104 commands
Commands catalog
Every slash command Kodelyth ECC ships. Type one in your AI tool to run a full workflow — parallel multi-agent audits, TDD and planning flows, build fixers, security sweeps, and memory tools.
Parallel & multi-agent
Fire several specialist agents at once — full audits, adversarial sweeps, and parallel execution in a single command.
/arenaargsThe Arena — GOD builds, EVIL attacks, repeat until the attacker gives up. The adversarial loop with scored findings, verification, convergence detection, and hard budget stops.
/debug-blitzParallel debug assault — fires debug-detective + silent-failure-hunter + env-debugger simultaneously. Three root-cause specialists on your bug at once.
/devil-modeParallel adversarial sweep — fires prompt-injection-hunter + supply-chain-auditor + secret-hunter + backdoor-hunter simultaneously. The full attacker-mindset audit in one command.
/evil-modeargsEVIL mode — adversarial sweep with scored findings, adversarial verification, and loop-until-dry. The upgrade of /devil-mode — unreproducible findings get refuted instead of padding the report.
/god-modeargsGOD mode — the constructive crew. Recalls past solutions, designs, builds test-first, self-critiques, hardens, and proves the work with a command that actually runs.
/multi-backendargsFan out backend implementation across parallel specialist agents
/multi-executeargsExecute a multi-agent plan across parallel workers
/multi-frontendargsFan out frontend implementation across parallel specialist agents
/multi-planargsPlan a task for parallel multi-agent execution
/multi-workflowargsOrchestrate a multi-step workflow across parallel agents
/onboardParallel codebase onboarding — fires code-explorer + architect + doc-updater simultaneously. Understand any codebase in 15 minutes instead of 3 days.
/pre-releaseParallel pre-release check — fires release-captain + security-reviewer + code-reviewer simultaneously. Go/no-go in one command before you ship.
/project-launchParallel founding-team blast for new projects. Fires architect + security + UX + TDD + pair-programmer simultaneously. One command, 5 specialist reports at once.
/refactor-sprintParallel refactor sprint — fires refactor-cleaner + code-simplifier + type-design-analyzer + tdd-guide simultaneously. Full cleanup in one pass.
/santa-loopAdversarial dual-review convergence loop — two independent model reviewers must both approve before code ships.
/security-auditParallel security audit — fires security-reviewer + dependency-doctor + api-guardian simultaneously. Full threat surface in one command.
/super-agentDrive a large objective to completion through the autonomous orchestrator — decompose, dispatch (parallel), integrate branches, verify. Resumable, budget-governed.
/swarmargsSpawn N specialist agents in parallel inside isolated git worktrees + a tmux session. Generalized /devil-mode.
/team-reviewParallel full-team audit for existing projects. Fires code-reviewer + security-reviewer + performance-optimizer + api-guardian simultaneously. One command, complete audit at once.
Single-agent & workflow
Focused commands for one job — reviews, builds, tests, planning, memory, and release workflows.
/agent-sortLegacy slash-entry shim for the agent-sort skill. Prefer the skill directly.
/asideAnswer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
/build-fixIncrementally fix build and type errors with minimal, safe changes
/checkpointargsSave a git checkpoint commit of the current working state
/clawLegacy slash-entry shim for the nanoclaw-repl skill. Prefer the skill directly.
/code-reviewargsCode review — local uncommitted changes or GitHub PR (pass PR number/URL for PR mode)
/context-budgetLegacy slash-entry shim for the context-budget skill. Prefer the skill directly.
/cpp-buildFix C++ build errors, CMake issues, and linker problems incrementally. Invokes the cpp-build-resolver agent for minimal, surgical fixes.
/cpp-reviewComprehensive C++ code review for memory safety, modern C++ idioms, concurrency, and security. Invokes the cpp-reviewer agent.
/cpp-testEnforce TDD workflow for C++. Write GoogleTest tests first, then implement. Verify coverage with gcov/lcov.
/dashboardBoot the localhost-only Kodelyth ECC observability dashboard. Visualizes memory, evolve signals, catalog, swarm sessions, and token-budget snapshots. Read-only. Zero telemetry.
/devfleetLegacy slash-entry shim for the claude-devfleet skill. Prefer the skill directly.
/docsLegacy slash-entry shim for the documentation-lookup skill. Prefer the skill directly.
/doctorDiagnose your Kodelyth ECC install — check for drift, missing files, version mismatches, and confirm everything is healthy
/e2eLegacy slash-entry shim for the e2e-testing skill. Prefer the skill directly.
/evalLegacy slash-entry shim for the eval-harness skill. Prefer the skill directly.
/evolveAnalyze instincts and suggest or generate evolved structures
/feature-devGuided feature development with codebase understanding and architecture focus
/flutter-buildFix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.
/flutter-reviewReview Flutter/Dart code for idiomatic patterns, widget best practices, state management, performance, accessibility, and security. Invokes the flutter-reviewer agent.
/flutter-testRun Flutter/Dart tests, report failures, and incrementally fix test issues. Covers unit, widget, golden, and integration tests.
/gan-buildargsGAN harness — generator/evaluator build loop for autonomous feature implementation
/gan-designargsGAN harness — expand a one-line prompt into a full product spec
/go-buildFix Go build errors, go vet warnings, and linter issues incrementally. Invokes the go-build-resolver agent for minimal, surgical fixes.
/go-reviewComprehensive Go code review for idiomatic patterns, concurrency safety, error handling, and security. Invokes the go-reviewer agent.
/go-testEnforce TDD workflow for Go. Write table-driven tests first, then implement. Verify 80%+ coverage with go test -cover.
/gradle-buildFix Gradle build errors for Android and KMP projects
/harness-auditAudit and optimize the local agent harness for reliability, cost, and throughput
/hookifyCreate hooks to prevent unwanted behaviors from conversation analysis or explicit instructions
/hookify-configureEnable or disable hookify rules interactively
/hookify-helpGet help with the hookify system
/hookify-listList all configured hookify rules
/immuneargsScan any codebase for the bug classes the arena has actually confirmed — executable detectors, each pinned to the commit that proves it.
/instinct-exportExport instincts from project/global scope to a file
/instinct-importImport instincts from file or URL into project/global scope
/instinct-statusShow learned instincts (project + global) with confidence
/jiraRetrieve a Jira ticket, analyze requirements, update status, or add comments. Uses the jira-integration skill and MCP or REST API.
/kotlin-buildFix Kotlin/Gradle build errors, compiler warnings, and dependency issues incrementally. Invokes the kotlin-build-resolver agent for minimal, surgical fixes.
/kotlin-reviewComprehensive Kotlin code review for idiomatic patterns, null safety, coroutine safety, and security. Invokes the kotlin-reviewer agent.
/kotlin-testEnforce TDD workflow for Kotlin. Write Kotest tests first, then implement. Verify 80%+ coverage with Kover.
/learnExtract reusable patterns from this session and save them as learned skills
/learn-evalExtract reusable patterns from the session, self-evaluate quality before saving, and determine the right save location (Global vs Project).
/lessonsLoad, view, and save project lessons from tasks/lessons.md. Works on ALL platforms — Claude Code, Windsurf, Cursor, Codex, Antigravity, OpenCode.
/loop-startargsStart an autonomous agent loop with quality gates and recovery controls
/loop-statusShow the status of running autonomous agent loops
/memoryManage local Kodelyth Memory — recall, capture, review, and curate what your AI knows about you
/memory-evolvePhase 3.4 self-evolving memory. Convert reuse + routing-miss signals into PR-ready proposals (skill drafts + routing-rule additions). Never auto-applies.
/model-routeargsRecommend the right model tier (trivial/standard/hard) for the current task
/orchestrateLegacy slash-entry shim for dmux-workflows and autonomous-agent-harness. Prefer the skills directly.
/planRestate requirements, assess risks, and create step-by-step implementation plan. WAIT for user CONFIRM before touching any code.
/pm2argsManage long-running dev processes with pm2 (start, stop, logs, status)
/projectsList known projects and their instinct statistics
/promotePromote project-scoped instincts to global scope
/prompt-optimizeLegacy slash-entry shim for the prompt-optimizer skill. Prefer the skill directly.
/prp-commitargsQuick commit with natural language file targeting — describe what to commit in plain English
/prp-implementargsExecute an implementation plan with rigorous validation loops
/prp-planargsCreate comprehensive feature implementation plan with codebase analysis and pattern extraction
/prp-prargsCreate a GitHub PR from current branch with unpushed commits — discovers templates, analyzes changes, pushes
/prp-prdargsInteractive PRD generator - problem-first, hypothesis-driven product spec with back-and-forth questioning
/pruneDelete pending instincts older than 30 days that were never promoted
/python-reviewComprehensive Python code review for PEP 8 compliance, type hints, security, and Pythonic idioms. Invokes the python-reviewer agent.
/quality-gateRun the full quality gate — build, lint, types, tests, security scan
/refactor-cleanRemove dead code, duplicates, and tech debt with safe automated cleanup
/replayargsReplay a finished swarm session — same task, optional A/B variations (different harness, agents, base ref).
/resume-sessionLoad the most recent session file from ~/.claude/session-data/ and resume work with full context from where the last session ended.
/review-prComprehensive PR review using specialized agents
/route-modelargsRecommend the right model tier (trivial/standard/hard) for the current task. Surfaces the cost-aware-model-routing rule on demand.
/rules-distillLegacy slash-entry shim for the rules-distill skill. Prefer the skill directly.
/rust-buildFix Rust build errors, borrow checker issues, and dependency problems incrementally. Invokes the rust-build-resolver agent for minimal, surgical fixes.
/rust-reviewComprehensive Rust code review for ownership, lifetimes, error handling, unsafe usage, and idiomatic patterns. Invokes the rust-reviewer agent.
/rust-testEnforce TDD workflow for Rust. Write tests first, then implement. Verify 80%+ coverage with cargo-llvm-cov.
/save-sessionSave current session state to a dated file in ~/.claude/session-data/ so work can be resumed in a future session with full context.
/sessionsManage Claude Code session history, aliases, and session metadata.
/setup-pmConfigure your preferred package manager (npm/pnpm/yarn/bun)
/skill-createAnalyze local git history to extract coding patterns and generate SKILL.md files. Local version of the Skill Creator GitHub App.
/skill-healthShow skill portfolio health dashboard with charts and analytics
/tddLegacy slash-entry shim for the tdd-workflow skill. Prefer the skill directly.
/terseargsSwitch reply compression level — /terse [lite|full|ultra|off]. Complements RTK (input savings) with output-side savings.
/terse-compressargsCompress a markdown file into terse form for permanent input-token savings. Byte-preserves code, URLs, paths.
/test-coverageAnalyze test coverage and identify the highest-value gaps to fill
/updateUpgrade Kodelyth ECC to the latest version, preserving your current install target and language profile
/update-codemapsRegenerate codemaps and architecture docs from the current source
/update-docsUpdate README and documentation to match the current code
/verifyLegacy slash-entry shim for the verification-loop skill. Prefer the skill directly.
/verify-supply-chainGenerate / verify SBOM, content manifest, and SLSA provenance for kodelyth-ecc. Use for compliance, audit, or tamper checks.