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/sparkelf/deepseek-harness-plus/agents-mdgit clone --depth 1 https://github.com/SparkElf/deepseek-harness-plusWrote 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/sparkelf/deepseek-harness-plus/agents-md)<a href="https://agentmods.dev/instructions/sparkelf/deepseek-harness-plus/agents-md"><img src="https://agentmods.dev/badge/instructions/sparkelf/deepseek-harness-plus/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 | $0.03255 | $0.03255 |
| Opus 5 | $0.01628 | $0.01628 |
| Sonnet 5 | $0.00651 | $0.00651 |
| Haiku 4.5 | $0.00326 | $0.00326 |
Grade A, and why
deepseek-harness-plus 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 2d 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.
This is a copy
92% identical to deepseek-harness AGENTS.md — 121 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
DeepSeek Harness is an all-plugin Cordis agent harness. Read docs/architecture.md before changing packages/; follow docs/AGENTS.md for documentation.
Pre-release stance: foundation over blast radius
Remove at the first tagged release. Until then, prefer foundations to compatibility shims: rename freely and update every reference. Backends reject old formats. SQLite uses monotonic SCHEMA_VERSION; dsh-session keeps SESSION_FORMAT_VERSION at 0 without compatibility promises.
Application launch. Only dsh profiles launch supported Node apps; package bins, demos, and public SDK argv escapes are forbidden (rule).
Security and defensive design are opt-in. Do not introduce either without explicit user authorization for the current task; this rule overrides default hardening guidance.
Repository layout
vendor/ Cordis source; see vendor/README.md
packages/ workspaces at packages/<group>/<pkg>/
core/ session, prompt, tools, agent, loop
api/ BFF and Typert RPC gateway
typert/ type graph, loader, registry
llm/ model interfaces and providers
e2b/ remote sandbox adapters
shell/ bash/pwsh providers and tools
subprocess/ process capability and Win32 library
terminal/ persistent sessions
fs/ lsp/ web/ skill/ context/ compaction/
subagent/ workflow/ webhook/ todo/ plan/ preset/ guard/
bundle/ boot/ sdk/ examples/ interaction/ hooks/
session/ identity/ settings/ credentials/ acp/
self-modification/ experimental/ support/ util/
python/ Python SDK and runtime
native/ native package sources
.agents/ workflows and Agent Notes
docs/ architecture and references
scripts/ gates and generators
website/ VitePress projection
Package groups: packages/README.md.
Commands
pnpm install
pnpm run clean
pnpm run test
pnpm run test:coverage
pnpm run test:e2e
pnpm run test:expected
pnpm run test:snapshot
pnpm run test:snapshot:record
pnpm run typecheck
pnpm run lint
pnpm run duplication
pnpm run build
pnpm run hygiene
pnpm run check:windows-wine # only for a known Windows failure
pnpm run doc-sync
pnpm run test:docs
pnpm run website:build
pnpm dsh --profile headless "task"
pnpm run demo:ptc -- "task"
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.
- 2d ago Changed · -17 lines · -484 tokens per session fce7c05a2ad8
- 5d ago First seen · 157 lines · 3,739 tokens per session scan A 18c161851860
deepseek-harness-plus AGENTS.md is an instructions file published in the GitHub repository SparkElf/deepseek-harness-plus (2 stars, last pushed yesterday), licensed MIT. It adds 3,255 tokens to every session, about $0.0163 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to deepseek-harness AGENTS.md, differing in 121 lines, and is treated as a copy.
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.
cocode AGENTS.md
AGENTS.md instructions for cocode-agency/cocode, covering agents.md, 仓库布局, 仓库边界, cocode-gui/ and cocode-tui/.
dsh-TUI CLAUDE.md
Claude Code instructions for ccch1mneyyy/dsh-TUI, a project described as: DSH 官方公众号收录的 TUI 补位插件：Claude Code 风，鲸鱼顶栏/实时状态/流式思考/双击 Esc 回滚/上下文进度+TPS。npm 一键装。 DSH official WeChat featured TUI plugin — Claude Code style: whale bar, live status, streaming thoughts, double-Esc rollback, context bar + TPS. npm one-click.
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）.
Tianshu-harness CLAUDE.md
Claude Code instructions for huiliyi37/Tianshu-harness, covering 天枢 (tianshu) / rivet, build & test, architecture, conventions and known constraints.