Dev & Engineering multi-agent-orchestrationtmuxautomated-bug-fixingbest-practicespython-313git-workflow

Claude Code Agent Farm

Orchestrate 20+ parallel Claude Code agents in tmux to systematically fix bugs and implement best practices, with lock-based coordination preventing conflicts.

FollowAgents review · FARS-2.1
Use with care
60/ 100 5-point scale 3.0 / 5
1 2 3 4 5 6
1Trust14 / 29 · 2.4/5

Least privilege: the default cc alias is `claude --dangerously-skip-permissions`; 20–50 agents run with all permission checks skipped and auto-invoke tools — a destructive default directly contrary to least privilege (scored 0). User confirmation: tool setup scripts claim ask-before-install and double-Ctrl+C force-kill exists, but no per-action confirmation during core runs (1). Data flow: monitoring dashboard, monitor state JSON, and a detailed two-script architecture are documented (2). Sensitive data: only settings. backup/corruption checks are mentioned; no privacy or API-key handling guidance (1). Dependency security: only typer and rich as core deps with version floors; small surface but no lockfile or audit evidence (2). External effects: automatic git commit/push to origin, with toggles like --skip-commit (2). Rollback: settings backup/restore with rotation plus git commit trail (2). Attribution: named author, email, repo links (2).

2Reliability8 / 14 · 2.9/5

Self-consistency: README contradictions — prompt inventory says 37 prompts in one place and '36 available' in another; license badge misrepresents the non-standard rider (1). Dependency availability: minimal core deps with floors, but hard reliance on external claude/tmux/uv, mitigated by doctor checks (2). Failure messages: doctor pre-flight, usage-limit detection, and max_errors thresholds are described, though code-level evidence is not in the provided files (2).

3Adaptability14 / 18 · 3.9/5

Audience/scenarios: 34 stacks, three workflows, 24 setup scripts — exceptionally well scoped (3). Capability boundaries: honestly documents degraded/inert monitoring with non-Claude CLIs (2). Trigger precision: CLI flags map to config keys with stated defaults (2). Environment fit: POSIX Linux, Python 3.13+, tmux explicitly required; macOS/Windows unsupported per classifier (2).

4Convention11 / 18 · 3.1/5

Information architecture: README well sectioned but extremely long and the supplied text is truncated (2). Install notes: setup.sh, doctor, and completion install form a complete path (3). Naming stability: package, command, and session names consistent throughout (2). Examples/FAQ: many config and command examples; no FAQ or troubleshooting section (2). Known limitations: candid caveats for alternate CLIs; other risks (cost, git contention) thinly covered (2). License: LICENSE is modified MIT with an OpenAI/Anthropic restrictive rider, not OSI-compatible; pyproject claims plain MIT and registry metadata is NOASSERTION — three-way inconsistency (1). Versioning: only 1.0.0 and a Beta classifier, no CHANGELOG (1). Maintenance: named author and Issues link, but no governance or response commitments (2).

5Effectiveness9 / 13 · 3.5/5

Output usability: HTML run reports, rich diff summaries, progress documents, and a monitoring dashboard are described (2). Marginal value: one-command orchestration of parallel Claude Code agents with lock coordination and tmux monitoring fills a genuine niche (3). Cost benefit: defaults of 20 agents (up to 50) on token-billed LLM CLIs with almost no cost guidance or budget controls in the README (1).

6Verifiability4 / 8 · 2.5/5

Claim traceability: most claims point to concrete files/commands (setup.sh, view_agents.sh, configs/*.) (2). Cross-source corroboration: README vs pyproject license conflict, internal prompt-count contradiction, and unverifiable 34-stack/31-guide lists within the supplied evidence (1). Fact/inference separation: the caveats section distinguishes confirmed behavior from expected degradation (2).

Evidence confidence: Low Reviewed Sep 10, 2026 Reviewed revision 892e19b08e9d
Safety controls not found in source: least-privilege scoping
Before you use it
  • The setup requires --dangerously-skip-permissions by default: 20–50 agents can modify, commit, and push your codebase with no per-action confirmation. Never run it against production repos or repos containing sensitive config without isolation.
  • The license is not standard MIT: it carries a restrictive rider against OpenAI/Anthropic and their affiliates (no provision, hosting, benchmarking, or training use). Legal review is required before enterprise adoption; pyproject's MIT claim conflicts with the actual LICENSE.
  • Automatic git push to origin can publish unreviewed agent-generated code to shared remotes; use --skip-commit or a dedicated review branch.
  • Very high runtime cost: 20 parallel LLM agents with auto-restart by default and almost no cost guidance in the README; pilot small and set usage limits first.
  • The coordination system is prompt-driven rather than code-enforced (the README states it is implemented entirely in the prompt file); its lock/conflict-prevention reliability is unverified without execution.
Review evidence [1][2][3]
See the full review method →

What does this agent do, and when should you use it?

Claude Code Agent Farm is a multi-agent orchestration framework written in Python 3.13 that runs up to 50 Claude Code agents in parallel (20 by default) inside a tmux session. The main script, claude_code_agent_farm.py, generates problem lists, launches agents in individual panes, monitors their health via heartbeat files and context-percentage parsing, and auto-restarts them on failure; the companion view_agents.sh script offers grid, focus, and split tmux viewing modes. It supports three workflows — bug fixing, best practices implementation, and cooperating multi-agent development — backed by 34 preconfigured tech-stack configs, 37 prompt templates, and 35 best practices guides. The cooperating workflow is implemented entirely through prompts: agents claim work via a JSON registry and lock files under a /coordination/ directory to avoid file conflicts. Runs produce HTML reports, and ~/.claude/settings. is automatically backed up and restored to guard against corruption.

End-to-end flow: 1) Runs the type-check, lint, and test commands defined in the config's problem_commands (e.g., cargo check, bun run type-check) to generate a combined problems file; 2) Launches agents one by one (staggered, default 10s) into a tmux session named claude_agents, each pane running Claude Code via the cc alias; 3) Agents pick random problem chunks (chunk_size dynamically adjusted) or work through best-practices guides in chunks, marking completed items [COMPLETED] to prevent duplication; 4) The Python orchestrator continuously monitors via heartbeat files (.heartbeats/agent*.heartbeat), context-percentage parsing, and tmux pane titles, auto-clearing context below a threshold (default 20%) and restarting errored or stalled agents (heartbeat stale >2 minutes) with exponential backoff; 5) Changes are git-committed (with --commit-every N for incremental commits), and Ctrl+R broadcasts /clear to all agents; 6) Each run ends with an agent_farm_report_*.html report, and monitor state is written to .claude_agent_farm_state. for external tools. In cooperating mode, agents coordinate via active_work_registry., planned_work_queue., and agent_locks/ lock files under /coordination/.

  1. Teams maintaining large Next.js or Python/FastAPI codebases that want to burn down a backlog of type-checker and linter errors in parallel
  2. Engineering teams on legacy-style codebases who want systematic modernization driven by the 35 best practices guides, with progress documents persisting across runs
  3. Advanced users running large-scale refactoring, type-hint coverage, or multi-faceted performance work on one codebase, suited to the cooperating-agents lock-based workflow
  4. Teams wanting automated cleanup on niche stacks like Solana, Unreal Engine, or Kubernetes AI inference, choosing from 34 preconfigured configs or writing custom JSON
  5. Ops engineers running unattended in CI/CD, using --no-monitor mode to launch agents headlessly

What are this agent's strengths and limitations?

Pros
  • Lock files and [COMPLETED] markers solve the core parallel-conflict problem, letting 20+ agents work the same codebase without stepping on each other
  • Mature context management: auto-clear below threshold, one-key Ctrl+R broadcast of /clear, adaptive idle timeout (3× median cycle time) and exponential-backoff restarts
  • 34 preconfigured tech stacks plus custom JSON configs, with 37 prompt templates and 35 best practices guides ready out of the box
  • Strong operability: doctor pre-flight checks, settings backup/rotation/restore, HTML run reports, and an externally readable state file
  • The cc alias can point at any interactive coding CLI (OpenCode, Codex CLI); the orchestrator does not hardcode the claude binary
Limitations
  • Monitoring is deeply Claude Code-specific: readiness detection (the 'Welcome to Claude Code!' banner), context-percentage parsing, /clear resets, and usage-limit detection degrade or go inert with other CLIs
  • Requires running with --dangerously-skip-permissions; agents can directly modify your codebase and execute commands, so the security risk must be self-assessed
  • Each agent consumes ~500MB RAM, and 20+ parallel agents impose real hardware and API-quota costs
  • Requires Python 3.13+ with a heavy runtime dependency set (tmux, uv, direnv, project toolchains), making environment setup nontrivial
  • The cooperating-agents workflow is primarily designed around Python FastAPI/Postgres; other stacks require designing your own prompts
  • GitHub shows license NOASSERTION; the actual license is MIT plus an OpenAI/Anthropic rider that should be reviewed before commercial use

How do you install or deploy this agent?

Prerequisites: Python 3.13+ (managed by uv), tmux, an installed and configured Claude Code (claude command), git, your project's tools (e.g., Bun, mypy, ruff), and optionally direnv.

git clone https://github.com/Dicklesworthstone/claude_code_agent_farm.git
cd claude_code_agent_farm
chmod +x setup.sh
./setup.sh

setup.sh creates a Python 3.13 virtualenv, installs dependencies, configures the cc alias (alias cc="ENABLE_BACKGROUND_TASKS=1 claude --dangerously-skip-permissions"), and sets up direnv. Verify with claude-code-agent-farm doctor --path /path/to/project.

How do you use this agent?

Bug fixing: claude-code-agent-farm --path /path/to/project --config configs/nextjs_config.
Best practices: copy the guide first (cp best_practices_guides/NEXTJS15_BEST_PRACTICES.md /path/to/project/best_practices_guides/), then run claude-code-agent-farm --path /path/to/project --config configs/nextjs_best_practices_config.

Cooperating agents: claude-code-agent-farm --path /project --prompt-file prompts/cooperating_agents_improvement_prompt_for_python_fastapi_postgres.txt --agents 5
Quick test run (5 agents, skip git): claude-code-agent-farm --path /project -n 5 --skip-regenerate --skip-commit

Headless: add --no-monitor --auto-restart. Start with 5-10 agents first; each agent uses ~500MB RAM and the default cap is 50. CLI flags (--agents, --chunk-size, --context-threshold, --commit-every) override the JSON config.

FAQ

Must I use Claude Code, or can I use other coding CLIs?
The orchestrator launches any interactive coding CLI via the cc alias, e.g., OpenCode (npx -y opencode-ai@latest) or OpenAI Codex CLI (npx -y @openai/codex). However, readiness detection, context management, auto-restart, and health checks all assume Claude Code and will be degraded or inert with other CLIs. npx startup latency also multiplies per agent pane; prefer a pinned global install.
What are the cost and resource requirements?
Each agent uses ~500MB RAM; the default is 20 agents with a cap of 50 (configurable via max_agents). All agents continuously call the LLM API, so token consumption scales with agent count and run duration. Start with 5-10 agents to test.
Will agents conflict or duplicate each other's work?
The bug-fixing workflow marks problems [COMPLETED] in the shared problems file to avoid duplication; the cooperating workflow uses a work registry, lock files, and a completed-work log under /coordination/, with locks stale after 2 hours automatically handled, enabling 20+ agents to work in parallel without conflicts.
What happens if Claude settings get corrupted?
Settings are automatically backed up before startup to .claude_agent_farm_backups/ in your project, keeping the last 10 with a 200MB total limit; corruption is detected and restored automatically. Use --full-backup for a comprehensive backup or restore manually from the backup directory.
How do I run it headlessly or in CI?
Use --no-monitor to launch agents and exit without the dashboard, combined with --auto-restart and --skip-commit to build automated code-improvement pipelines. External tools can track progress by reading .claude_agent_farm_state..

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related agents