little-loops

Rewrite an issue's Implementation Steps, Acceptance Criteria, and Files to Modify in place from its own accumulated research findings, without appending or bulldozing human prose

Use when asked to audit documentation accuracy, coverage, or find documentation gaps.

Use when asked about project health, velocity, bug trends, or whether we're making progress.

Use when asked for an adversarial go/no-go review or whether an issue is worth implementing.

Use when asked to manually compact a session's memory, trigger session summarization, or reduce a long session's context footprint.

Use when asked to manually compact a session's memory, trigger session summarization, or reduce a long session's context footprint.

Use when asked to detect conflicting requirements or incompatible decisions across open issues.

Use when asked to decompose a theme or goal into an EPIC with 3–8 child issues. Creates the EPIC file, pre-wired child stubs, and stages everything for git.

Use when asked to prove an unproven internal mechanism with an isolated code spike before implementing.

Use when asked to capture or create an issue from conversation or natural language.

Use when asked to select the winning implementation option for an issue with decision_needed.

Use when a refined issue is missing integration points or wiring in the implementation plan.

Use when asked for a pre-implementation confidence check or whether an issue is ready to implement.

Use when asked to find dependencies between issues or prepare a dependency-aware sprint plan.

Use when asked to review loop config quality, validate loop YAML, or audit a loop definition.

Use when asked to assess loop effectiveness, audit goal achievement, or detect phantom success.

Use when asked to configure little-loops, change settings, or update ll-config.json.

Use when asked to review epic health, audit stalled children, check scope drift, find missing coverage, or assess closure readiness. Produces a structured health report and actionable recommendations. Read-only.

Use when asked to audit Claude Code config, validate plugin settings, or diagnose plugin issues.

Validate active issues against key documents for relevance and alignment

Analyze user message history to identify patterns, workflows, and automation opportunities

Analyze codebase architecture for patterns, organization, and improvements

Use when asked to capture or create an issue from conversation or natural language.

Run code quality checks (lint, format, types, build)

Create git commits with user approval and no Claude attribution

Generate comprehensive PR descriptions following repository templates

Analyze codebase for deprecated, unused, or dead code that can be safely removed

Use when asked for an adversarial go/no-go review or whether an issue is worth implementing.

Generate continuation prompt for session handoff

List all available little-loops commands with descriptions

Iterate on existing implementation plans with thorough research and updates

Analyze user message history to suggest FSM loop configurations automatically. Uses ll-messages output to identify repeated workflows and generate ready-to-use loop YAML. Also supports --from-commands mode to suggest loops from the available command/skill catalog without requiring message history, and --from-sequences mode to suggest loops from ll-logs sequences n-gram output. Trigger keywords: "suggest loops", "loop from history", "automate workflow", "create loop from messages", "analyze messages for loops", "ll-messages loop", "suggest automation", "detect patterns for loops", "suggest loops from commands", "loop from catalog", "from-commands", "suggest loops from sequences", "from-sequences", "loop from ll-logs"

Manage releases - create git tags, generate changelogs, and manage GitHub releases. Integrates with Issue Management to include completed issues in release notes. Trigger keywords: "manage release", "create release", "new release", "tag release", "publish release", "make release", "bump version"

Find and fix issue filenames with missing or duplicate IDs across types (e.g., BUG-007 and FEAT-007)

Open a pull request for the current branch. Trigger keywords: "open pr", "create pull request", "submit pr", "create pr", "open pull request", "submit for review", "make a pr"

Analyze issues and prepend priority levels (P0-P5) to filenames

Analyze and validate an issue file for accuracy, utility, and completeness, then auto-correct to make implementation-ready or close if invalid

Refine issue files with codebase-driven research to fill knowledge gaps needed for implementation

Resume from a previous session's continuation prompt

Run test suites with common patterns