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/itmisx/deepx-code/openspecnpx skills add itmisx/deepx-code --skill openspecgit clone --depth 1 https://github.com/itmisx/deepx-codeWhat 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 | $0.00073 | $0.01344 |
| Opus 5 | $0.00036 | $0.00672 |
| Sonnet 5 | $0.00015 | $0.00269 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
openspec 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 yesterday.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSpec — 规格驱动开发(SDD)
提炼自官方 OpenSpec(https://github.com/Fission-AI/OpenSpec)的约定、文件格式与流程。 核心:"Agree before you build" —— 改动的行为规格写清楚、与用户对齐后,再写实现代码。
理念(不是僵硬的瀑布)
- fluid not rigid:不设阶段闸门,可按合理顺序产出 artifacts。
- iterative not waterfall:边做边学,规格可迭代细化。
- easy not complex:轻量、少仪式。
- brownfield-first:多数是改既有系统,所以用 delta(增/改/删) 描述"对现有行为的改动",而非从零描述整个系统。
目录两区
openspec/
specs/ # 真相基线:系统【当前】如何工作(按 capability 分)
<capability>/spec.md
changes/ # 提案:对基线的【改动】,每个改动一个文件夹
<change-id>/
proposal.md # 为什么 + 改什么
design.md # 可选,仅复杂改动写(技术方案/取舍)
tasks.md # 实现清单
specs/<capability>/spec.md # 该改动对规格的 DELTA(ADDED/MODIFIED/REMOVED)
specs/ 是源头真相;changes/<id>/ 是尚未合并的改动。归档时 change 的 delta 合并进 specs/。
文件格式(照官方,别自由发挥)
proposal.md
## Why
<动机:为什么要这个改动>
## What Changes
### 1. <子改动>
<说明>
### 2. <子改动>
...
tasks.md
## 1. <分组>
- [ ] 1.1 <小而可验证的任务>
- [ ] 1.2 ...
## 2. <分组>
- [ ] 2.1 ...
specs//spec.md —— 关键:delta 格式
按 ADDED / MODIFIED / REMOVED / RENAMED 标 delta;每条 Requirement 用 SHALL,且至少含一个 Scenario:
## ADDED Requirements
### Requirement: <名称>
<The system SHALL ...>
#### Scenario: <场景名>
- **WHEN** <条件>
- **THEN** <预期>
- **AND** <附加预期>
## MODIFIED Requirements
### Requirement: <已存在的需求名>
<改后的 SHALL 描述 + 场景>
## REMOVED Requirements
### Requirement: <要删除的需求名>
绝不用 README.md 或自由 bullet 代替——必须是 spec.md,且用上面的 Requirement + Scenario(WHEN/THEN)结构。
design.md(可选)
仅当改动复杂、需要记录架构 / 关键决策 / 取舍时才写;简单改动跳过。
工作流
- Propose:在
openspec/changes/<change-id>/建文件夹,写proposal.md+(需要时)design.md+tasks.md+specs/<capability>/spec.md(delta)。分成"短到能读完"的小块给用户看,迭代到对齐。 - Implement:对齐后按
tasks.md逐项实现,严格遵循 spec delta;每完成勾掉。若现实迫使偏离规格,先停下更新规格、重新对齐,别默默跑偏。 - Archive:改动完成并验证后,把它的 spec delta **应用(apply)**进
openspec/specs/基线,并把 change 文件夹移入归档(如openspec/changes/archive/)。- 应用语义:
ADDED→ 把该 Requirement 加入基线;MODIFIED→ 用新内容替换基线里同名 Requirement;REMOVED→ 从基线删除该 Requirement。 - 关键:
## ADDED/MODIFIED/REMOVED是只属于 change 里那份 delta 的标记。基线specs/<capability>/spec.md是当前真相,只保留当前的 Requirements / Scenario,不要带这些 delta 标记(用## Requirements或直接列### Requirement:即可)。换句话说:归档是"把 delta 应用进基线",不是"把 delta 整份拷进基线"。
- 应用语义:
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.
- yesterday First seen · 98 lines · 73 tokens per session scan A 3857d09b51d5
openspec is a skill published in the GitHub repository itmisx/deepx-code (383 stars, last pushed 7d ago), licensed MIT. It adds 73 tokens to every session and 1,344 once invoked, about $0.0004 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
ai-style
当任务是用中文撰写或改写面向读者的文案(产品发布稿、公众号文章、邮件、README 等), 或用户反馈文字「AI 味太重」「不像人写的」时,加载本 Skill。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
data_analysis
基于已确认数据执行可审计的数学计算和描述统计。.
pr-comments
Use when the user asks to review pull request comments, or when the /pr-comments command runs — fetch and analyze PR review comments on the current branch and summarize actionable items.
review
Use when asked to review a codebase or a change, or when the /review command runs — assess design, correctness, maintainability, and test coverage with actionable feedback.
dsh-doc-site-sync
Use when publishing, updating, moving, or removing DeepSeek Harness documentation website pages; editing website/docs.ts mappings or navigation; diagnosing a page missing from the VitePress site; fixing projected documentation links; or running the docs:dev, docs:check, and doc-sync workflow after website-content…