Plugins

Lazy capability catalog for DeepSeek Harness: one compact index plus search/describe/call meta-tools for MCP tools and skills, instead of every schema on every request

Shows which graft index a dsh session is serving and whether it still matches the code, and gives the model graft_ask, graft_grep, graft_callers, graft_skeleton and graft_map as native tools.

Governed long-term memory for DeepSeek Harness: append-only evidence ledger with write guards, 7-tier authority claims, supersede chains, and budgeted pre-step injection with per-domain quotas.

Superself's self CLI as model-facing tools (project context, work units, reports, decisions) plus a /self command — cross-session, cross-project project state kept outside the code repo.

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

Reversible context folding plus external memory for DeepSeek Harness: tool output collapses into expandable lines, session facts become auditable records.

DSH 工作区记忆画像：有证据、有版本、能解释变化；索引简报省 token、轮末本地召回、红线 / 审批队列 / 版本链 / 注入审计；零依赖、不出站。

Context governance for DSH: folds oversized tool results, collapses the tool surface and keeps the prompt cache warm, so long sessions stop getting more expensive.

Long-term memory scoped to the DSH workspace. A session opens with a one-line-per-memory index - bodies are fetched on demand by the `memory` tool, so the same character budget holds about three times as many entries - and when a turn ends a purely local search over the last user message pulls the matching memories into the next briefing at no model cost. Optional auto-capture distils a stretch of conversation into structured memories; in draft mode they wait in an approval queue instead of landing directly. A portrait layer keeps a workspace and a global picture, rewritten from the journal and the records, with the same draft-or-direct choice. Settings → Memory holds the archive, list and timeline views, a health check (duplicate clusters, stale entries, broken links), the supersede version chain with rollback, and a read-only scan that imports existing WorkBuddy / Qoder memory files.

Merges other sessions' context into the current turn: evidence-weighted conflict resolution, retraction of claims whose premises were retracted, trust labelling that resists cross-session prompt injection, and budget-bounded packing. Ships a benchmark.

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.

DeepSeek Harness plugin: Superself's `self` CLI as model-facing tools plus a /self command — cross-session, cross-project project state for agents.

Local task checkpoints and bounded recovery for DSH, with optional L0–L3 hierarchical memory, dependency-aware retrieval, prerequisite-aware context, and six opt-in memory tools.

Project-scoped SQLite memory with progressive retrieval, bounded context, a composer button and visual review. Install the repository-root DSH bundle, then run /learning-init with an absolute project path using local Python 3.10+.

DeepSeek Harness (Cordis) plugin — bi-temporal VSA memory + cognition engine + BLAKE3 provenance, exposed as a DSH storage+session plugin. End-to-end tested with a real Python subprocess.

Externalizes oversized assistant and tool messages in long sessions into project files while keeping a recent window, and archives reasoning from empty turns as a visible message so long tasks do not stall on context size.

Sidebar GitHub panel plus github_* agent tools: list your repositories, inspect issues and pull requests, and create, update or comment on issues.

Health check for a DSH profile: scores skills and agent instruction files, subagent definitions and presets on one shared 18-bucket S–E grade scale, with a sidebar panel, four dsh360_* tools, and a backup with undo for every write.

Continuous dictation for the composer using a local SenseVoice ONNX model on CPU: recognised text appears while you speak, a pause ends the sentence and writes it into the input box, and audio never leaves the machine.

Session archive with tags, notes and per-session metrics, plus a Plan-Do-Check-Act loop over the archived sessions that produces prompt and AGENTS.md rules and re-measures them on later sessions. Runs locally without calling a model.

Infinite-canvas mind map in the sidebar: grow nodes with Tab, tidy a branch into a tree, ask the assistant to expand a node into child ideas, and export to Markdown, OPML, FreeMind, JSON or PNG.

Intercepts DSH tool results before the model reads them: dedupe cache for repeated calls, a declarative decision graph that replaces large outputs with structured digests, an injection gate, and an honest token ledger that includes a negative-return account for over-compression. Measured 1400-1600 tokens saved per hit; the cumulative ledger is currently negative and the README says why, including that it cannot skip model turns.

Fork of kirkchinese/dsh-capability-catalog 0.1.4 (cannot be installed alongside the upstream capability catalog / @kirkchinese/dsh-rea): a REA-focused MCP gateway with three fixed search, describe and call tools, cached schemas, session controls and native DSH result handling. Requires DSH 0.2.1-rc.4 or 0.2.2-rc.1 and a Node/npm setup able to run REA.

Dormant-by-default MCP for dsh: one mcp_summon tool; summoning a server registers its tools as real native mcp__<server>__<tool> tools for the rest of the session, and release unregisters them and stops the process.