refactor(commands): rename review command to codereview for clarity

The `/ring:review` command is renamed to `/ring:codereview` to more
accurately reflect its function.

The name "review" was too generic and could be misinterpreted.
"codereview" is explicit, clarifying that the command triggers a
parallel code review by specialized agents. This enhances command
discoverability and reduces ambiguity.

All documentation, skill files, and examples across the repository are
updated to reflect this new command name.

The command's definition is also expanded to provide a more comprehensive
guide on the parallel review workflow, detailing the process and
expected output format.

Finally, a new `AGENTS.md` symlink is added for easier navigation.
This commit is contained in:
Fred Amaral 2025-11-27 13:42:05 -03:00
parent 0d9728dd7a
commit 218d66d077
No known key found for this signature in database
GPG key ID: ADFE56C96F4AC56A
8 changed files with 23 additions and 22 deletions

1
AGENTS.md Symbolic link
View file

@ -0,0 +1 @@
CLAUDE.md

View file

@ -139,11 +139,11 @@ dev-team/agents/
**Key Characteristics:**
- Invoked via Claude's `Task` tool with `subagent_type`
- Must specify model (typically "opus" for comprehensive analysis)
- Review agents run in parallel (3 reviewers dispatch simultaneously via `/ring:review` command)
- Review agents run in parallel (3 reviewers dispatch simultaneously via `/ring:codereview` command)
- Developer agents provide specialized domain expertise
- Return structured reports with severity-based findings
**Note:** Parallel review orchestration is handled by the `/ring:review` command
**Note:** Parallel review orchestration is handled by the `/ring:codereview` command
### 3. Commands (`commands/`)
**Purpose:** Slash commands that provide shortcuts to skills/workflows
@ -154,7 +154,7 @@ default/commands/
├── brainstorm.md # /ring-default:brainstorm - Socratic design refinement
├── write-plan.md # /ring-default:write-plan - Implementation planning
├── execute-plan.md # /ring-default:execute-plan - Batch execution
├── review.md # /ring-default:review - Parallel 3-reviewer dispatch
├── codereview.md # /ring-default:codereview - Parallel 3-reviewer dispatch
└── worktree.md # /ring-default:worktree - Git worktree creation
pm-team/commands/
@ -294,7 +294,7 @@ sequenceDiagram
participant business-reviewer
participant security-reviewer
User->>Claude: /ring:review
User->>Claude: /ring:codereview
Note over Claude: Command provides<br/>parallel review workflow
Claude->>Task Tool: Dispatch 3 parallel tasks
@ -427,7 +427,7 @@ Complex Skill → TodoWrite tracking
**Example Mappings:**
- `/ring:brainstorm``brainstorming` skill
- `/ring:write-plan``writing-plans` skill
- `/ring:review` → `full-reviewer` agent → 3 parallel review agents
- `/ring:codereview` → `full-reviewer` agent → 3 parallel review agents
### Skills ↔ Shared Patterns
@ -505,7 +505,7 @@ SKILL.md frontmatter → generate-skills-ref.py → formatted overview → sessi
1. Create `{plugin}/agents/{name}.md` with model specification
2. Include YAML frontmatter: `name`, `description`, `model`, `version`
3. Invoke via Task tool with `subagent_type="ring:{name}"`
4. Review agents can run in parallel via `/ring:review`
4. Review agents can run in parallel via `/ring:codereview`
5. Developer agents provide domain expertise via direct Task invocation
### Adding New Commands

View file

@ -56,7 +56,7 @@ ring/ # Monorepo root
│ │ ├── write-plan.md # Implementation planning
│ │ └── codebase-explorer.md # Deep architecture analysis (Opus)
│ ├── commands/ # 6 slash commands
│ │ ├── review.md # /ring-default:review - dispatch 3 parallel reviewers
│ │ ├── codereview.md # /ring-default:codereview - dispatch 3 parallel reviewers
│ │ └── brainstorm.md # /ring-default:brainstorm - interactive design
│ ├── hooks/ # Session lifecycle
│ │ ├── hooks.json # SessionStart, UserPromptSubmit config
@ -151,7 +151,7 @@ Skill tool: "ring:systematic-debugging" # Debug with 4-phase analysis
Skill tool: "ring:using-ring" # Load mandatory workflows
# Slash commands
/ring-default:review # Dispatch 3 parallel reviewers
/ring-default:codereview # Dispatch 3 parallel reviewers
/ring-default:brainstorm # Socratic design refinement
/ring-pm-team:pre-dev-feature # <2 day features (3 gates)
/ring-pm-team:pre-dev-full # ≥2 day features (8 gates)

View file

@ -63,7 +63,7 @@ Quick reference guide for the Ring skills library and workflow system. This mono
│ PLUGIN │ Self-contained package (skills+agents+commands) │
│ HOOK │ Auto-runs at session events (injects context) │
│ SKILL │ Workflow pattern (Claude Code uses internally) │
│ COMMAND │ User-invokable action (/ring:review)
│ COMMAND │ User-invokable action (/ring:codereview) │
│ AGENT │ Specialized subprocess (Task tool dispatch) │
└────────────┴──────────────────────────────────────────────────┘
```
@ -99,7 +99,7 @@ All commands prefixed with `/ring-default:` (can use `/ring:` shorthand in conte
| Command | Use Case | Example |
|---------|----------|---------|
| `/ring-default:review [files-or-paths]` | Dispatch 3 parallel code reviewers | `/ring-default:review src/auth/` |
| `/ring-default:codereview [files-or-paths]` | Dispatch 3 parallel code reviewers | `/ring-default:codereview src/auth/` |
| `/ring-default:commit [message]` | Create git commit with AI trailers | `/ring-default:commit "fix(auth): improve token validation"` |
### Iterative AI Development (ralph-wiggum)
@ -184,7 +184,7 @@ Invoke via `Task tool with subagent_type: "..."`.
| `ring-default:business-logic-reviewer` | Domain correctness, edge cases, requirements | Opus |
| `ring-default:security-reviewer` | Vulnerabilities, OWASP, auth, validation | Opus |
**Example:** Before merging, run all 3 parallel reviewers via `/ring-default:review src/`
**Example:** Before merging, run all 3 parallel reviewers via `/ring-default:codereview src/`
### Planning & Analysis (ring-default)
@ -239,7 +239,7 @@ For documentation creation and review:
2. **Plan**`/ring-pm-team:pre-dev-feature feature-name` (or `pre-dev-full` if complex)
3. **Isolate**`/ring-default:worktree feature-branch`
4. **Implement** → Use `ring-default:test-driven-development` skill
5. **Review**`/ring-default:review src/` (dispatches 3 reviewers)
5. **Review**`/ring-default:codereview src/` (dispatches 3 reviewers)
6. **Commit**`/ring-default:commit "message"`
### Bug Investigation
@ -248,12 +248,12 @@ For documentation creation and review:
2. **Trace** → Use `ring-default:root-cause-tracing` if needed
3. **Implement** → Use `ring-default:test-driven-development` skill
4. **Verify** → Use `ring-default:verification-before-completion` skill
5. **Review & Merge**`/ring-default:review` + `/ring-default:commit`
5. **Review & Merge**`/ring-default:codereview` + `/ring-default:commit`
### Code Review
```
/ring-default:review [files-or-paths]
/ring-default:codereview [files-or-paths]
Runs in parallel:
• ring-default:code-reviewer (Opus)
@ -271,7 +271,7 @@ These enforce quality standards:
1. **TDD is enforced** Test must fail (RED) before implementation
2. **Skill check is mandatory** Use `using-ring` before any task
3. **Reviewers run parallel** Never sequential review (use `/ring-default:review`)
3. **Reviewers run parallel** Never sequential review (use `/ring-default:codereview`)
4. **Verification required** Don't claim complete without evidence
5. **No incomplete code** No "TODO" or placeholder comments
6. **Error handling required** Don't ignore errors
@ -288,14 +288,14 @@ These enforce quality standards:
| Feature will take < 2 days | `/ring-pm-team:pre-dev-feature` |
| Feature will take ≥ 2 days or has complex dependencies | `/ring-pm-team:pre-dev-full` |
| Need implementation tasks | `/ring-default:write-plan` |
| Before merging code | `/ring-default:review` |
| Before merging code | `/ring-default:codereview` |
### Agent Selection
| Need | Agent to Use |
|------|-------------|
| General code quality review | 3 parallel reviewers via `/ring-default:review` |
| General code quality review | 3 parallel reviewers via `/ring-default:codereview` |
| Language-agnostic backend design | `ring-dev-team:backend-engineer` |
| Go backend expertise | `ring-dev-team:backend-engineer-golang` |
| TypeScript/Node.js backend | `ring-dev-team:backend-engineer-typescript` |

View file

@ -28,7 +28,7 @@ Ring solves this by:
- `ring-default:security-reviewer` - Safety review (vulnerabilities, OWASP, authentication)
- `ring-default:write-plan` - Implementation planning agent
- `ring-default:codebase-explorer` - Deep architecture analysis (Opus-powered, complements built-in Explore)
- Use `/ring-default:review` command to orchestrate parallel review workflow
- Use `/ring-default:codereview` command to orchestrate parallel review workflow
**Developer Agents (dev-team plugin):**
- `ring-dev-team:backend-engineer` - Language-agnostic backend specialist (adapts to Go/TypeScript/Python/etc)

View file

@ -1,5 +1,5 @@
---
name: review
name: codereview
description: Run comprehensive parallel code review with all 3 specialized reviewers
argument-hint: "[files-or-paths]"
---

View file

@ -74,7 +74,7 @@ Three specialized reviewers run in **parallel** for maximum speed:
**Two ways to run parallel reviews:**
1. **Direct parallel dispatch:** Launch 3 Task calls in single message (explicit control)
2. **/ring:review command:** Command that provides workflow instructions for parallel review (convenience)
2. **/ring:codereview command:** Command that provides workflow instructions for parallel review (convenience)
## How to Request

View file

@ -258,13 +258,13 @@ Ralph complements other Ring workflows:
- Use **brainstorming** to design the task before starting a Ralph loop
- Include **TDD patterns** in your Ralph prompt for self-verification
- After Ralph completes, run **/ring-default:review** for code quality check
- After Ralph completes, run **/ring-default:codereview** for code quality check
**Example workflow:**
```
1. /ring-default:brainstorm "TODO API design"
2. /ralph-wiggum:ralph-loop "Implement TODO API per design..." --max-iterations 30
3. /ring-default:review src/
3. /ring-default:codereview src/
4. /ring-default:commit "feat: add TODO API"
```