component or state, conversation or Session behavior, or lifecycle, concurrency, subprocess, and teardown code. Its [review principles](docs/defensive-patterns/README.md#why-these-rules) apply per artifact.
## Type safety and documentation
Everything compiles
Steady2 mentions in 2 weeks
No other project uses it yet
282k3mo agoReviewMountCreate a free account to mount
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auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, deletes small UI and purely mechanical records, classifies other implemented notes by future decision value, deletes rejected notes that no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 and review DSH user-visible UI: alignment, spacing, icons, visual foundation, geometry and interaction. Use before UI changes in client, experimental and app packages; verify affected rendered results before handoff.
Steady2 mentions in 2 weeks
4 projects use a version of this
282k3mo agoReviewMountCreate a free account to mount
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.
Steady2 mentions in 2 weeks
No other project uses it yet
282k3mo agoReviewMountCreate a free account to mount
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 creating a deepseek-harness pull request, or when updating its description after later changes or a handled review round. Defines each description section, Issue references, test design, change-specific disclosures, and the AI Usage section with its levels, stages, grading rules, AI-DECLARATION badge, and update timing.
Steady2 mentions in 2 weeks
No other project uses it yet
282k3mo agoReviewMountCreate a free account to mount
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.
Steady2 mentions in 2 weeks
6 projects use a version of this
282k3mo agoReviewMountCreate a free account to mount
Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.
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`; publication requires gh v2.99.0 or later, and a GIF over 5 MiB is split into parts. 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.
timing, ownership, modality, exceptions, consequences, and non-obvious orientation; delete narration, test walkthroughs, review analysis, and code restatement. Keep the local contract and link its rationale. Use [dsh-prose-standard
Steady2 mentions in 2 weeks
No other project uses it yet
282k3mo agoReviewMountCreate a free account to mount
packages have one independent version and release workflow.
## Runtime rules
- Landlock's argv, exit codes, diagnostics, and fail-closed confinement are defined in [docs/cli-contract.md](docs/cli-contract.md). Do not change them when
Steady2 mentions in 2 weeks
No other project uses it yet
282k3mo agoReviewMountCreate a free account to mount
current design; these are the rules you must not violate when writing or reviewing client code:
1. **Two declaration forms**: use `ctx.slots.register({ name, children?, store?, inject? }, Component)` for a parent
Steady2 mentions in 2 weeks
No other project uses it yet
282k3mo agoReviewMountCreate a free account to mount
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.
Steady2 mentions in 2 weeks
1 project uses a version of this
282k3mo agoReviewMountCreate a free account to mount
name == ...` chain); `tools/todo_tool.py` is the pattern.
## Message-flow invariants (every change is reviewed against these)
- **Prompt caching must not break.** Never alter past context, change toolsets, reload memories,
or rebuild
1 project uses a version of this
264k2d agoReviewMountCreate a free account to mount
core.
Two invariants shape almost every design decision and are the lens for reviewing any change:
- **Per-conversation prompt caching is sacred.** Mutating past context, swapping toolsets,
reloading memories
No other project uses it yet
264k2d agoReviewMountCreate a free account to mount
pool is keyed by home
(`cron.max_parallel_jobs` is per profile); and the stale-code yield gate asks
`scheduler_ownership.owns_cron_tick_for(home)` / `live_gateway_ticking(home)` instead
1 project uses a version of this
264k2d agoReviewMountCreate a free account to mount
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.