CCManager is a command-line application for managing multiple sessions of AI coding assistants across Git worktrees and projects. It is for developers working with tools such as Claude Code, Gemini CLI, Codex CLI, Cursor Agent, Copilot CLI, Cline CLI, OpenCode, and Kimi CLI, and the catalogue entries provide commands and instructions for its workflows.
Borrowing it
Nothing to install: this file belongs to kbwo/ccmanager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kbwo/ccmanager/main/.claude/commands/kiro/spec-design.mdgit clone --depth 1 https://github.com/kbwo/ccmanagerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/kbwo/ccmanager/spec-design)<a href="https://agentmods.dev/commands/kbwo/ccmanager/spec-design"><img src="https://agentmods.dev/badge/commands/kbwo/ccmanager/spec-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/kbwo/ccmanager/spec-design"><img src="https://agentmods.dev/badge/commands/kbwo/ccmanager/spec-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00007 | $0.04015 |
| Opus 5.5 | $0.00003 | $0.01606 |
| Sonnet 5.5 | $0.00001 | $0.00803 |
| Haiku 4.5 | $0.00001 | $0.00402 |
Grade A, and why
spec-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- spec-design — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Design
Generate a technical design document for feature $1.
Task: Create Technical Design Document
1. Prerequisites & File Handling
- Requirements Approval Check:
- If invoked with
-y($2 == "-y"), setrequirements.approved=trueinspec.json - Otherwise, stop with an actionable message if requirements are missing or unapproved
- If invoked with
- Design File Handling:
- If design.md does not exist: Create new design.md file
- If design.md exists: Interactive prompt with options:
- [o] Overwrite: Generate completely new design document
- [m] Merge: Generate new design document using existing content as reference context
- [c] Cancel: Stop execution for manual review
- Context Loading: Read
.kiro/specs/$1/requirements.md, core steering documents, and existing design.md (if merge mode)
2. Discovery & Analysis Phase
CRITICAL: Before generating the design, conduct thorough research and analysis:
Feature Classification & Process Adaptation
Classify feature type to adapt process scope:
- New Feature (greenfield): Full process including technology selection and architecture decisions
- Extension (existing system): Focus on integration analysis, minimal architectural changes
- Simple Addition (CRUD, UI): Streamlined process, follow established patterns
- Complex Integration (external systems, new domains): Comprehensive analysis and risk assessment
Process Adaptation: Skip or streamline analysis steps based on classification above
A. Requirements to Technical Components Mapping
- Map requirements (EARS format) to technical components
- Extract non-functional requirements (performance, security, scalability)
- Identify core technical challenges and constraints
B. Existing Implementation Analysis
MANDATORY when modifying or extending existing features:
- Analyze codebase structure, dependencies, patterns
- Map reusable modules, services, utilities
- Understand domain boundaries, layers, data flow
- Determine extension vs. refactor vs. wrap approach
- Prioritize minimal changes and file reuse
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 459 lines · 7 tokens per session scan A d60fbd93acae
spec-design is a command published in the GitHub repository kbwo/ccmanager (1,266 stars, last pushed 3d ago), licensed MIT. It adds 7 tokens to every session and 4,015 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
maestro-odyssey
Long-running iterative cycle — one entry, seven modes (debug|improve|planex|review|security|defensive|ui). Shared archaeology/audit → fix → verify → generalize → discover → persist skeleton with mode-specific dimensions. User-invoked campaign entry; single-step fixes route via /maestro-next.
dispatch
Every task description uses structured format for clarity.
maestro-companion
Quick execution for small tasks — minimal run lifecycle (start + done) with evidence recording. Full LLM capability, scoped to mechanically clear tasks.
maestro-fork
Create or sync session worktree for parallel dev.
maestro-guard
Manage editing boundary restrictions.
converge
Bash: python /scripts/aco.py --session {rundir}/work/team report.