research
97Command Claude Code
../constructs/packs/k-hole/commands/research.md.
Platform layer of the Loa protocol
This repository also configures its own agents. See what loa-freeside tells them →
Command Claude Code
../constructs/packs/k-hole/commands/research.md.
Command Claude Code
../constructs/packs/dynamic-auth/commands/resolve-wallet.md.
Command Claude Code
Extend the retrospective command to support multi-session batch analysis for cross-session pattern detection.
Command Claude Code
Trigger manual learning retrospective to extract reusable skills from debugging discoveries. Run at end of session or after significant implementation work.
Command Claude Code
../constructs/packs/gtm-collective/commands/review-gtm.md.
Command Claude Code
Validate sprint implementation against acceptance criteria. Reviews actual code, not just reports. Quality gate before security audit. Resolves local sprint IDs to global IDs via Sprint Ledger.
Command Claude Code
Review and audit your work.
Command Claude Code
Analyze an existing codebase and generate Loa grimoire artifacts. Extracts code truth, validates against existing docs and user context, performs three-way drift analysis, and creates evidence-grounded PRD/SDD. "The Loa rides through the code, channeling truth into the grimoire.".
Command Claude Code
Test documentation usability by spawning zero-context agents that attempt tasks using only the provided docs. Identifies gaps that human reviewers miss due to the curse of knowledge.
Command Claude Code
Autonomous excellence loop with iterative Bridgebuilder review.
Command Claude Code
Gracefully stop a running run. Completes current phase, commits state, pushes to branch, and creates draft PR marked as incomplete.
Command Claude Code
Resume a halted run from last checkpoint. Validates state, verifies branch integrity, and continues execution.
Command Claude Code
Execute all sprints in sequence for complete release cycles. Autonomous implementation of an entire sprint plan with a single consolidated PR at the end (v1.15.1).
Command Claude Code
Display current run state and progress. Shows run details, cycle progress, metrics, and circuit breaker status.
Command Claude Code
Autonomous execution of sprint implementation with cycle loop until review and audit pass.
Command Claude Code
../constructs/packs/the-speakers/commands/score-experience.md.
Command Claude Code
../constructs/packs/gygax/commands/scry.md.
Command Claude Code
../constructs/packs/gecko/commands/sense-estate.md.
Command Claude Code
../constructs/packs/gecko/commands/sensing-construct-console.md.
Command Claude Code
../constructs/packs/gecko/commands/sensing-path-friction.md.
Command Claude Code
Deploy and archive the development cycle.
Command Claude Code
../constructs/packs/showcase/commands/showcase-audit.md.
Command Claude Code
../constructs/packs/showcase/commands/showcase-data.md.
Command Claude Code
../constructs/packs/showcase/commands/showcase-layout.md.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: