DeepSeek Harness is an all-plugin Cordis agent harness. Read docs/architecture.md before changing packages/; follow docs/AGENTS.md for documentation. Public APIs are pre-stable; update every consumer. Follow version/status and type acknowledgements. Adjacent migration may add a version-named successor but never move, overwrite, or delete committed generations; predecessors imply neither fallback nor downgrade support. SQLite uses monotonic SCHEMA_VERSION. Acknowledge declared persistence-type changes. Application launch. Only dsh profiles launch supported Node apps; package bins, demos, and public SDK argv escapes are forbidden (rule). Package…
Agent Notes are effectively RFCs written by agents: durable proposals and decision records that preserve rationale, alternatives, consequences, and required verification. Follow the documentation standard and the Agent Note rules. Every new Agent Note triggers a supersession check. Search the active tree for older notes covering the same decision or mechanism, classify any full or partial supersession with dsh-archive-agent-notes, and archive every qualifying implemented triplet in the same PR. Keep partial supersessions active and cross-linked. Files under archived/ are frozen…
Archived Agent Note triplets under the kind directories are frozen historical snapshots, not current authority. Never edit, reformat, translate, repair, delete, or move a sealed artifact; use an active Agent Note or current documentation for new decisions and facts. The archival change may only relocate a complete English/Chinese/sidecar triplet, insert the identical Archived: YYYY-MM-DD line below both Status: implemented lines, re-record the sidecar, and repair or delete inbound links. Do not inspect, verify, or repair links out of archived notes.
These Agent Notes describe shipped decisions. Follow the root instructions, documentation standard, and Agent Note format; verify-agent-note-format gates the lifecycle-specific structure. Keep paths, symbols, defaults, and mechanisms current in the same change that alters them. Rewrite stale facts in place; do not append change history. When a shipped note is unlikely to guide future work, archive its complete triplet through dsh-archive-agent-notes instead of continuing to maintain it. Update factual realization in place. A reversal of the decision or its rationale…
Use when writing or changing a model-facing tool definition (name, description, parameter schema, or its system-prompt section), and when designing skills, context loading, or multi-step workflows, to make information discoverable and use context efficiently.
Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, deletes small UI and purely mechanical records, classifies other implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind} triplet and manifest rules.
Design, review, and diagnose DeepSeek Harness tests and fixtures that can fail nondeterministically under CI concurrency, shared host resources, clocks, process-global state, subprocesses, network listeners, or asynchronous teardown. Use when adding or changing tests with those risks, investigating flaky CI, or reviewing test isolation; use dsh-pre-push-checks separately to select outgoing commands.
Design and review DeepSeek Harness client UI changes — visual token discipline, reuse-before-adding, feedback surfaces (toast vs in-place notice vs empty state), overlay and menu safety, platform window adaptation, loading states, and error copy placement. Use when adding or changing product-user-visible GUI behavior in packages/client, or when reviewing such a PR.
Use when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the review-specific checks that code alone can't show
Create, restructure, review, audit, or migrate DeepSeek Harness Markdown documentation, package READMEs, and the documentation website using audience-first hierarchy, kind-mapped YAML metadata, bilingual line alignment, summary/contents navigation, progressive user-to-developer detail, executed-operation fact-checking, and repository validation. Use for new or revised DSH docs, docs-tree organization, documentation-quality audits and budgets, website page publishing, and bilingual documentation structure changes.
Find evidence-backed simplifications in DeepSeek Harness code, APIs, configuration, tests, and prose; write or consolidate proposals, identify small inline cleanups, or assess simplifications from another branch. Use for removing dead, duplicated, speculative, or unnecessarily maintained behavior and infrastructure.
Use when landing a stack of dependent GitHub PRs (A ← B ← C, where each bases on the one below) onto master, merging a PR whose base is another open PR's branch, or whenever a request mentions "stacked PRs", "PR stack", "dependent PRs", or merging several related PRs in sequence. Requires every same-repository dependency chain to use GitHub's official stacked-PR feature before landing so GitHub owns stack-wide rules, CI, ordering, retargeting, and merge state.
Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and immediately after gh stack sync publishes rewritten branches, to select the smallest tests and checks that cover the outgoing or just-published diff without reflexively running the full repository suite.
Use when writing, reviewing, restoring, trimming, or auditing prose in the deepseek-harness repo, including deciding where documentation or comments are required across Markdown, JSDoc, code and test comments, prompts, descriptions, diagnostics, and CLI or UI strings.
Use when investigating or optimizing DeepSeek Harness performance, designing realistic synthetic benchmarks or CI performance gates, profiling long Sessions or Web responsiveness, or turning performance PR evidence into measured behavior-preserving fixes.
Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.
Use when auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as (decision N), audit item codes, or §N of uncommitted drafts; change narration such as "used to", "no longer", "this cut"; stack or review vantage ("a later PR in this stack", "rejected in review"); reviewer-addressed justifications; control-flow narration; or hedged planning residue in comments, JSDoc, docs, or Agent Notes.
Record browser or Web UI interaction demos as optimized GIFs using the available browser-control workflow, optional Playwright Videos for higher capture frame rates, and deterministic encoding, then attach the GIF to a pull request with `gh --attach`, falling back to a dedicated assets branch where attach cannot apply. Use when asked to make, record, or generate a GIF that demonstrates a browser workflow, and for every pull request that changes product-user-visible GUI behavior, which MUST include a GIF recorded from the pull request's real server and model flow.
This tree owns cross-package behavior of shipped dsh profiles. Start product scenarios through apps/cli/src/bin.ts with --profile <name> or the <name> shorthand; a test-only Loader driver is allowed only when the public profile output cannot expose the asserted internal evidence. Keep a composition here only when the CLI profile assembly is the subject. Move package-specific Loader configurations and drivers into that package's tests/fixtures/. Recorded-session replay belongs under top-level snapshots/; other expected output uses *.expected.e2e.ts and an owner-local expected/ directory. User-facing optional…
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 or AGENTS.md?
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.
What is a skill?
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.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
DeepSeekAGENTS.md