Skip to main content
skill CX Codex

cc-sdd-new-agent — Claude Code skill: what it does, how to install

The cc-sdd-new-agent skill guides a new coding-agent integration in cc-sdd, from official-format research and planning to implementation checks.

MIT ★ 3,774 updated 2026-10-22

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add gotalab/cc-sdd --skill cc-sdd-new-agent -a claude-code
Open on GitHub

What cc-sdd-new-agent does

The skill follows the repository SOP for adding or extending an agent in tools/cc-sdd. It first gathers the target agent id, documentation, integration scope, and work type, then writes a plan to docs/cc-sdd/plans/agent-plan-{agent-id}.md. That plan records the researched format, nearby implementation differences, changed files, compatibility impact, rollback, and verification steps.

After approval, the skill updates tools/cc-sdd/src/agents/registry.ts, adds a manifest and agent templates, converts YAML frontmatter, and creates a real-manifest test. Skills-based integrations use packages built around SKILL.md. Verification covers npm test, a build with dry-run, a temporary-directory apply test, language checks, and generated-file counts. Implementation waits for plan approval unless the user explicitly requests direct changes.

What it helps with

  • plan a new coding-agent integration
  • research command and frontmatter formats from official docs
  • add an agent manifest and template package
  • verify generated artifacts with tests and dry-run

Example prompts for the agent

  • Create a plan for a new agent with id my-agent and save it as docs/cc-sdd/plans/agent-plan-my-agent.md.
  • Add support for a new agent in tools/cc-sdd using the SOP, then wait for my approval before editing implementation files.
  • Assess a migration to skills-based templates and document compatibility, rollback, and CLI flag impact.

How to install cc-sdd-new-agent

1Skills CLI (Vercel)

npx skills add gotalab/cc-sdd --skill cc-sdd-new-agent -a claude-code

2Manually: put the files in place

~/.claude/skills/cc-sdd-new-agent/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/cc-sdd-new-agent/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about cc-sdd-new-agent

How do I install cc-sdd-new-agent in Claude Code?

Run npx skills add gotalab/cc-sdd --skill cc-sdd-new-agent -a claude-code. The skill file will be at ~/.claude/skills/cc-sdd-new-agent/SKILL.md.

What does cc-sdd-new-agent do?

It guides the addition or extension of a coding-agent integration in cc-sdd. The workflow covers research, a plan document, registry and template changes, tests, and verification.

Does cc-sdd-new-agent support Codex?

Yes. The skill targets Claude Code and Codex, and it includes migration planning with compatibility and CLI flag impact recorded before implementation.

Source text

SKILL.md · MIT
---
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`

© gotalab · MIT · gotalab/cc-sdd

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set12

The whole set →
requirements-review-gate The requirements-review-gate rule halts work and requires fixing the requirements draft before requirements.md is written. It validates scope coverage, EARS format compliance, and structural quality. CX Codex +1 ★ 3,774repo stars design-review-gate design-review-gate audits draft architectures before generating design.md. It links requirement IDs to concrete components and prevents speculative interfaces. CX Codex +1 ★ 3,774repo stars ears-format The ears-format rule formats acceptance criteria with EARS patterns. Use it when a specification needs clear conditions, subjects, and system responses. CX Codex +1 ★ 3,774repo stars design-discovery-full The design-discovery-full rule systematically maps requirements, existing code, technologies, and risks before design begins. It ensures architectural choices rest on facts rather than assumptions. CX Codex +1 ★ 3,774repo stars design-review design-review reviews technical design documents before coding starts and issues a GO/NO-GO verdict. Caps feedback at three critical issues tied directly to project requirements. CX Codex +1 ★ 3,774repo stars gap-analysis The gap-analysis rule structures the analysis of your existing codebase, identifies what's missing for a feature, and helps you decide whether to extend existing components or build new ones. CX Codex +1 ★ 3,774repo stars tasks-generation tasks-generation guides AI coding agents to generate structured, dependency-ordered technical task plans from specifications without leaking low-level code details. CX Codex +1 ★ 3,774repo stars design-principles The design-principles rule sets checks for architecture, types, documentation, and Mermaid diagrams. Use it when drafting design.md or reviewing component boundaries. CX Codex +1 ★ 3,774repo stars

Project sponsors

Companies that keep this analytics open