DeepSeek Harness is an open-source framework for building and running AI agents, organized so that its functionality is provided through plugins. Developers use it to launch agent workflows through a local web interface or from source, while the catalogue add-ons extend the harness as plugins.
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 skills add deepseek-ai/deepseek-harness --skill editing-cordis-compositionsgit clone --depth 1 https://github.com/deepseek-ai/deepseek-harnessWrote 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/skills/deepseek-ai/deepseek-harness/editing-cordis-compositions)<a href="https://agentmods.dev/skills/deepseek-ai/deepseek-harness/editing-cordis-compositions"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/editing-cordis-compositions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/deepseek-ai/deepseek-harness/editing-cordis-compositions"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/editing-cordis-compositions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00041 | $0.01278 |
| Opus 5.5 | $0.00016 | $0.00511 |
| Sonnet 5.5 | $0.00008 | $0.00256 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
editing-cordis-compositions 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 1mo 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- editing-cordis-compositions — 100% identical, 183 lines differ
- editing-cordis-compositions — 100% identical, 183 lines differ
- editing-cordis-compositions — 97% identical, 172 lines differ
- editing-cordis-compositions — 97% identical, 172 lines differ
- editing-cordis-compositions — 97% identical, 172 lines differ
- editing-cordis-compositions — 97% identical, 172 lines differ
- editing-cordis-compositions — 95% identical, 18 lines differ
- editing-cordis-compositions — 84% identical, 144 lines differ
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editing Cordis compositions
Agent presets are ordinary @deepseek-ai/dsh-agent-preset declarations carried by bundle patches. Nothing edits a declaration in place: a preset is created or changed by installing a bundle whose patch declares or overrides it. This file states the declaration format; when it leaves a question open, read the @deepseek-ai/dsh-agent-preset README and lib/types declarations under the packageDir that cordis_inspect_query Config.listConfigs returns when queried with a preset-<id> row's entry id, or packages/preset/agent-preset/src in a source checkout.
Where declarations live
The shipped Web presets are presets/<id>.patch.yml files of the @deepseek-ai/dsh-web-app bundle, ids standard, ptc, minimal and cordis. Installed, the bundle resolves from the dsh installation, not the profile; querying Config.listConfigs with the entry id of any preset-<id> row it declares returns that packageDir. In a source checkout of DSH it is packages/bundle/web-app/. Read one file with the file-read tool when you need a template; minimal.patch.yml is the shortest. In Desktop the bundle sits inside app.asar, which shell commands cannot open. Load cordis-composition-reference for the patch dialect and the list of plugin packages a preset can mount.
A declaration row has these config fields: id (required, lowercase letters, digits and hyphens), plugins (required Cordis entry list), and optional name, description and order (roster position). The Loader row id is preset-<id> by convention.
Create a preset
Write a bundle directory in the workspace with exactly two files, then install it.
review-preset/package.json:
{
"name": "@local/dsh-review-preset",
"version": "1.0.0",
"private": true,
"type": "module",
"dsh": { "bundle": { "patch": "./cordis.patch.yml" } }
}
review-preset/cordis.patch.yml:
- insert:
- id: preset-review
name: '@deepseek-ai/dsh-agent-preset'
config:
id: review
name: Review
description: Reviews changes with the shell only.
order: 10
plugins:
- id: persona
name: '@deepseek-ai/dsh-persona'
config:
prefix: You review software changes.
- id: tool-bash
name: '@deepseek-ai/dsh-tool-bash'
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.
- 1mo ago Changed · -18 lines · -28 tokens per session 974cc1e115bf
- 1mo ago Changed · -63 lines dbf68650fc61
- 1mo ago Changed 6f5a82eebfe6
- 1mo ago First seen · 166 lines · 69 tokens per session scan A 861b3b8b7983
editing-cordis-compositions is a skill published in the GitHub repository deepseek-ai/deepseek-harness (261,388 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 1,278 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
industry-research-method
A Chinese-language method for researching an industry by mapping its supply chain, tracking policies and news, and writing sourced reports. It separates the chain into upstream inputs, midstream production, and downstream distribution or use.
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.