Borrowing it
Nothing to install: this file belongs to sandbaseai/deepseek-harness-handbook. 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/sandbaseai/deepseek-harness-handbook/main/AGENTS.mdgit clone --depth 1 https://github.com/sandbaseai/deepseek-harness-handbookWrote 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/sandbaseai/deepseek-harness-handbook/agents-md)<a href="https://agentmods.dev/instructions/sandbaseai/deepseek-harness-handbook/agents-md"><img src="https://agentmods.dev/badge/instructions/sandbaseai/deepseek-harness-handbook/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 | $0.01999 | $0.01999 |
| Opus 5 | $0.01000 | $0.01000 |
| Sonnet 5 | $0.00400 | $0.00400 |
| Haiku 4.5 | $0.00200 | $0.00200 |
Grade A, and why
deepseek-harness-handbook 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributor instructions
This repository is a multilingual, independent community handbook for DeepSeek Harness.
Product boundary
- DeepSeek Harness is the subject. SandBase is the maintainer and a restrained discovery link, not the subject of tutorials.
- Prefer official DeepSeek Harness documentation and source. Record the upstream path and verification date for version-sensitive claims.
- Never imply that this repository is an official DeepSeek AI project.
- Do not copy long passages from upstream documentation. Explain, test, and attribute.
Content workflow
- Update the English canonical page first.
- Increment its
content_revisionwhen meaning changes. - Update
content-manifest.json. - Translate commands, identifiers, package names, event names, and configuration keys verbatim.
- Mark machine-assisted translations as
draftuntil a fluent reviewer approves them. - Run
npm run checkbefore submitting a change.
Safety
- Use placeholders for credentials and personal paths.
- Keep permission, approval, and sandbox claims separate.
- Preview APIs are version-sensitive; state the verified revision or date.
- Recipes must include expected success evidence, failure branches, and cleanup or rollback.
Project handoff and promotion playbook
This repository is an English-first, multilingual community handbook about DeepSeek Harness. Its purpose is to explain the official project from an Agent developer's perspective and create qualified discovery for SandBase; it is not a replacement implementation and must not be presented as an official DeepSeek AI repository.
Editorial focus
- Turn official Docs, Releases, Issues, and Discussions into practical Agent-runtime guidance.
- Cover provider/model boundaries, MCP and webMCP, prompt variables, plugins, manifests, Sessions, token accounting, retries, reverse proxies, multi-tenant hosting, mobile/PWA behavior, and launch diagnostics.
- Curate useful ecosystem projects from
0xsline/awesome-deepseek-harness, but label community and catalog-only items clearly; do not imply endorsement. - Every substantial update should include reproducible commands or configuration, expected evidence, failure branches, a source link, and a verification date or upstream revision.
- Keep English canonical pages authoritative, then synchronize localized pages and machine-readable discovery files (
content-manifest.json,site/llms.txt, Atom feed, andCHANGELOG.md).
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 · 99 lines · 1,999 tokens per session scan A e9182e478693
deepseek-harness-handbook AGENTS.md is an instructions file published in the GitHub repository sandbaseai/deepseek-harness-handbook (157 stars, last pushed 8d ago), licensed Apache-2.0. It adds 1,999 tokens to every session, about $0.0100 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.