Investigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.
日本語の概要は準備中です。原文の説明を表示しています。
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.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
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.
Use plan-first as the default:
docs/cc-sdd/plans/agent-plan-{agent-id}.mdtools/cc-sdd/...Do not skip the plan document unless the user explicitly requests direct implementation.
Collect the minimum inputs before editing files:
commands-only, commands+agents, or skillsnew-agent or migrationIf any item is unclear, resolve it during Phase 1 research before creating implementation files.
Read docs/cc-sdd/sop-new-agent.md and extract all required spec details from official docs:
Record exact values (not assumptions) in the plan document.
Copy and fill:
docs/cc-sdd/templates/agent-plan-template.mdInclude:
Write the completed plan to:
docs/cc-sdd/plans/agent-plan-{agent-id}.mdBefore implementation, ensure the plan explicitly states:
commands-only, commands+agents, skills)new-agent or migrationPick the nearest existing implementation and copy from it:
commands-only: start from tools/cc-sdd/templates/agents/codex or another commands-only agentcommands+agents: start from tools/cc-sdd/templates/agents/claude-code-agent or tools/cc-sdd/templates/agents/opencode-agentskills: start from tools/cc-sdd/templates/agents/claude-code-skillsStart implementation only after the plan file exists and the user has confirmed to proceed.
Apply the standard 5 implementation steps from SOP:
tools/cc-sdd/src/agents/registry.tstools/cc-sdd/templates/manifests/{agent-id}.jsontools/cc-sdd/templates/agents/{agent-id}/...tools/cc-sdd/test/realManifest{AgentName}.test.tsFor skills integration, generate SKILL.md-based command packages under templates/agents/{agent-id}/skills/.
If the request is migration (or migration may be needed), read references/skills-migration.md and decide strategy before editing:
{agent-id}-skills as a new option)Always document compatibility impact and CLI flag impact in the plan.
Run verification in tools/cc-sdd:
npm testnpm run build && node dist/index.js --agent {agent-id} --dry-run--overwrite=force--lang ja, --lang en)If tests cannot run, explicitly report which step is blocked and why.
docs/cc-sdd/plans/agent-plan-{agent-id}.mddocs/cc-sdd/sop-new-agent.mddocs/cc-sdd/templates/agent-plan-template.mdreferences/skills-migration.mdreferences/plan-output-checklist.mdまだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Investigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.
日本語の概要は準備中です。原文の説明を表示しています。
Entry point for new work. Determines the best action path or work decomposition (update existing spec, create new spec, mixed decomposition, or no spec needed) and refines ideas through structured dialogue.
日本語の概要は準備中です。原文の説明を表示しています。
Implement approved tasks using TDD with native subagent dispatch. Runs all pending tasks autonomously or selected tasks manually.
日本語の概要は準備中です。原文の説明を表示しています。
Implement approved tasks in Cascade using TDD and inline review. Runs all pending tasks or selected tasks in the main context.
日本語の概要は準備中です。原文の説明を表示しています。
Implement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tasks manually.
日本語の概要は準備中です。原文の説明を表示しています。
Review a task implementation against approved specs, task boundaries, and verification evidence. Use after an implementer finishes a task, after remediation, or before accepting a task as complete.
日本語の概要は準備中です。原文の説明を表示しています。