gates, then hands the build to agents that are boxed in by the orchestrator, not
by their own good behaviour.
plan → ADR/PRD → issues → TDD build → e2e, with human review gates on every design phase and a hash-sealed approval that auto-reverts if a doc changes.claude CLI in stream-json mode, parses its events, and enforces per-run turn/cost/time budgets.touches set so they never collide.PreToolUse deny hook that blocks workers from writing their own verification.foreman retro clusters failures into gated skill/prompt patches that must pass foreman bench before they can land.foreman --demo # launch the full TUI against a throwaway sample repo,
# driven by a mocked agent backend — ZERO tokens spent
foreman demo (non-interactive) and foreman --demo (the live TUI) run the entire
plan → … → e2e pipeline on canned stream-json, so you can explore every gate and
screen before spending a cent.
Dashboard at a glance (illustrative layout — run foreman --demo to see it live):
┌ Foreman ─────────────────────────────────── agentic delivery orchestrator ──┐
│ Features (n) │ daily-plan — phase: building cost: $0.41 ●2 wk │
│ ▸ daily-plan │ Press b to (re)start · w workers · x attention │
│ backlog-aging │ │
│ │ Issue board │
│ Vendored skills │ queued in_progress done merged │
│ ✓ foreman-tdd v4 │ ISS-004 ISS-002 ISS-001 ISS-003 │
│ ✓ foreman-grill… v3 │ ISS-005 │
│ Read-only agents │ │
│ ✓ foreman-evaluator │ [ global activity log … ] │
├─────────────────────────┴────────────────────────────────────────────────┤
│ ⠹ ACTIVE ISS-002 worker · turn 12/30 · $0.18 · running pytest │
│ n New p Plan g Grill s Slice c Confirm b Build v Review w Workers … │
└────────────────────────────────────────────────────────────────────────────┘
# 1. Install (exposes a single `foreman` command)
pipx install . # or: uv tool install .
# 2. Point it at any repo
cd /path/to/your/repo
foreman init # scaffolds .foreman/ and installs the foreman-* skills
# into .claude/skills/
# 3. See the whole thing work end-to-end with NO tokens spent
foreman demo # runs the full pipeline against a throwaway sample repo
# using a mocked agent backend (canned stream-json)
# 4. Launch the TUI for real work
foreman # (same as `foreman tui`)
foreman --demo # launch the TUI against a throwaway sample repo
foreman status # show vendored-skill + agent status + features for the repo
foreman init --force # re-create config and reinstall the foreman-* skills/agents
foreman build # resume/continue the autonomous build of a feature
foreman retro # cluster recurring failures → gated skill/prompt patch drafts
foreman bench # replay the eval set; report success-rate/cost/turn deltas
foreman --version
claude CLI installed and authenticated (claude --version)gitForeman is fully keyboard-driven. Launch it with foreman (or foreman --demo
to try it with a mocked backend and zero token spend). Every screen also shows its
keys in the footer; the reference below is the complete map.
You spend almost all of your time on the Dashboard. It lists your features on the left, shows the selected feature's current phase + cost + a live issue board on the right, and tells you the single next key to press in its hint line. The other screens (Review, Workers, Attention, Metrics, Retro, Settings) are pushed on top with a single key and dismissed with Esc.
A feature moves through phases; the Dashboard hint tells you what to press at each:
| Phase | Hint shown | You press |
|---|---|---|
request |
Run the planner | p |
plan_review |
Review the plan (a=approve, r=request changes) | v |
grilling |
Run the grill (ADR + PRD) | g |
doc_review |
Review ADR / PRD | v |
slicing |
Run the slicer | s |
queue_review |
Confirm the queue, then build | c then b |
building |
(Re)start the build · workers · attention | b · w · x |
done |
Feature complete 🎉 — see report.md |
— |
The home screen. Select a feature with the arrow keys, then act on it.
| Key | Action |
|---|---|
| ↑ / ↓ | Select a feature in the list |
| n | New feature (opens the create modal) |
| p | Run the planner → plan.md |
| g | Run the grill → ADR + PRD |
| s | Run the slicer → issue files |
| c | Confirm the queue (final gate before build) |
| b | Start / resume the build loop |
| v | Open the Review screen (plan / ADR / PRD) |
| w | Open the Worker view (live agent logs) |
| x | Open the Attention queue (escalations) |
| m | Open the Metrics pane |
| t | Open the Retro patch gate |
| , | Open Settings (read-only config view) |
| q | Quit |
A small form: type a title, Tab into the request box (description
request.md and selects the new feature.Where you approve or push back on the plan, adr, and prd drafts. The top of
the screen surfaces the grill's "decisions made on your behalf" digest and any
open questions; the body renders the document; a comment box at the bottom is
used as your answers to those open questions.
| Key | Action |
|---|---|
| a | Approve the current doc |
| r | **Request chang |