Plugin marketplace

context-kit

Fifteen context-engineering plugins for GitHub Copilot, APM, and Claude Code: retrieval modalities, hybrid local RAG, durable memory, decision-corpus governance, orchestration, steering, verification, multi-lens review, exhaustive corpus review, runtime evidence, token economics, handoff, and portable plugin authoring.

1 · mbeacom/context-kit15 pluginsMITupdated 17 days ago

Add this marketplace

Then install any plugin below by name — each page has its exact command.

memory

claude

Provenance-bound durable memory with immutable records, append-only review state, active-only recall, and offline semantic recall via a first-party rag provider.

1 skill · 4 commands · 1 MCP server · hooks

1

Portable, bounded, verified task-state handoffs with manual write/resume commands, a read-only compiler, and deterministic validation.

1 skill · 2 commands · 1 agent

1

Measure agent token usage from local host records, and settle tool savings claims with controlled A/B runs that require a preserved answer.

2 skills · 2 commands

1

verify

claude

Read-only claim verification and prospective change-impact analysis with per-claim verdicts, blast-radius mapping, and file:line evidence.

2 skills · 1 command · 1 agent

1

Exhaustive review of a corpus too large to read at once: hashed unit inventory, bounded resumable shards, and a coverage ledger that separates a real gap from an undecidable one.

1 skill · 1 command · 1 agent

1

Multi-lens evaluative review: independent adversarial, architect, consumer, and operator charters return typed findings that merge on agreement and preserve disagreement as an explicit tradeoff.

1 skill · 1 command · 1 agent

1

Plan-big / execute-small orchestration: a strong model plans and delegates token-heavy work to cheaper subagents.

1 skill · 1 command · 1 agent

1

Controlled runtime evidence for claims static verification cannot settle, using exact IDs from a user-owned command allowlist and bounded artifacts.

1 skill · 1 command · 1 agent

1

Bridge an adrkit decision corpus to context-kit's durable memory and semantic retrieval: promote observed decisions toward ratifiable ADRs and recall decisions by meaning.

2 commands

1

Fast CLI search across modalities: lexical, structural, code-intelligence, structured-data, history, rewrite, metrics, and docs.

2 skills

1

indexkit

claude

Local-first semantic RAG: embed through a configurable Ollama endpoint, index with turbovec, and optionally fuse FTS5/BM25.

1 skill · hooks

1

Author portable GitHub Copilot, APM, and Claude Code plugins with scaffolding, manifest/frontmatter checks, and deterministic catalog and release-readiness gates.

1 skill · 1 command

1

The spine: a retrieval-strategist agent and retrieval-strategy skill that pick and compose search modalities.

1 skill · 1 agent

1

Choose where guidance lives — always-on memory, path-scoped rules, on-demand skills, subagents, MCP servers, or deterministic hooks — to steer agents while keeping the always-on context budget small.

1 skill

1

obsidian

claude

Skill-only RAG bridge: turn an Obsidian vault's graph and tags into a candidate set fed to indexkit.

1 skill

1

README badge

Shows how many plugins this repo ships, and links here.

claude & codex plugins15 plugins