little-loops 1.103.0

Development workflow toolkit for Claude Code with issue management, code quality commands, and automated processing

little-loops

The toolkit for long-horizon, eval-gated AI software development. Built as a Claude Code plugin.

Today's agents do small tasks well and ship features poorly. little-loops removes that ceiling with three things they're missing: durability (the run outlives the session), consistency (the toolbelt is the process), and verification (the harness is the spec).

Stop babysitting chats. Start shipping features.

1. Chat sessions are holding you back. Run asynchronous agents until done — scale without limits.

The unit of work is the feature, the sprint, or the overnight optimization — not a single chat. Runs survive terminal close, context exhaustion, and laptop sleep. Parallel sprints fan out across isolated worktrees and complete independently of your terminal.

• ll-parallel — kick off N concurrent feature implementations in isolated worktrees. Walk away. They converge without you.
• --background + ll-loop resume — runs survive terminal close, sleep, and reboot. Resume picks up exactly where it stopped, mid-trajectory.
• harness-optimize — score-gated overnight optimization runs. Accept-or-revert each mutation. If interrupted, resume to the highest-scoring commit.
• Session handoff — a fresh context picks up mid-issue without losing the thread. Context limits stop being a planning constraint.

Ship features, not sessions.

2. Smart tools create smart processes.

Raw agents re-derive the same structural moves differently each run. The ll- CLI removes the improvisation surface: context gathering, issue lifecycle, sprint moves, and worktree setup all run as typed commands. Two runs of the same feature land in the same shape — by construction, not by prompting.

• 27 typed CLI tools (ll-issues, ll-sprint, ll-loop, ll-parallel, ll-action, etc.) — structural work runs as commands, not improvised tool calls
• /ll:manage-issue — composes the CLIs into a fixed plan → implement → verify → complete sequence. The agent reasons inside steps, not about which steps to take
• Skill harnesses (/ll:ready-issue, /ll:wire-issue, /ll:confidence-check) — same inputs, same gates, same outputs
• Worktree setup, branch naming, issue ID generation — mechanical operations that produce identical structure across runs

Same feature, same shape, every run.

3. Harness-driven development is awesome. And hard. Auto-generate autonomous harnesses and let your agents go anywhere.

Harness-driven development is TDD's analog for agent-built software: define what "working" looks like first, then iterate until the harness passes. little-loops grades, writes, and improves the harness for you — removing the engineering tax that keeps most teams skipping evals entirely.

The harness grades:

• Six layered gate types — exit code, deterministic external state, full agentic user simulation, LLM-as-judge, diff size invariant, no-op detection
• Cheapest gates run first. Failures route back to execution rather than advancing
• Stall detection catches the "already done" no-op that silently burns through iteration budgets

The harness writes itself:

• /ll:create-eval-from-issues — turn an issue's acceptance criteria into a runnable harness in under a minute
• /ll:create-loop — auto-derive the full harness from your project config
• Annotated templates and ll-loop validate — dry-run the FSM before paying for a real run

The harness improves itself:

• harness-optimize — hill-climbing on harness artifacts. One targeted edit per iteration, benchmark, accept on rising score, revert otherwise
• APO loop category with five prompt-optimization strategies — point it at a prompt, converge to a target score
• /ll:audit-loop-run — four-valued verdict (met / phantom / partial / degraded) catches failure modes humans miss

Point at context. Get a harness.

---

Install

Prerequisites: Claude Code + Python 3.11+

# Add the GitHub repository as a marketplace
/plugin marketplace add BrennonTWilliams/little-loops

# Install the plugin
/plugin install ll@little-loops

# Install CLI tools (for ll-parallel, ll-loop, ll-auto, etc.)
pip install little-loops

Using Codex CLI? See docs/codex/getting-started.md — run /ll:init --codex and ll-adapt-skills-for-codex --apply to get started.

Alternative install methods

From local path (development):

/plugin marketplace add /path/to/little-loops
/plugin install ll@little-loops

Manual configuration — add to .claude/settings.local.json:

{
  "extraKnownMarketplaces": {
    "local": {
      "source": {
        "source": "directory",
        "path": "/path/to/little-loops"
      }
    }
  },
  "enabledPlugins": {
    "ll@local": true
  }
}

---

First 60 seconds

Four ways to feel the difference, top to bottom:

Scan and triage a codebase

/ll:init                  # Auto-detect project type, generate config
/ll:scan-codebase         # Find issues (technical)
/ll:prioritize-issues     # Auto-assign P0–P5 priorities
/ll:map-dependencies      # Cross-issue dependency graph

Ship an issue end-to-end

/ll:manage-issue bug fix BUG-001   # Plan → implement → verify → complete

Fan out a parallel sprint

ll-sprint create v2-launch --issues FEAT-001,FEAT-002,FEAT-003
ll-parallel --workers 3            # Three isolated worktrees, three features, zero babysitting

Eval-driven development

/ll:create-eval-from-issues FEAT-001   # Turn acceptance criteria into a runnable harness
ll-loop validate harness-optimize      # Dry-run the FSM before paying for a real run
ll-loop run harness-optimize -b        # Score-gated hill climbing in the background

---

What's in the box

• 28 slash commands — issue discovery, refinement, planning, code quality, git, automation
• 9 specialized agents — codebase analysis, pattern finding, consistency checking, loop diagnosis, web research
• 30 skills — deterministic harnesses for common workflows (confidence checks, issue wiring, loop creation)
• 27 CLI tools — ll-auto, ll-parallel, ll-sprint, ll-loop, ll-action, and more
• 49 FSM loops — recurring automation workflows (backlog triage, sprint building, eval harnesses)
• Configuration system — project-type templates for Python, JS/TS, Go, Rust, Java, .NET, and generic

Full reference: Command Reference · CLI Reference

---

Documentation

• docs.little-loops.ai — hosted docs (searchable, dark mode, mobile)
• Configuration Reference — all options, variable substitution, overrides
• Loops Guide — FSM YAML authoring, loop patterns, practical examples
• Session Handoff Guide — context management and continuation
• Architecture Overview — system design and diagrams
• Troubleshooting — common issues and solutions
• Contributing — development setup, testing, guidelines

License

MIT