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/yangfan-code-star/context-dev/record-decisionnpx skills add YangFan-Code-Star/context-dev --skill record-decisiongit clone --depth 1 https://github.com/YangFan-Code-Star/context-devWhat 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 | $0.00580 |
| Opus 5 | $0.00034 | $0.00290 |
| Sonnet 5 | $0.00014 | $0.00116 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade A, and why
record-decision 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.
What it actually says
记录架构决策
代码能表达"做了什么"，表达不了"为什么不用另一个方案"。缺了这部分，agent 会反复提议已经被否决过的东西，而你要一遍遍重新解释。
什么时候该写
- 在两个及以上方案之间做了选择，且另一个方案也说得通
- 引入或换掉一个核心依赖、框架、存储
- 定下一个会扩散到很多文件的约定（金额怎么存、时间怎么表示、错误怎么传）
- 明确否决了一个看起来很自然的做法
不该写的：没有取舍的选择（"用项目已有的 logger"）、随时可以改的局部实现、纯风格问题。
怎么写
- 找到
docs/decisions/里最大的编号，加一。文件名NNNN-用短横线连接的标题.md，标题是结论不是议题——写「金额用整数最小单位存储」，不要写「关于金额存储的讨论」。 - 复制
docs/decisions/template.md，填写。 - 关键在**「其他方案」一节：把认真考虑过的方案写下来，以及放弃它的具体原因**。这一节是 ADR 全部价值所在，只写一句"性能不好"等于没写。
- 如果这个决策会影响日常写代码的方式，在
AGENTS.md加一行指针，正文留在 ADR 里。
只增不改
决策变了不要改旧文件，写一份新的，然后在旧的顶部加一行：
> 已被 [ADR 0007](0007-xxx.md) 取代。
保留被推翻的记录，是为了让后来者知道"这条路走过了"，而不是重新走一遍。
写完检查
- 标题是结论，不是议题
- 「其他方案」里每个被放弃的选项都有具体理由
- 没有写进真实密钥、生产数据或个人信息
- 如果影响日常写法，
AGENTS.md里留了指针
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 · 42 lines · 68 tokens per session scan A a0085accfe53
record-decision is a skill published in the GitHub repository YangFan-Code-Star/context-dev (2 stars, last pushed 14d ago), licensed MIT. It adds 68 tokens to every session and 580 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 2026-08-31.
Other skills, from other repositories
dsh-plugin-dev
开发 DeepSeek Harness (DSH) 插件的标准与权威参考：编写/修改/审查/调试 DSH/Cordis 插件、服务、事件、插件配置、模型工具、LLM 适配器、三种角色拆分、打包安装、workspace 包、cordis.yml 组合时使用；提到 DSH 插件、Cordis、plugin、服务、事件、工具、适配器即触发。 The authoritative standard for developing DeepSeek Harness (DSH) plugins — create, modify, review or debug DSH/Cordis plugins, services, events…
agent-handoff
Cross-platform skill for Codex, Claude Code, and DeepSeek Harness (DSH) that creates, updates, compacts, rotates, repairs, and reviews durable repository handoffs. Use when bootstrapping cross-session memory; creating or maintaining AGENTHANDOFF.md and .agent-handoff files; adding AGENTS.md or .claude/CLAUDE.md rules…
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
storage-analyzer
对 macOS 做一次只读存储分析，产出交互式 HTML 报告。流程：扫描 → 分析分级 → 生成网页 → 打开。.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.