Documentation Index
Fetch the complete documentation index at: https://mintlify.com/affaan-m/ECC/llms.txt
Use this file to discover all available pages before exploring further.
Typing /code-review is faster than composing the full prompt from scratch every time. ECC’s 93 slash commands are harness-native entry points that translate a short invocation into a complete, structured workflow — routing to the right skill, delegating to the right agent, or orchestrating a multi-step pipeline without any manual wiring.
What Commands Are
Commands are .md files stored in commands/ and installed to ~/.claude/commands/. When you type /command-name in a Claude Code session, the harness loads the corresponding .md file and executes the workflow it defines. That workflow typically:
- Invokes one or more skills for domain knowledge
- Delegates steps to a sub-agent when task scope warrants it
- Enforces a verification loop before finishing
Commands are convenience shims — the durable logic lives in skills. The commands/ layer exists for slash-command compatibility and rapid invocation, not as the canonical source of workflow truth. If you find yourself editing a command to change its behaviour, the change belongs in the underlying skill.
Commands vs. Skills
| Command | Skill |
|---|
| Lives in | ~/.claude/commands/ | ~/.claude/skills/ |
| Activation | User types /command-name | Context-based or referenced by command/agent |
| Format | Single .md file | Directory with SKILL.md, or single .md |
| Purpose | Quick entry point, workflow shim | Durable knowledge, versioned logic |
| When to edit | Almost never — prefer editing the skill | When the knowledge itself changes |
Command Categories
Core Workflow
Orchestration
Multi-Agent
Language & Build
Session Management
Learning & Instincts
Epics & Project Ops
Loops & Infrastructure
The essential commands for planning, reviewing, and verifying work.| Command | What It Does |
|---|
/plan | Restate requirements, assess risks, write step-by-step implementation plan — waits for your confirm before touching code |
/code-review | Full code quality, security, and maintainability review of changed files |
/build-fix | Detect and fix build errors — delegates to the right build-resolver agent automatically |
/quality-gate | Quality gate check against project standards |
/refactor-clean | Remove dead code, consolidate duplicates, clean up structure |
/security-scan | Run a security-focused audit of changed code |
/test-coverage | Report test coverage and identify gaps |
/prune | Prune stale context, dead branches, and unused references |
/feature-dev | End-to-end feature development workflow |
Commands for multi-step feature development and multi-agent coordination.| Command | What It Does |
|---|
/orch-add-feature | Full orchestrated feature implementation (plan → implement → review → verify) |
/orch-build-mvp | Build a minimum viable feature end-to-end |
/orch-change-feature | Orchestrated workflow for modifying an existing feature |
/orch-fix-defect | Orchestrated defect resolution with root-cause analysis |
/orch-refine-code | Orchestrated code quality refinement pass |
/orch-review | Orchestrated multi-stage code review |
/plan-prd | Generate a Product Requirements Document from a feature description |
/plan | Implementation plan with risk assessment — waits for confirm before touching code |
Commands that spawn and coordinate multiple specialized sub-agents.| Command | What It Does |
|---|
/multi-plan | Multi-model collaborative planning |
/multi-workflow | Multi-model collaborative development |
/multi-backend | Backend-focused multi-model development |
/multi-frontend | Frontend-focused multi-model development |
/multi-execute | Multi-model collaborative execution |
Language-specific review, test, and build-fix commands.| Command | What It Does |
|---|
/rust-build | Fix Rust build + borrow checker issues |
/rust-review | Rust code review — ownership, lifetimes, unsafe usage |
/rust-test | TDD for Rust (cargo test, integration tests) |
/go-build | Fix Go build errors and go vet warnings |
/go-review | Go review — idiomatic patterns, concurrency safety, error handling |
/go-test | TDD for Go (table-driven, 80%+ coverage with go test -cover) |
/react-build | Fix React/Next.js build errors |
/react-review | React code review |
/react-test | React component testing |
/flutter-build | Fix Flutter/Dart build errors |
/flutter-review | Flutter code review |
/flutter-test | Flutter test workflow |
/kotlin-build | Fix Kotlin/Gradle compiler errors |
/kotlin-review | Kotlin review — null safety, coroutine safety |
/kotlin-test | TDD for Kotlin (Kotest + Kover) |
/cpp-build | Fix C++ CMake and linker problems |
/cpp-review | C++ review — memory safety, modern idioms |
/cpp-test | TDD for C++ (GoogleTest + gcov/lcov) |
/gradle-build | Fix Gradle errors for Android / KMP |
/python-review | Python review — PEP 8, type hints, security |
/fastapi-review | FastAPI-specific code review |
/vue-review | Vue.js code review |
/gan-build | Fix GAN / ML model build errors |
/gan-design | GAN architecture design workflow |
Commands for saving, restoring, and inspecting session state.| Command | What It Does |
|---|
/save-session | Save current session state to ~/.claude/session-data/ |
/resume-session | Load the most recent saved session and resume from where you left off |
/sessions | Browse, search, and manage session history with aliases |
/checkpoint | Mark a checkpoint in the current session |
/aside | Answer a quick side question without losing current task context |
Commands for capturing reusable patterns and managing learned knowledge.| Command | What It Does |
|---|
/learn | Extract reusable patterns from the current session |
/learn-eval | Extract patterns + self-evaluate quality before saving |
/evolve | Analyse learned instincts, suggest evolved skill structures |
/promote | Promote project-scoped instincts to global scope |
/instinct-status | Show all learned instincts (project + global) with confidence scores |
/instinct-export | Export instincts to a file |
/instinct-import | Import instincts from a file or URL |
/skill-create | Analyse local git history → generate a reusable skill |
/skill-health | Skill portfolio health dashboard with analytics |
Commands for managing larger work units and project infrastructure.| Command | What It Does |
|---|
/epic-claim | Claim an epic or work item for the current agent |
/epic-decompose | Break an epic into actionable sub-tasks |
/epic-publish | Publish an epic’s output to the target system |
/epic-review | Review an epic’s implementation for completeness |
/epic-sync | Sync epic status with external tracker (e.g., Jira) |
/epic-unblock | Identify and resolve blockers for a stalled epic |
/epic-validate | Validate epic acceptance criteria |
/jira | Jira integration workflow |
/pr | Create and manage pull requests |
/review-pr | Review an open pull request |
/project-init | Initialize a new project with ECC configuration |
/projects | List known projects and their instinct statistics |
Commands for automation, infrastructure management, and process control.| Command | What It Does |
|---|
/loop-start | Start a recurring agent loop on an interval |
/loop-status | Check status of running loops |
/harness-audit | Audit the agent harness configuration for reliability and cost |
/model-route | Route a task to the right model (Haiku / Sonnet / Opus) |
/pm2 | PM2 process manager initialisation |
/setup-pm | Configure package manager (npm / pnpm / yarn / bun) |
/cost-report | Generate a cost and token-usage report |
/auto-update | Update ECC components to the latest version |
/ecc-guide | Interactive ECC setup and usage guide |
/hookify | Create or configure hooks conversationally |
Quick Decision Guide
Starting a new feature? → /plan first, then /feature-dev
Code just written? → /code-review
Build broken? → /build-fix
Need language-specific review? → /rust-review, /go-review, /python-review, etc.
Update project docs? → /update-docs or /update-codemaps
Session about to end? → /save-session or /learn-eval
Resuming next day? → /resume-session
Context getting heavy? → /checkpoint
Want to extract what you learned? → /learn-eval then /evolve
Running repeated tasks? → /loop-start
Installing Commands
# Commands are installed as part of the default ECC install
npx ecc install --target claude
# Written to ~/.claude/commands/
# Verify:
ls ~/.claude/commands/
/ in any Claude Code session to see the full command list with inline descriptions.