deepseek-harness / packages
deepseek-ai/deepseek-harness/packages/AGENTS.md
These package-specific rules supplement the repo-wide conventions.
One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
deepseek-ai/deepseek-harness/packages/AGENTS.md
These package-specific rules supplement the repo-wide conventions.
deepseek-ai/deepseek-harness/packages/experimental/AGENTS.md
These rules supplement the package rules. The experimental publication decision owns the publication policy; the Agent Teams package decision owns dependency isolation and promotion rationale.
deepseek-ai/deepseek-harness/packages/experimental/webworker-runtime/tests/fixtures/vfs-example/workspace/.agents/skills/preview-tour/SKILL.md
Inspect the bundled Preview workspace and its deterministic Session examples.
deepseek-ai/deepseek-harness/packages/preset/agent-preset/skills/cordis-composition-reference/SKILL.md
Use when writing or reading a Cordis bundle patch or agent preset for this harness and you need the Loader YAML dialect (insert, override by id, group, disabled, isolate, !!js) or the list of installable Harness plugin packages and what each provides.
deepseek-ai/deepseek-harness/packages/preset/agent-preset/skills/cordis-plugin-development/SKILL.md
Use when adding, enabling, disabling, installing, configuring, or debugging a plugin, bundle, feature, page, panel, tool, or MCP connection in the current Harness profile, including a shipped plugin that is disabled by default, and for any visual object, decoration, or widget request that names no other destination, which means an installed UI plugin rendered in the Harness Web UI.
deepseek-ai/deepseek-harness/packages/preset/agent-preset/skills/editing-cordis-compositions/SKILL.md
Use when creating, changing, or validating an agent preset or other Cordis composition for this harness, including deciding host versus preset placement and checking that an authored preset mounts.
deepseek-ai/deepseek-harness/packages/schedule/AGENTS.md
These rules supplement the repository and package instructions for packages/schedule/*.
deepseek-ai/deepseek-harness/packages/skill/skill-office/assets/office-docx/SKILL.md
Create, read, edit, and check Word documents (.docx), including reports, letters, and formatted tables. Use when a DOCX file is an input or requested deliverable. Load this skill before running Office commands. Use only bundled LibreOffice unless the user explicitly opts out; without that opt-out, do not search for another LibreOffice executable.
deepseek-ai/deepseek-harness/packages/skill/skill-office/assets/office-pptx/SKILL.md
Create, read, edit, and check PowerPoint presentations (.pptx), including slide text, tables, images, and charts. Use when a PPTX file is an input or requested deliverable. Load this skill before running Office commands. Use only bundled LibreOffice unless the user explicitly opts out; without that opt-out, do not search for another LibreOffice executable.
deepseek-ai/deepseek-harness/packages/skill/skill-office/assets/office-xlsx/SKILL.md
Read, create, and modify Excel workbooks (.xlsx), including data, formulas, formatting, and pandas analysis. Use for Excel inputs or deliverables. Load before running Office commands. Data and formula tasks skip visual inspection; inspect only for formatting or layout needs. Use only bundled LibreOffice unless the user explicitly opts out; without that opt-out, do not search for another LibreOffice executable.
deepseek-ai/deepseek-harness/packages/web/AGENTS.md
These rules supplement the package conventions in packages/AGENTS.md.
deepseek-ai/deepseek-harness/scripts/AGENTS.md
Gate scripts invoke pnpm shell-free, normalize repository-relative glob paths to / at ingestion, and keep platform adaptation in the gate that needs it instead of a shared platform layer. Source-ownership gates use syntax-aware discovery, guard against an empty or narrowed corpus, and test every admitted/excluded form that changes their detection boundary. Script specs run in forked workers beside the rest of the suite and beside the other gate processes in their job, so own every port, temporary path, and child…
deepseek-ai/deepseek-harness/snapshots/AGENTS.md
This tree contains only tests whose committed session JSONL is replay input and expected persisted output. Keep non-session ARIA, geometry, generator, CLI, and unit expected output with its owning app, script, or package; use test:expected, test:web, or test for its owning tier. Every process under test starts through the dsh CLI with a shipped profile and optional scenario patches. Test clients may drive a public protocol or browser interface; do not add another application entrypoint, hidden CLI mode, or executable…
deepseek-ai/deepseek-harness/snapshots/session/agent-instructions/workspace/AGENTS.md
AGENTS.canonical.md
deepseek-ai/deepseek-harness/snapshots/session/ptc-workspace-context/workspace/AGENTS.md
Workspace snapshot root instruction.
deepseek-ai/deepseek-harness/snapshots/session/ptc-workspace-context/workspace/nested/AGENTS.md
When asked for the Code Mode workspace handshake, answer exactly CODEMODECONTEXT_OK and nothing else.
deepseek-ai/deepseek-harness/snapshots/session/skill-load/workspace/.dsh/skills/model-only-skill/SKILL.md
Prove user-disabled skills remain available to the model.
deepseek-ai/deepseek-harness/snapshots/session/skill-load/workspace/.dsh/skills/snapshot-skill/SKILL.md
Exercise project skill discovery and loading in snapshot tests.
deepseek-ai/deepseek-harness/snapshots/session/skill-load/workspace/.dsh/skills/user-only-skill/SKILL.md
Prove model-disabled skills stay outside the model catalog.
deepseek-ai/deepseek-harness/website/AGENTS.md
Follow the root instructions, the documentation standard, and the documentation workflow. website/ owns only VitePress configuration, presentation assets, and the publication manifest. This file is the only maintained Markdown file in this subtree. Keep canonical prose and generated catalogs in their owning docs/ tier, then expose selected pages through docs.ts. Never add locale, route, API, or copied documentation trees such as website/zh-CN/, website/en/, or website/api/. The projector writes disposable Markdown to the ignored website/.generated/ directory. Never edit or commit .generated/,…
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.