serhattayaz-ai
27d58e589a
The ecc@ecc plugin namespaces agents, commands and skills as `ecc:<name>`. A manual install (install-apply --target claude|claude-project) places the same files at bare names under ~/.claude, so plugin-prefixed references in copied markdown point at agents and commands that do not exist in that layout (e.g. subagent_type "ecc:planner", frontmatter agent: ecc:...). - Add plugin-namespace.js with stripPluginNamespace(), which removes the `ecc:` prefix before an identifier and leaves `ecc@ecc`, URLs and words ending in "ecc" alone. - Apply it to markdown copy operations when the target is claude or claude-project. Non-markdown files and other targets are unchanged. - Reword the agents rule so it describes both install modes instead of stating that agents only ship with the plugin. - Cover the transform with tests/lib/install-plugin-namespace.test.js.
3.0 KiB
Agent Orchestration
Available Agents
ECC agents come either from the ecc@ecc plugin (plugin-scoped names, ecc:<name>) or from a manual install into ~/.claude/agents/ (bare names, <name>). Use the name that matches the install you have; the manual installer strips the ecc: prefix from copied files.
They are invoked through the Agent tool with that subagent_type:
Agent(subagent_type: "ecc:planner", prompt: "...")
| Agent | Purpose | When to Use |
|---|---|---|
| ecc:planner | Implementation planning | Complex features, refactoring |
| ecc:architect | System design | Architectural decisions |
| ecc:tdd-guide | Test-driven development | New features, bug fixes |
| ecc:code-reviewer | Code review | After writing code |
| ecc:security-reviewer | Security analysis | Before commits |
| ecc:build-error-resolver | Fix build errors | When build fails |
| ecc:e2e-runner | E2E testing | Critical user flows |
| ecc:refactor-cleaner | Dead code cleanup | Code maintenance |
| ecc:doc-updater | Documentation | Updating docs |
| ecc:rust-reviewer | Rust code review | Rust projects |
| ecc:harmonyos-app-resolver | HarmonyOS app development | HarmonyOS/ArkTS projects |
For the full roster of 68 agents, see /ecc:ecc-guide.
Immediate Agent Usage
No user prompt needed:
- Complex feature requests - Use ecc:planner agent
- Code just written/modified - Use ecc:code-reviewer agent
- Bug fix or new feature - Use ecc:tdd-guide agent
- Architectural decision - Use ecc:architect agent
Parallel Task Execution
ALWAYS use parallel Task execution for independent operations:
# GOOD: Parallel execution
Launch 3 agents in parallel:
1. Agent 1: Security analysis of auth module
2. Agent 2: Performance review of cache system
3. Agent 3: Type checking of utilities
# BAD: Sequential when unnecessary
First agent 1, then agent 2, then agent 3
Delegation Completion Contract
Applies to every agent at every depth (parent, child, grandchild):
- Your final message IS the deliverable. Never end your turn with "waiting for background agents" — a spawned task is not a completed task. Ending your turn while children are running orphans their results (completed children cannot notify a parent whose turn has ended).
- If you delegate, you own collection. Wait for results, integrate them, then return. Fire-and-forget delegation is forbidden.
- Decompose only when the work cannot fit in one context. Do not re-delegate a task already sized for a single agent — depth is an outcome, not a plan.
Rationale: observed failure mode — research agents followed "Parallel Task Execution" above, spawned children, and returned "waiting" as their final answer. All children completed successfully but their results were orphaned. The parallel rule without a completion contract produces zombie tasks.
Multi-Perspective Analysis
For complex problems, use split role sub-agents:
- Factual reviewer
- Senior engineer
- Security expert
- Consistency reviewer
- Redundancy checker