gotalab/cc-sdd / .agents/skills/cc-sdd-new-agent
cc-sdd-new-agent
VerifiedAdd or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end. Use when introducing a new agent, adding a subagent-capable variant, or evaluating migration of an existing supported agent to skills-based templates.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.5 KB |
| agents/openai.yaml | config | 351 B |
| references/plan-output-checklist.md | markdown | 1.2 KB |
| references/skills-migration.md | markdown | 2.3 KB |
SKILL.md
View on GitHub---
name: cc-sdd-new-agent
description: Add or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end. Use when introducing a new agent, adding a subagent-capable variant, or evaluating migration of an existing supported agent to skills-based templates.
---
# CC-SDD New Agent Integration
## Goal
Add a production-ready agent integration to `tools/cc-sdd` with complete research, implementation, and verification artifacts.
Use the existing SOP and templates in this repository instead of inventing a new process.
## Default Operation Mode
Use `plan-first` as the default:
- First deliverable: `docs/cc-sdd/plans/agent-plan-{agent-id}.md`
- Second deliverable (after plan approval): implementation changes in `tools/cc-sdd/...`
Do not skip the plan document unless the user explicitly requests direct implementation.
## Collect Inputs First
Collect the minimum inputs before editing files:
- Target agent display name and agent id (kebab-case)
- Official documentation URL for command/agent/skills format
- Integration scope: `commands-only`, `commands+agents`, or `skills`
- Whether work type is `new-agent` or `migration`
If any item is unclear, resolve it during Phase 1 research before creating implementation files.
## Execution Workflow
### 1) Run Phase 1 Research
Read `docs/cc-sdd/sop-new-agent.md` and extract all required spec details from official docs:
- commands directory
- agent directory (if supported)
- documentation filename
- command invocation format
- YAML frontmatter schema for commands and agents (or skills)
- placeholders/arguments format
Record exact values (not assumptions) in the plan document.
### 2) Create Plan Document
Copy and fill:
- `docs/cc-sdd/templates/agent-plan-template.md`
Include:
- Phase 1 research summary table
- Differences vs nearest existing agent pattern
- 5-step implementation plan
- changed-file list
- verification plan
Write the completed plan to:
- `docs/cc-sdd/plans/agent-plan-{agent-id}.md`
Before implementation, ensure the plan explicitly states:
- integration scope (`commands-only`, `commands+agents`, `skills`)
- whether this is `new-agent` or `migration`
- compatibility impact and rollback approach
### 3) Choose Base Pattern and Implement
Pick the nearest existing implementation and copy from it:
- `commands-only`: start from `tools/cc-sdd/templates/agents/codex` or another commands-only agent
- `commands+agents`: start from `tools/cc-sdd/templates/agents/claude-code-agent` or `tools/cc-sdd/templates/agents/opencode-agent`
- `skills`: start from `tools/cc-sdd/templates/agents/claude-code-skills`
Start implementation only after the plan file exists and the user has confirmed to proceed.
Apply the standard 5 implementation steps from SOP:
1. Update `tools/cc-sdd/src/agents/registry.ts`
2. Add `tools/cc-sdd/templates/manifests/{agent-id}.json`
3. Add `tools/cc-sdd/templates/agents/{agent-id}/...`
4. Convert YAML frontmatter to target-agent format (keep body unless incompatibility is confirmed)
5. Add `tools/cc-sdd/test/realManifest{AgentName}.test.ts`
For `skills` integration, generate `SKILL.md`-based command packages under `templates/agents/{agent-id}/skills/`.
### 4) Handle Migration Cases
If the request is migration (or migration may be needed), read `references/skills-migration.md` and decide strategy before editing:
- Recommended default: additive migration (`{agent-id}-skills` as a new option)
- Use in-place replacement only when explicitly requested
Always document compatibility impact and CLI flag impact in the plan.
### 5) Verify Before Reporting
Run verification in `tools/cc-sdd`:
- `npm test`
- `npm run build && node dist/index.js --agent {agent-id} --dry-run`
- local temp-directory apply test with `--overwrite=force`
- language checks (`--lang ja`, `--lang en`)
- generated file count checks
If tests cannot run, explicitly report which step is blocked and why.
## Completion Criteria
- Plan file exists at `docs/cc-sdd/plans/agent-plan-{agent-id}.md`
- Registry entry exists and routes to the new manifest id
- Manifest artifacts match target integration scope
- Templates render to expected target directories
- Real manifest test exists and passes
- Dry-run output matches expected artifact plan
- Plan document is updated with research evidence and verification notes
## References
- SOP: `docs/cc-sdd/sop-new-agent.md`
- Plan template: `docs/cc-sdd/templates/agent-plan-template.md`
- Migration guide: `references/skills-migration.md`
- Plan checklist: `references/plan-output-checklist.md`
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |