Orkas is a desktop application for commanding a team of AI agents through one chat, with a commander model assigning work to specialist agents in parallel or in sequence. People use it to coordinate research, writing, presentations, and software tasks while keeping files on their computer. The catalogue includes skills for extending the agents available to Orkas.
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 skills add Orkas-AI/Orkas --skill 68fb048b85cbgit clone --depth 1 https://github.com/Orkas-AI/OrkasWrote 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/skills/orkas-ai/orkas/68fb048b85cb)<a href="https://agentmods.dev/skills/orkas-ai/orkas/68fb048b85cb"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/68fb048b85cb/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/skills/orkas-ai/orkas/68fb048b85cb"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/68fb048b85cb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00002 | $0.01675 |
| Opus 5 | $0.00001 | $0.00838 |
| Sonnet 5 | $0.00000 | $0.00335 |
| Haiku 4.5 | $0.00000 | $0.00168 |
Grade A, and why
product-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 10d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
产品研发
把已经明确的产品行为或工程问题转成可审查的技术决策、聚焦代码变更、工程验证和真实交付证据。本 skill 负责工程执行纪律；产品方向探索、一次性 demo、产品级验收定义和 GitHub 维护分别交给对应能力。
何时使用
- 从 PRD、issue、设计或明确目标实现功能。
- 修复 bug、失败测试、CI/build、性能或回归问题。
- 做有行为约束的重构、代码评审或技术方案审查。
- 需要 ADR、spike/POC、迁移、兼容性、依赖或回滚决策。
- 实现后需要工程测试、diff 自审和可审计交付。
不要用于仍缺核心用户、问题或成功标准的产品探索；不要把产品验收场景等同于工程自动化测试；不要自动提交、推送、发布或操作外部系统。
边界先行
- 如果目标用户、核心问题、期望结果或成功证据仍是产品选择，不编造推荐 MVP、PRD、功能范围、架构或代码；只指出最小缺口，并路由到产品需求分析。
- 如果用户明确要一次性、可丢弃、用于理解度或想法验证的 demo，不生成实现工件，也不套用生产研发流程；把时间盒、可点击性、可丢弃性和验证问题原样交给原型验证能力。
- 只有当行为或工程问题明确到可以从仓库继续求证时，才进入下面的研发主线。
Finite Input Fast Path
当任务只有用户明确列出的有限输入文件、确定的输出路径，且不要求代码或仓库行为变更时，按材料处理快速路径执行：
- 读取一次本 skill 后，直接按工具上限批量读取全部指定输入；多个独立批次尽量在同一模型轮并行发出。
- 写入指定交付物，只回读该交付物一次做聚焦验证，然后结束。
- Skip generic repository discovery：不搜索仓库规则、manifest/CI，不运行 Git/分支/基线/diff 探测，也不扩展到未指定文件。
- 不用
manage_execution_plan叙述有限批次的进度；只有存在真实依赖链、跨边界实现或高风险决策时才建计划。
这个快速路径只减少与任务无关的工程仪式，不跳过用户指定输入、输出验证或安全边界。
执行主线
- 建立工程合同：区分 feature、bug/test failure、refactor、review-only、performance、decision/spike、CI/build；明确目标、非目标、不变量和完成证据。
- 先建立仓库地图：读取仓库接入检查，确认规则、脏工作区、构建测试入口、相关符号/调用路径和现有模式。
- 风险分支前置：仓库地图显示依赖、迁移、兼容、安全、外部副作用、不可逆操作或大影响面时，在首次相关安装或编辑前读取变更安全；没有这些风险时跳过。
- 先决策后编辑：存在关键取舍时读取 ADR、spike 或 decision review；多文件/跨边界任务先写短计划，小修复直接给出最小变更路径。
- 实现与快速反馈：读取实现与快速反馈；先基线或复现，再小步编辑，每个切片后做便宜且聚焦的检查。
- 按结果深入：失败路径读取 debugging；实际工程测试读取 engineering-tests。
- 提交前独立复核：读取评审与完成门禁，从完整 diff 和验收—证据矩阵重新判断，不沿用“实现已经正确”的假设。
渐进路由
| 场景 | 读取 |
|---|---|
| 仓库规则、工作区状态、命令入口、模块/符号/测试地图 | 仓库接入检查 |
| 技术选型、架构边界、不可逆决策、ADR | 架构决策 |
| 技术预研、POC、spike、可行性结论 | 技术预研 |
| 上线前追问、隐藏假设、方案取舍审查 | 决策复核 |
| 阶段、任务、直接依赖、研发交接 | 研发模板 |
| 编码、TDD、小步实现、快速反馈 | 实现 |
| Bug、失败测试、回归、异常行为 | 调试 |
| 单元/集成/契约/E2E/构建等工程验证 | 工程测试 |
| 依赖、迁移、兼容、安全、外部副作用、回滚 | 变更安全 |
| diff 评审、完成门禁、证据化交付 | 评审与完成 |
What ships with it
11 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.
- _meta.json 951 B
- references/architecture-decision.md 2.7 KB
- references/change-safety.md 3.2 KB
- references/debugging.md 2.0 KB
- references/decision-review.md 2.9 KB
- references/engineering-tests.md 2.5 KB
- references/implementation.md 2.3 KB
- references/product-dev-template.md 2.7 KB
- references/repository-intake.md 2.8 KB
- references/review-and-finish.md 3.0 KB
- references/technical-spike.md 2.8 KB
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.
- 10d ago First seen · 83 lines · 2 tokens per session scan A 55bf3b024135
product-dev is a skill published in the GitHub repository Orkas-AI/Orkas (1,848 stars, last pushed yesterday), licensed MIT. It adds 2 tokens to every session and 1,675 once invoked, about $0.0000 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
tutti-workspace-app-factory
Create, convert, or repair one Tutti workspace app as either a self-contained publishable package under package/ or a Chrome-style local debug app under .tutti/dev-app/. Use for mention://workspace-app-factory/create handoffs, mention://workspace-app-factory handoffs, standalone app generation, adapting existing…
tutti-ui-system
Use when working with @tutti-os/ui-system components, replacing local UI with shared components, querying component ids or metadata, promoting UI into shared base or business components, or maintaining UI-system storyboard inventory.
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
takt
A workflow engine that runs a task through a sequence of steps defined in a YAML file, using separate coding agents for the work.
takt
A workflow engine for coordinating multiple coding agents. It reads a YAML workflow, a text configuration format, and moves agents through its defined steps and rules.
create-coordclaw-team
A Skill for creating a CoordClaw multi-agent collaborative team. Through an 8-step standardized process, from requirement gathering to team validation, rapidly build a complete AI team.