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 cordis-composition-referencegit 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/cordis-composition-reference)<a href="https://agentmods.dev/skills/deepseek-ai/deepseek-harness/cordis-composition-reference"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/cordis-composition-reference/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/cordis-composition-reference"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/cordis-composition-reference.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.00640 |
| Opus 5.5 | $0.00024 | $0.00256 |
| Sonnet 5.5 | $0.00012 | $0.00128 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
cordis-composition-reference 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 23d 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
1 near-identical copy found in the catalogue:
- cordis-composition-reference — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cordis composition reference
Reference material for bundle patches and preset plugin lists. Procedures live in cordis-plugin-development and editing-cordis-compositions.
Loader patch dialect
A profile composes an ordered list of patch layers over the bundle entry lists. Each patch is a mapping:
insert: [rows]appends rows; with anidnaming an existinggroup: truerow, the rows are appended inside that group'sconfiglist.- A patch with an
idand noinserttargets the existing row with that id. Supplied fields replace the row's fields;configis replaced wholesale, never deep-merged, so restate every field the row needs. A truthynameasserts the existing plugin name rather than renaming it. - Non-insert patches without a nonempty
id, and targets that match no row, are warned about and skipped.
A row has id, name (the plugin package specifier; inserted relative paths are anchored beside their patch file), optional config, and optional disabled, inject, intercept, and isolate.
group: truewithname: cordis:groupmakesconfiga nested entry list and allows patches to insert into it by id.cordis:includeloads a literal YAML or JSON entry list fromconfig.path.disabledaccepts a boolean, null, or a!!jsexpression evaluated against the Loader context at every mount decision. A disabled row omits requiredconfigunlessgroup: trueforces activation.!!jsscalars are Loader expressions, never!js. Insideconfigthey are evaluated after the row's declared injections activate, against that plugin's context (ctx.<service>), so!!js dshHomePath('sessions')and!!js "!ctx.get('profileContext')"are valid. Other row metadata stays literal.isolatemaps service names totrueor a realm label; a preset plugin that provides a service isolates the provider and all consumers together. Scope controls contributions and event visibility;isolatecontrols service instances.
plugin_manager list_plugins reports each row's enabled flag and fiberPhase; set_plugin and set_bundle answer overridden when a higher-priority layer wins.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago First seen · 30 lines · 59 tokens per session scan A 6583a81d9f4d
cordis-composition-reference is a skill published in the GitHub repository deepseek-ai/deepseek-harness (250,433 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 640 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 2026-09-23.
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.