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 instructions/tsrigo/dsh-from-scratch/agents-mdgit clone --depth 1 https://github.com/tsrigo/dsh-from-scratchWrote 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/instructions/tsrigo/dsh-from-scratch/agents-md)<a href="https://agentmods.dev/instructions/tsrigo/dsh-from-scratch/agents-md"><img src="https://agentmods.dev/badge/instructions/tsrigo/dsh-from-scratch/agents-md.svg" alt="Measured on agentmods" 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 | $0.00526 | $0.00526 |
| Opus 5 | $0.00263 | $0.00263 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
dsh-from-scratch AGENTS.md 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 4d 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.
What it actually says
DSH 维护约定
固定章节名称
教程的六个章节名称必须保持以下写法，不得改写、替换成概括性标题或自行重命名：
第一章·Agent LoopDSH 的 Agent Loop 是什么样的?
第二章·上下文与缓存复用上下文是怎样组织的，为缓存复用做了什么优化？
第三章·一切皆插件如何实现“一切皆插件”？
第四章·让运行有迹可循DSH 怎么记录和保存 Agent 执行过程?
第五章·运行时自进化DSH 是如何持续自进化的?
第六章·长程任务续行DSH 是如何持续完成长程任务的？
关于 deepseek-harness-from-scratch 的更多信息，请参见 ./deepseek-harness-from-scratch/README.md 和 ./deepseek-harness-from-scratch/AGENTS.md 。
先专注 ts 版本，python 先不管
关于文本风格：
用 https://github.com/oil-oil/oil-tone 润色一遍。
此外：
- 尽量少用不是...而是...的句型，很多时候它被用来“硬凑”对仗和高级感，前后的 A 和 B 并没有提供真正的干货或深刻洞察。 也不使用“是 X，不是 Y”的对比句式。
- 少用引号、破折号。缺乏具体肉身记忆与在地情感的装腔格式，缺乏人味。
- 不常见的缩写，需要给出全称与解释。
- 尽量不要使用比喻。如果一个说法需要读者推断其指代对象，改为直接说明。
- 也不使用拟人表述。
- 自包含，不要突然冒出来一个概念
追求：简明，有逻辑，coherent ，自包含，有层次，逻辑通顺
注意，不要通过降低信息量的方式来换取简洁。
不能修改章节标题和问句，这是我钦定的。
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.
- 4d ago First seen · 42 lines · 526 tokens per session scan A 460931608f9c
dsh-from-scratch AGENTS.md is an instructions file published in the GitHub repository tsrigo/dsh-from-scratch (10 stars, last pushed 18d ago), licensed MIT. It adds 526 tokens to every session, about $0.0026 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 instructions, from other repositories
dsh-TUI AGENTS.md
AGENTS.md instructions for ccch1mneyyy/dsh-TUI, covering agents.md, 仓库布局, 命令, 上游边界与契约 and 约定与红线.
DSH-better-sidebar AGENTS.md
AGENTS.md instructions for omdsh-dev/DSH-better-sidebar, covering dsh-better-sidebar 仓库规则（agents）, 1. 仓库硬约束（必须遵守）, 2. ci 挂载冒烟（plugin-mount job / pnpm test:mount）, 3. dsh 0.1.2 适配要点（0.1.2-rc.1+ 基线） and 4. npm 发版（github release → npm publish）.
dsh-worktable AGENTS.md
Instructions for Aisland-SJL/dsh-worktable, covering dsh-worktable 项目规则, 协作方式（用户定案，最高优先级）, 边界, 构建与验证 and 领域约定（会话中必须遵守）.
modsearch AGENTS.md
AGENTS.md instructions for liustack/modsearch, covering project overview (for ai agent), goal, technical approach, code organization and skills directory.
DeepSeek-Harness-Desktop AGENTS.md
Instructions for web-casa/DeepSeek-Harness-Desktop, covering agents.md — dsh desktop, 项目本质, 不可违背的安全不变量, 版本单一事实源（改动版本时必须同时改全部） and harness 升级启动契约（bump pin 前必读）.
deepseek-harness-handbook AGENTS.md
AGENTS.md instructions for sandbaseai/deepseek-harness-handbook, covering contributor instructions, product boundary, content workflow, safety and project handoff and promotion playbook.