Interverse Roadmap

57 plugins assessed against the 2026 state of the art (arXiv · HN · frontier tooling). Filter and search below. Each verdict links to its full assessment.

27 keep22 improve4 modernize3 merge1 deprecate

57 / 57 shown

Verdict	Plugin	P / E	Wave	SOTA gap / rationale
modernize	interflux	P1 / L	1	Three concrete frontier deltas, in priority order. (1) Embedding-gated triage: Step 1.2 agent scoring and Step
keep	interskill	P1 / S	1	The audit skill is a static, LLM-read manual checklist with no executable verification. SOTA on self-correctio
keep	tldr-swinton	P1 / M	1	Progressive tool disclosure on its own MCP surface. The server registers all 26 tldr-code tools eagerly; the 2
deprecate	interfluence	P2 / S	2	N/A for a retired plugin — but the deprecation rationale itself is SOTA-aligned: per-project glob-routed voice
merge	interknow	P2 / M	2	Embedding-based semantic retrieval (RAG-MCP / MemRouter gated memory) is the named feature but is non-function
merge	interplug	P2 / M	2	Two gaps. (1) The validate skill is human-read prose, not a deterministic runnable check with machine-parseabl
merge	intertree	P2 / M	2	Project-hierarchy/registry is a code-reconnaissance + persistent-knowledge concern; the 2026 frontier is graph
modernize	interlearn	P2 / M	2	Retrieval is flat keyword/grep — no semantic search, no embeddings, no agentic multi-hop retrieval. The 2025-2
modernize	interloop	P2 / M	2	Tool-grounded / executable verification (ReVeal, arXiv:2506.11442; "From Code to Courtroom," arXiv:2510.24367;
modernize	intertrace	P2 / M	2	This is a mature, honest, well-scoped plugin: the "report-first, beads-on-confirm" gating, three independently
improve	intercache	P2 / M	2	Auto-invocation via deterministic hooks. The 'harness engineering as a discipline' SOTA trend (hooks for anyth
improve	intercheck	P2 / S	2	Type-level verification. The strongest frontier signal for a code-quality guard is that tool-grounded, executa
improve	intercraft	P2 / M	2	Progressive tool disclosure / RAG-MCP as a first-class agent-native design principle. The "MCP context-bloat b
improve	interdeep	P2 / M	2	Agentic, parallel, runtime-graph research orchestration. The plugin lacks (1) agent-controlled multi-hop retri
improve	interject	P2 / M	2	Two frontier ideas are missing. (a) Experience-driven distillation into reusable principles (EvolveR arXiv:251
improve	interkasten	P2 / M	2	Primary: progressive tool disclosure. All ~34 tools load their schemas eagerly at server start; the 2026 conse
improve	interlab	P2 / M	2	Single-run keep/discard is the frontier gap. run_experiment executes the benchmark exactly once and log_experi
improve	interleave	P2 / M	2	The core bet is correct and SOTA-aligned: "render the boring parts with a script, only call the LLM for the in
improve	interlens	P2 / M	2	Two frontier ideas it lacks: (a) Progressive tool disclosure / RAG-MCP — it eager-loads 21 tool schemas instea
improve	intermem	P2 / M	2	All matching is lexical (SHA-256 exact-hash stability + difflib/keyword-overlap dedup). The 2026 agent-memory
improve	internext	P2 / M	2	Embedding/deterministic semantic gating as a no-LLM fast path (Select-then-Solve arXiv routing, RAG-MCP, agent
improve	interpath	P2 / M	2	This is a mature, well-tested plugin that does its narrow job well and is already partly ahead of the SOTA cur
improve	interpeer	P2 / M	2	Two frontier ideas it lacks. (1) Machine-readable receipt artifacts: its own vision doc flags emitting JSON/YA
improve	interpub	P2 / S	2	Minor and mostly optional. (1) The publish pipeline produces no structured, consumable receipt event — vision.
improve	interpulse	P2 / M	2	Passive gauge with no relief action. Frontier (Anthropic write/select/compress/isolate, +29%/+39%; demand-pagi
improve	interrank	P2 / M	2	Embedding-based semantic gating for task->benchmark and task->model recommendation. recommend_benchmarks/recom
improve	intersearch	P2 / M	2	Chunk-level + hybrid retrieval with an ANN index. Current SOTA retrieval folds chunking, dense+sparse hybrid s
improve	interseed	P2 / M	2	Agentic/embedding-based semantic retrieval for matching ideas to project context (RAG-MCP / agentic-RAG, embed
improve	interspect	P2 / L	2	Routing decisions are a pure counting-rule statistical gate over accumulated evidence (weighted hit-rate vs fi
improve	intertest	P2 / S	2	verification-before-completion encodes single-shot success ("run the command once, see 0 failures, then claim"
improve	intervoice	P2 / M	2	The validated retrieve -> rewrite -> self-critique pipeline (few-shot style-nearest exemplars + a reflection/v
keep	interchart	P2 / S	2	Does exactly what it claims: a deterministic static scanner of 529 lines plus a self-contained D3 v7 renderer
keep	interdoc	P2 / M	2	Verification grounding. The 2026 reflection/verification findings (From Code to Courtroom; the Bash-validation
keep	interfer	P2 / M	2	Two narrow gaps, both at the MCP/integration surface rather than the inference core. (1) The MCP server is han
keep	interform	P2 / S	2	Lacks a verification/critic loop. SOTA (2026) is emphatic that "verification is the new bottleneck" and that g
keep	interhelm	P2 / M	2	Two frontier ideas it lacks. (1) Code Mode / code-execution-with-MCP framing (Cloudflare Code Mode ~99.9% inpu
keep	interlock	P2 / M	2	Eager tool registration is the one frontier miss. RegisterAll calls AddTools on all 20 tools unconditionally a
keep	intermap	P2 / M	2	The call graph / reference edges are computed in-memory per tool call and discarded; there is no persistent, i
keep	intermix	P2 / M	2	Single-run-per-cell evaluation. No k-trial repetition, variance, or seed control anywhere in the code (grep fo
keep	intermux	P2 / M	2	This is a mature, tightly-scoped, well-engineered plugin that does exactly what it claims, and it sits in the
keep	interphase	P2 / S	2	The F8 discovery scorer (score_bead) is a hand-tuned static weighting (priority 0-60, phase 0-30, recency 0-20
keep	intersight	P2 / S	2	Schema-conformance is enforced only by prose instructions, not programmatically. The plugin emits JSON claimin
keep	interstat	P2 / M	2	Two frontier ideas it lacks. (1) Pricing/model data is hardcoded and goes stale — the SOTA findings establish
keep	intersynth	P2 / M	2	Mature, actively maintained plugin (v0.1.13; recent commits added Lorenzen move validation, Sawyer flow envelo
keep	intertrack	P2 / S	2	No frontier-architecture gap that matters for its purpose — this is a metrics-store, not an agent. The one gen
keep	intertrust	P2 / M	2	Mature, focused, working plugin that implements the frontier insight that verification/review-quality is the b
keep	interwatch	P2 / M	2	All drift detection is lexical/structural — regex/glob counts, git name-status, bead CLI deltas, mtime thresho
keep	tool-time	P2 / M	2	Token/cost accounting. The dominant 2026 finding ('the token bill comes due' — token economics as the #1 enter
keep	tuivision	P2 / M	2	Two frontier ideas it lacks, both already foreshadowed in its own roadmap. (1) Reliability-science evaluation
improve	interlore	P3 / M	3	Embedding-based semantic gating for pattern clustering (RAG-MCP, arXiv: >50% fewer tokens and tool-selection a
keep	interdev	P3 / S	3	Bundled CC docs are a static Apr-2026 snapshot with no freshness metadata or staleness gate — they reference T
keep	interline	P3 / S	3	none material. The frontier ideas (multi-agent orchestration, agent memory tiers, MCP tool-selection/progressi
keep	intermonk	P3 / S	3	Verification is purely free-form NL critique by LLM agents (Phase 6 monk re-evaluation + hostile auditor), wit
keep	intername	P3 / S	3	Essentially none that warrants modernization. The single tangentially-relevant frontier idea is the agent-inte
keep	interscribe	P3 / S	3	Two frontier ideas it lacks, neither severe: (1) Deterministic guardrail enforcement. The harness-engineering
keep	intership	P3 / S	3	none — the 2025-2026 frontier themes (orchestration topology, multi-tier agent memory, MCP tool-selection-at-s
keep	interslack	P3 / S	3	Two real-but-minor frontier gaps, neither warranting a modernize verdict. (1) Supply-chain/security posture: t