by VKirill
Multi-agent AI coding factory for one person — Claude Code PM + Codex/Qwen/Grok/Kimi/AGY writers, durable conveyor, auto-merge to main
# Add to your Claude Code skills
git clone https://github.com/VKirill/claude-lane-stackGuides for using ai agents skills like claude-lane-stack.
Last scanned: 7/18/2026
{
"issues": [
{
"file": "skills/claude-code/SKILL.md",
"line": 76,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://claude.ai/install.sh | bash\"",
"severity": "medium"
},
{
"file": "skills/claude-code/SKILL.md",
"line": 94,
"type": "dangerous-command",
"message": "Dangerous command (writes to Claude config): \">.md` (project) or `~/.claude/\"",
"severity": "medium"
},
{
"file": "skills/claude-code/SKILL.md",
"line": 82,
"type": "dangerous-command",
"message": "Dangerous command (disables permission prompts): \"bypassPermissions\"",
"severity": "medium"
}
],
"status": "PASSED",
"scannedAt": "2026-07-18T06:04:03.821Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}claude-lane-stack is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by VKirill. Multi-agent AI coding factory for one person — Claude Code PM + Codex/Qwen/Grok/Kimi/AGY writers, durable conveyor, auto-merge to main. It has 112 GitHub stars.
Yes. claude-lane-stack passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/VKirill/claude-lane-stack" and add it to your Claude Code skills directory (see the Installation section above).
claude-lane-stack is primarily written in Python. It is open-source under VKirill 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 claude-lane-stack against similar tools.
No comments yet. Be the first to share your thoughts!
One human. One AI project manager. Real CLI coding agents on a durable conveyor.
Talk to Claude Code — it runs Codex / Qwen / Grok / Kimi / AGY, checks work, merges to main, reviews at night.
| 🏭 Factory, not five chats | 🛡️ Owned paths | 🌙 Night review | 📦 Auto-merge to main |
| One PM holds context | Writers stay in their lane | Independent Codex Sol rail | You never merge by hand |
Working with AI coding tools usually means: five windows, copy-paste, midnight merges, and zero review discipline.
Claude Lane Stack turns that into a conveyor — plain files + git, no mandatory cloud DB.
| 😩 Typical AI coding | ✨ Lane Stack |
|---|---|
| Re-explain context every chat | One PM holds the plan |
| Models overwrite each other | owns_paths on every task |
| Nobody reviews the AI | Typed night shift (review → fix → re-review) |
| You merge branches | PM merges main after checks |
| “What were we doing?” | resume-project → Now / Blocked / Next |
| Jobs die at ~2 min Bash | Detached processes (survive chat close) |
[!TIP] New here? Start with the Beginner guide — zero jargon, factory metaphors.
This is not “one model does everything.”
The stack is a control plane that runs real CLI coding agents as durable processes.
| CLI | Required? | Role |
|---|---|---|
| Claude Code | Yes | PM (dev-orchestrator), watchers, chat with you |
| OpenAI Codex CLI | Optional | Day writer · night Sol review · onboard · docs · emergency |
| Qwen Code | Optional | Daytime durable writer |
| Grok (xAI CLI) | Optional | Daytime durable writer |
| Kimi CLI | Optional | Daytime durable writer (often full-profile default) |
| AGY (Gemini-oriented) | Optional | Daytime durable writer |
You ──chat──► Claude Code · dev-orchestrator ← always
│
run-supervisor + run-controller
┌─────┬─────┬─────┬─────┐
▼ ▼ ▼ ▼ ▼
Codex Qwen Grok Kimi AGY
│ │ │ │ │
└─────┴─────┴─────┴─────┘
│
owns → L1 verify → acceptance → main
agents-doctor / adoc builds the profileacceptance.json, progressive acceptmain_write in adoc (e.g. codex → qwen)| Profile | Writers | Review |
|---|---|---|
claude-only |
Claude only | light |
claude-codex |
Codex process | Codex Sol night |
claude-qwen / grok / kimi / agy |
that CLI | as configured |
full |
multi-writer ready | Codex night |
You (chat) → PM (dev-orchestrator)
│ plan-critique · task YAML in .agents/runs/
▼
run-supervisor ← Claude watches one run
│
▼
run-controller ← durable OS process
│
▼
writer CLI process ← codex / qwen / grok / …
│
▼
owns → L1 tests → acceptance.json
│
▼
PM merges → main → (night) Codex review
You don’t hand-launch “Qwen the coder” for normal work.
You talk to the PM. The PM starts the conveyor. The writer is a background process, not a random brand-named subagent.
| Day | Night | |
|---|---|---|
| Goal | Ship fast | Independent quality |
| Product code | Writer from adoc | Repair after findings |
| Watch | run-supervisor |
night-shift |
| LLM review every commit? | No | Yes — Codex Sol |
| Done | acceptance.json + main |
Finding fixed + re-review |
| Role | Kind | Does |
|---|---|---|
| You | Human | Say what you want |
dev-orchestrator |
Claude agent (PM) | Plan · dispatch · merge · chat |
run-supervisor |
Claude (watch) | One run until accepted/blocked |
run-controller |
OS process | DAG · retry · owns/verify/accept |
| Writer process | CLI (Codex/Qwen/…) | Implements the task card |
lane-supervisor |
Claude (1 action) | Typed lane-ctl recovery |
emergency-writer |
Claude → Codex | After terminal block only |
night-reviewer / night-shift |
Codex Sol | Night review + findings |
project-onboarder |
Codex | Project passport |
docs-maintainer |
Codex | Docs refresh |
Built-ins Claude may also use: Explore, Plan, general-purpose (research / side tasks — not the daytime product conveyor).
Aliases: codex-implementer → emergency-writer, etc. → agents/claude/README.md
Every unit of work lives under .agents/runs/<slug>/tasks/*.yaml:
| Field | Meaning |
|---|---|
owns_paths |
Files this task may touch |
verification[] |
Focused L1 checks |
lane: |
Matches adoc main_write |
| Receipts | report → owns → verify → acceptance.json |
[!IMPORTANT] No
acceptance.json→ not done. Chat green ≠ shipped.
git clone https://github.com/VKirill/claude-lane-stack.git
cd claude-lane-stack && git checkout v1.14.16 # or: main
./install.sh
export PATH="$HOME/.agents/bin:$PATH"
Needs: Claude Code · Git · Python 3 (+ PyYAML/jsonschema) · Node · rsync · flock
Optional: Codex · Qwen · Grok · Kimi · AGY · Linux: bubblewrap
cd /path/to/your-project
agents-doctor --apply . # or: adoc
# if you use the host launcher:
cc # menu → 1 = dev-orchestrator
# or raw:
claude --agent dev-orchestrator --name lane-pm-myproject
| In chat | When |
|---|---|
/project-onboard |
First time on a repo |
/resume-project |
After a break |
| “Add dark mode to settings” | Normal feature work |
| Knob | Meaning |
|---|---|
Writer main_write |
codex / qwen / grok / kimi / agy |
| Model / effort | e.g. Codex luna + max |
| Fast mode | Codex service_tier: fast |
| Workspace | in_place · worktree · auto |
| Plan critique | off · structural · LLM before dispatch |
| Command | Purpose |
|---|---|
agents-doctor / adoc |
Detect CLIs · write profile |
resume-project . |
Now / Blocked / Next |
run-init · run-validate · run-board |
Runs (usually via PM) |
run-controller start|watch|status |
Durable lifecycle |
lane-ctl … |
Typed control plane |
night-shift · night-shift-all |
Night review/repair |
plan-critique --run-dir … |
Plan quality gate |
No. Claude Code alone works (claude-only). Each extra CLI is a pluggable writer (or Codex review rail).
A built-in Claude Code subagent for multi-step side tasks (docs). PM may use it for research. Product features still go through the conveyor.
Claude Code host limit. Write