Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/kivo360/omoios/spec-driven-devnpx skills add kivo360/OmoiOS --skill spec-driven-devgit clone --depth 1 https://github.com/kivo360/OmoiOSWhat 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 | $0.00068 | $0.13217 |
| Opus 5 | $0.00034 | $0.06609 |
| Sonnet 5 | $0.00014 | $0.02643 |
| Haiku 4.5 | $0.00007 | $0.01322 |
Grade A, and why
spec-driven-dev 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 1,942 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Development
A systematic workflow for turning feature ideas into actionable work items that AI agents can execute.
Architecture Note: This skill is designed to work with a state machine orchestrator that executes each phase as a separate Claude SDK session. Each phase saves checkpoints to the database and can resume from any point after failure. See
docs/spec-execution-stability.mdfor the full architecture.
🔴 CRITICAL: Read This Skill Document Thoroughly
YOU MUST follow this skill document exactly. This is not optional guidance—it is the required workflow.
Before Creating ANY Spec Files:
- READ THIS ENTIRE SKILL DOCUMENT - Don't skim. Read every section to understand the required formats.
- CHECK EXISTING FILES - Run
ls -la .omoi_os/to see what already exists. Don't duplicate. - REFERENCE THE TEMPLATES - Every file type has a specific format. Copy the exact structure.
- USE THE CLI TOOLS - Validate with
python spec_cli.py validatebefore syncing.
During Spec Creation:
- REFER BACK TO THIS DOCUMENT OFTEN - When unsure about format, re-read the relevant section.
- COPY FRONTMATTER EXACTLY - Don't improvise. Use the exact field names shown in templates.
- CHECK YOUR WORK - After creating files, run validation to catch errors early.
Output Requirements:
- ALL files MUST have YAML frontmatter - No exceptions
- ALL frontmatter fields MUST match the templates - Use exact field names
- ALL specs MUST be synced - Run
python spec_cli.py sync pushwhen done - ALL IDs MUST follow conventions - TKT-001, TSK-001, REQ-FEATURE-001, etc.
If You're Unsure:
- Re-read this skill document - The answer is here
- Look at the Concrete Example section - Full file contents are provided
- Run validation -
python spec_cli.py validatewill tell you what's wrong
🔄 State Machine Architecture
Overview
Spec generation runs as a state machine with discrete phases. Each phase:
- Receives context from previous phases
- Executes a focused, time-boxed Claude SDK session
- Validates output with evaluators
- Saves checkpoint to database and file system
- Stores session transcript for potential resumption
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/claude_sdk_patterns.md 9.5 KB
- references/design_output.json 11 KB
- references/design_template.md 8.4 KB
- references/explore_output.json 3.5 KB
- references/requirements_output.json 4.9 KB
- references/requirements_template.md 6.7 KB
- references/task_template.md 4.0 KB
- references/tasks_output.json 9.4 KB
- references/ticket_template.md 5.0 KB
- scripts/api_client.py 49 KB runs code
- scripts/generate_ids.py 4.2 KB runs code
- scripts/init_feature.py 6.4 KB runs code
- scripts/models.py 21 KB runs code
- scripts/parse_specs.py 31 KB runs code
- scripts/spec_cli.py 39 KB runs code
- scripts/validate_specs.py 14 KB runs code
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.
- 3d ago First seen · 1,942 lines · 68 tokens per session scan A a5abcabba747
spec-driven-dev is a skill published in the GitHub repository kivo360/OmoiOS (75 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 13,217 once invoked, about $0.0003 per session on Opus 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 skills, from other repositories
meeting-facilitate
组织多 Agent 会议全生命周期——创建会议、spawn 真实参与者、推进轮次、签到校验、结束汇总。当需要多方协作做决策、评审方案、辩论分歧、复盘项目、头脑风暴或方案评估时使用本技能。.
os-workflow
在 AI Team OS 项目里使用 CC 内置 Workflow（ultracode）时，让工作流产出回写 OS 的标准做法。当 Leader 准备调用 Workflow 工具编排子 agent 时使用。.
meeting-participate
Participate in AI Team OS meetings with structured discussion rounds.
business-overview
经营全景分析技能。当用户需要了解整体经营状况、核心KPI、趋势对比、同比环比、利润分析时使用。.
enterprise-sales
自研产品客户拜访技能。当客户经理需要拜访政企客户、准备解决方案、或生成方案文档时使用本技能。.
complaint-handling
客户投诉处理规程。当用户表达不满、愤怒、投诉产品质量问题、要求升级处理或找领导、威胁差评或退款时使用。.