Borrowing it
Nothing to install: this file belongs to xiehuan123/dsh-deepread. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xiehuan123/dsh-deepread/main/AGENTS.mdgit clone --depth 1 https://github.com/xiehuan123/dsh-deepreadWrote 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/xiehuan123/dsh-deepread/agents-md)<a href="https://agentmods.dev/instructions/xiehuan123/dsh-deepread/agents-md"><img src="https://agentmods.dev/badge/instructions/xiehuan123/dsh-deepread/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 5.1 | $0.00876 | $0.00876 |
| Opus 5 | $0.00438 | $0.00438 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
dsh-deepread 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 8d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is an out-of-tree plugin for DeepSeek Harness. Before changing plugin packaging, Cordis wiring, the browser client, or host-facing tests, read docs/deepseek-harness-integration.md.
Upstream authority
- The local upstream checkout is
/Users/xiehuan/Desktop/project/deepseek-harness. Treat its documentation and current source as authoritative; do not infer Harness APIs from this plugin's compatibility shims. - If the upstream checkout contains a usable
.codegraph/index, use CodeGraph before text search. If CodeGraph reports that the index is unavailable, continue with upstream documentation and source. - Do not edit the upstream checkout while working on this plugin unless the user explicitly requests an upstream change.
Plugin identities and source files
- Keep these identities distinct: npm/client-module id
dsh-deepread, Cordis plugin name and tool namedeepread, and patch row iddeepread. src/index.tsandsrc/host/**/*.tsare the Node-half sources.src/client/**/*.tsare the browser-half sources.lib/types/**/*.js,lib/types/**/*.d.ts, andlib/client.jsare generated; never edit them directly.package.jsonownsdsh.bundle,dsh.client,dsh.skills, exports, dependencies, and packed files.cordis.patch.ymlonly mounts the Node half.package.json, the root package inpackage-lock.json,dsh-plugin.json, rootplugin.json,.claude-plugin/plugin.json, and.codex-plugin/plugin.jsonare real version sources and must stay identical. The current dsh-TUI minimum is0.8.1, using the Host-only Community Consensus v0.15 manifest.- The Web client is optional packaging: DeepSeek Harness Web loads
lib/client.js; Harness headless and dsh-TUI load the Host entry and skill without loading browser UI. .codex-plugin/,.claude-plugin/, and rootplugin.jsonare host metadata. They do not install or activate the DeepSeek Harness profile bundle.
Release documentation
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.
- 8d ago First seen · 39 lines · 876 tokens per session scan A a5e81a32c601
dsh-deepread AGENTS.md is an instructions file published in the GitHub repository xiehuan123/dsh-deepread (48 stars, last pushed 5d ago), licensed MIT. It adds 876 tokens to every session, about $0.0044 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.