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/stvlynn/dsh.fish/claude-mdgit clone --depth 1 https://github.com/stvlynn/dsh.fishWrote 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/stvlynn/dsh.fish/claude-md)<a href="https://agentmods.dev/instructions/stvlynn/dsh.fish/claude-md"><img src="https://agentmods.dev/badge/instructions/stvlynn/dsh.fish/claude-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 | $0.02064 | $0.02064 |
| Opus 5 | $0.01032 | $0.01032 |
| Sonnet 5 | $0.00413 | $0.00413 |
| Haiku 4.5 | $0.00206 | $0.00206 |
Grade A, and why
dsh.fish CLAUDE.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 5d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Coding Guidelines
Language- and framework-agnostic template for agent-driven projects.
Read this file first. Then follow the documentation map below before writing any code.
⚠️ Before you start
- Read the docs first. Do not assume conventions; this project is documented so agents do not have to guess.
- Ask when boundaries are unclear. If a requirement, layer boundary, business rule, or technology choice is ambiguous, ask the user before proceeding.
- Check logs and docs before inventing workarounds. When something does not behave as expected, inspect logs, tests, and the relevant
docs/file. Do not add fallback logic to bypass a problem you have not understood.
Documentation map
Understand the project
docs/README.md— top-level index and domain map.docs/project/README.md— project overview, goals, and tech-stack placeholders.docs/project/architecture.md— system architecture, module boundaries, and data flow.
Write frontend code
docs/frontend/README.md— Feature-Sliced Design (FSD) entry point.docs/frontend/fsd-overview.md— what FSD is and why it is used here.docs/frontend/layers.md— responsibilities ofapp,pages,widgets,features,entities,shared.docs/frontend/slices.md— how to split code into slices.docs/frontend/segments.md—ui,model,lib,api,configsegments.docs/frontend/public-api.md— public API and re-export rules.docs/frontend/import-rules.md— cross-layer and cross-slice import rules.docs/frontend/ui-patterns.md— semantic styling, no hardcoded copy, no redundant copy.docs/frontend/i18n.md— locales, message catalogs, locale-aware links and loaders.
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.
- 5d ago First seen · 168 lines · 2,064 tokens per session scan A 8ec0b3a389c0
dsh.fish CLAUDE.md is an instructions file published in the GitHub repository stvlynn/dsh.fish (2 stars, last pushed yesterday), licensed MIT. It adds 2,064 tokens to every session, about $0.0103 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
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）.
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.
awesome-deepseek-harness-plugins AGENTS.md
AGENTS.md instructions for imsai-sh/awesome-deepseek-harness-plugins, covering repository instructions, the submission gate is the product, generated files, cross-repo contracts (no ci spans both repositories) and permanent urls.
dsh-launcher AGENTS.md
AGENTS.md instructions for Ruler4396/dsh-launcher, covering agents.md — 对本仓库中所有 ai agent 的强制指示, 🚨 第一优先：架构铁律（不读就动代码 = 违规）, 🔥 快速合规清单（动代码前自检）, 🧭 项目地图（定位代码） and ✅ 完成后必须自查.