weavatrix 1.9.0 → 1.9.2

package/README.md

@@ -1,9 +1,9 @@
 # Weavatrix — native MCP repository intelligence
 
-[![CI](https://github.com/sergii-ziborov/weavatrix/actions/workflows/ci.yml/badge.svg)](https://github.com/sergii-ziborov/weavatrix/actions/workflows/ci.yml)
+[![CI](https://github.com/Weavatrix/weavatrix/actions/workflows/ci.yml/badge.svg)](https://github.com/Weavatrix/weavatrix/actions/workflows/ci.yml)
 [![npm](https://img.shields.io/npm/v/weavatrix.svg)](https://www.npmjs.com/package/weavatrix)
 [![engine](https://img.shields.io/crates/v/weavatrix-rust.svg?label=engine)](https://crates.io/crates/weavatrix-rust)
-[![MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/sergii-ziborov/weavatrix/blob/main/LICENSE)
+[![MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/Weavatrix/weavatrix/blob/main/LICENSE)
 
 **Give your coding agent repository evidence before it starts guessing.**
 
@@ -129,16 +129,16 @@ coding agent
     |
     | MCP over stdio
     v
-weavatrix 1.9.0
+weavatrix 1.9.2
     profile catalog · refresh · watcher · MCP framing
     |
     v
-weavatrix-rust 2.7.1
+weavatrix-rust 2.7.3
     typed graph · analysis · 43 read-only operations
 ```
 
 This npm product owns MCP transport and native distribution. The
-[`weavatrix-rust`](https://github.com/sergii-ziborov/weavatrix-rust) crate is
+[`weavatrix-rust`](https://github.com/Weavatrix/weavatrix-rust) crate is
 the reusable protocol-independent engine; it is not an MCP server.
 Its standalone diagnostic therefore reports `weavatrix-rust <engine-version>`,
 while this MCP product reports both its product and embedded-engine identities.
@@ -166,7 +166,7 @@ thresholds and sitting slightly above the 30.34x recorded for the 1.0.0
 baseline.
 
 Full evidence and methodology:
-[benchmarks](https://github.com/sergii-ziborov/weavatrix/blob/main/docs/benchmarks.md).
+[benchmarks](https://github.com/Weavatrix/weavatrix/blob/main/docs/benchmarks.md).
 
 ## Safety
 
@@ -181,12 +181,12 @@ Full evidence and methodology:
 
 ## Links
 
-- [Source and issues](https://github.com/sergii-ziborov/weavatrix)
-- [Engine API](https://github.com/sergii-ziborov/weavatrix-rust)
-- [Tool reference](https://github.com/sergii-ziborov/weavatrix/blob/main/docs/tool-reference.md)
-- [Language support](https://github.com/sergii-ziborov/weavatrix/blob/main/docs/language-support.md)
-- [Architecture](https://github.com/sergii-ziborov/weavatrix/blob/main/docs/architecture.md)
-- [Benchmarks](https://github.com/sergii-ziborov/weavatrix/blob/main/docs/benchmarks.md)
+- [Source and issues](https://github.com/Weavatrix/weavatrix)
+- [Engine API](https://github.com/Weavatrix/weavatrix-rust)
+- [Tool reference](https://github.com/Weavatrix/weavatrix/blob/main/docs/tool-reference.md)
+- [Language support](https://github.com/Weavatrix/weavatrix/blob/main/docs/language-support.md)
+- [Architecture](https://github.com/Weavatrix/weavatrix/blob/main/docs/architecture.md)
+- [Benchmarks](https://github.com/Weavatrix/weavatrix/blob/main/docs/benchmarks.md)
 
 ## License
 

package/package.json

@@ -1,19 +1,19 @@
 {
   "name": "weavatrix",
-  "version": "1.9.0",
-  "weavatrixEngineVersion": "2.7.1",
+  "version": "1.9.2",
+  "weavatrixEngineVersion": "2.7.3",
   "description": "Native repository intelligence for coding agents: 43 read-only MCP operations backed by typed evidence graphs, impact, architecture, APIs, Git, search, semantics, and memory.",
   "author": "Sergii Ziborov <sergii.ziborov@gmail.com>",
   "license": "MIT",
   "homepage": "https://weavatrix.com",
   "repository": {
     "type": "git",
-    "url": "git+https://github.com/sergii-ziborov/weavatrix.git"
+    "url": "git+https://github.com/Weavatrix/weavatrix.git"
   },
   "bugs": {
-    "url": "https://github.com/sergii-ziborov/weavatrix/issues"
+    "url": "https://github.com/Weavatrix/weavatrix/issues"
   },
-  "mcpName": "io.github.sergii-ziborov/weavatrix",
+  "mcpName": "io.github.Weavatrix/weavatrix",
   "type": "module",
   "engines": {
     "node": ">=18"

package/server.json

@@ -1,20 +1,20 @@
 {
   "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
-  "name": "io.github.sergii-ziborov/weavatrix",
+  "name": "io.github.Weavatrix/weavatrix",
   "title": "Weavatrix",
   "description": "Native Weavatrix MCP: 43 read-only repository tools across 24 code and configuration surfaces.",
   "repository": {
-    "url": "https://github.com/sergii-ziborov/weavatrix",
+    "url": "https://github.com/Weavatrix/weavatrix",
     "source": "github"
   },
-  "version": "1.9.0",
+  "version": "1.9.2",
   "websiteUrl": "https://weavatrix.com",
   "packages": [
     {
       "registryType": "npm",
       "registryBaseUrl": "https://registry.npmjs.org",
       "identifier": "weavatrix",
-      "version": "1.9.0",
+      "version": "1.9.2",
       "runtimeHint": "npx",
       "transport": {
         "type": "stdio"

package/skill/SKILL.md

@@ -1,66 +1,47 @@
 ---
 name: weavatrix
-description: Use the native Weavatrix MCP for local repository intelligence across Rust, JavaScript, TypeScript, Python, Go, Java, C, C++, C#, SQL, GraphQL, Protobuf, infrastructure, and event transports. Trigger for codebase orientation, source search, dependency and call graphs, endpoint or transport tracing, cross-repository impact, dead-code and duplicate review, Health audits, architecture checks, Git history, coverage, vector or semantic search, SEO links, and temporal memory.
+description: >-
+  Use the Weavatrix MCP when a repository task benefits from indexed evidence:
+  codebase orientation, symbol/source search, dependency or call graphs, change
+  impact, API/event tracing, architecture checks, Git/coverage evidence,
+  duplicates, dead-code review, or semantic context. Skip it for trivial
+  single-file edits or when a known source file and native tests already answer
+  the task.
 ---
 
 # Weavatrix
 
-Use Weavatrix as the evidence layer for repository work. Start with the
-smallest graph query that answers the task, inspect decisive source spans, and
-then use repository-native tests or benchmarks for behavioral proof.
+Use Weavatrix on demand as a compact evidence layer. It is most useful when a
+question crosses files, symbols, modules, revisions, repositories, or runtime
+contracts. Do not call it merely because the server is available.
 
-## Start
+## Minimal workflow
 
 1. Call `graph_stats` to confirm the active repository and graph revision.
 2. Use `module_map` for orientation or `search_code` for a known literal.
-3. Pin an exact symbol with `inspect_symbol` or `context_bundle`.
-4. Expand only with `get_neighbors`, `get_dependents`, `query_graph`, or
-   `shortest_path` when the task needs relationship evidence.
-
-Call `rebuild_graph` only when the active repository changed before the
-server's refresh completed or when deliberately changing graph mode.
-
-## Route the task
-
-- API inventory: `list_endpoints`; one request path: `trace_endpoint`.
-- GraphQL, gRPC/Protobuf, Kafka, RabbitMQ/AMQP, NATS, SNS/SQS, or JMS across
-  repositories: `list_known_repos`, then `trace_api_contract` with an explicit
-  backend, clients, and transport.
-- Cross-repository Git evidence: `cross_repo_git`.
-- Branch or patch impact: `change_impact`; transitive symbol risk:
-  `get_dependents`; structural drift: `graph_diff`.
-- Repository health: `run_audit`, then targeted `find_dead_code`,
-  `find_duplicates`, `coverage_map`, and `hot_path_review`.
-- Intended architecture: `get_architecture_contract`, `prepare_change`, then
-  `verify_architecture`; explain or propose an exception only for a concrete
-  violation fingerprint.
-- Change gate: use `verified_change` with the same task and base revision in
-  plan and verify phases.
-- Vector, semantic, SEO, and temporal context: `vector_search`,
-  `semantic_link`, `seo_link_suggestions`, and `memory_context`.
-
-Read [references/tool-routing.md](references/tool-routing.md) when selecting
-among similar tools or reviewing transport evidence.
-
-## Evidence rules
-
-- Treat source spans, extractor identity, graph revision, relation type, and
-  confidence as part of every finding.
-- Distinguish static reachability from measured coverage.
-- Confirm dead-code and clone candidates in source and framework registration
-  points before editing.
-- Preserve exact transport identity. Do not merge AMQP, RabbitMQ, NATS, Kafka,
-  SNS/SQS, JMS, GraphQL, or gRPC evidence merely because operations share
-  names such as `publish`, `send`, or `subscribe`.
-- For dynamic JavaScript or Python dispatch, narrow with repository
-  configuration, imports, call receivers, literals, runtime evidence, and
-  source spans. Never guess a transport or call target.
-- Use `output_format:"text"` for compact interaction and JSON for automation
-  or retained evidence.
-
-## Safety
-
-The core is read-only and offline: it may read local source, Git objects,
-coverage, and derived graph state, but it does not edit source or perform
-network security scans. Use `weavatrix-refactor` only for explicitly approved
-write plans and `weavatrix-online` only for explicitly approved network work.
+3. Pin decisive evidence with `inspect_symbol`, `context_bundle`, or
+   `read_source`.
+4. Expand only when needed: `get_dependents` or `change_impact` for risk,
+   `trace_endpoint` or `trace_api_contract` for runtime contracts,
+   `verify_architecture` for policy, and `run_audit` for a broad health pass.
+5. Use repository-native tests or benchmarks for behavioral proof.
+
+Prefer `output_format:"text"` and a small `token_budget` for conversational
+work. Use JSON only for automation or retained evidence. Call `rebuild_graph`
+only when the repository changed before automatic refresh completed or when
+deliberately changing graph mode.
+
+Read [references/tool-routing.md](references/tool-routing.md) only when choosing
+among similar tools, tracing cross-repository transports, or interpreting
+audit and coverage results.
+
+## Evidence and safety
+
+- Keep source spans, graph revision, relation type, extractor, and confidence
+  attached to findings.
+- Treat static reachability and audit output as candidates, not runtime proof.
+- Preserve exact transport identity; do not merge Kafka, AMQP/RabbitMQ, NATS,
+  SNS/SQS, JMS, GraphQL, and gRPC evidence because operation names match.
+- The core is local, offline, and read-only. Use `weavatrix-refactor` only for
+  an explicitly approved write plan and `weavatrix-online` only for explicitly
+  approved network work.

package/skill/references/tool-routing.md

@@ -1,55 +1,66 @@
-# Tool routing
-
-## Graph and source
-
-- `graph_stats`: repository identity, freshness, counts, and evidence.
-- `module_map`, `list_communities`, `get_community`, `god_nodes`: topology.
-- `build_graph`: workspace aggregators, members, targets, and runner
-  configurations from manifest evidence; no build tool runs.
-- `get_node`, `get_neighbors`, `inspect_symbol`, `context_bundle`: exact
-  entities and local evidence.
-- `query_graph`, `shortest_path`, `get_dependents`: bounded traversal.
-- `search_code`, `read_source`: lexical and source confirmation.
-- `map_stacktrace`: paste a Node, JVM, Python, or Rust stack trace; frames map
-  to repository files and the nearest symbol, so debugging starts at the graph
-  instead of at a directory listing.
-- Pass `token_budget` on `search_code`, `read_source`, `context_bundle`, or
-  `query_graph` to fit the answer into the context window you have left; the
-  report states exactly what was dropped.
-
-## Change and history
-
-- `change_impact`: current diff, explicit files, or supplied patch.
-- `select_tests`: the suites a change most plausibly needs to run, ranked by
-  graph distance; static selection, no coverage run consumed.
-- `graph_diff`: structural comparison with an immutable Git revision.
-- `git_history`: churn and co-change in one repository.
-- `cross_repo_git`: histories, shared commits, or diffs across repositories.
-- `verified_change`: composite plan/verify evidence envelope.
-
-## Runtime contracts
-
-- `list_endpoints` and `trace_endpoint`: HTTP routes and handlers.
-- `trace_api_contract`: HTTP, GraphQL, Protobuf/gRPC, and event transports
-  across registered repositories.
-- Select `transport:"event"` for Kafka, RabbitMQ/AMQP, NATS, SNS/SQS, and JMS;
-  retain the concrete transport, topic/queue/subject, operation, source span,
-  and producer/consumer direction from each evidence row.
+# Tool routing index
+
+Open only the card for the method you are about to call. Each card explains
+when to use the method, its exact published inputs, and a minimal compact call.
+The live MCP `tools/list` schema is authoritative.
+
+## Graph, source, and orientation
+
+- [`graph_stats`](tools/graph_stats.md) — Graph size, evidence and build freshness.
+- [`get_node`](tools/get_node.md) — Resolve one exact graph node.
+- [`get_neighbors`](tools/get_neighbors.md) — Direct typed incoming and outgoing relationships.
+- [`query_graph`](tools/query_graph.md) — Bounded BFS or DFS around exact or textual seeds.
+- [`god_nodes`](tools/god_nodes.md) — Rank high-connectivity production nodes.
+- [`shortest_path`](tools/shortest_path.md) — Shortest typed dependency path between two nodes.
+- [`get_community`](tools/get_community.md) — Return one weak graph component.
+- [`list_communities`](tools/list_communities.md) — List deterministic weak graph components.
+- [`module_map`](tools/module_map.md) — Production folder and dependency map.
+- [`build_graph`](tools/build_graph.md) — Workspace, target and runner topology from manifest evidence.
+- [`search_code`](tools/search_code.md) — Literal or Rust-regex repository search without ripgrep.
+- [`read_source`](tools/read_source.md) — Bounded source context by node or repository path.
+- [`inspect_symbol`](tools/inspect_symbol.md) — Definition, direct relationships and source evidence.
+- [`context_bundle`](tools/context_bundle.md) — Compact graph and source bundle for one symbol.
+- [`map_stacktrace`](tools/map_stacktrace.md) — Map stack-trace text onto repository files and symbols.
+
+## Change impact and Git
+
+- [`get_dependents`](tools/get_dependents.md) — Bounded transitive reverse blast radius.
+- [`change_impact`](tools/change_impact.md) — Read-only Git change impact with graph evidence.
+- [`select_tests`](tools/select_tests.md) — Select the test suites a change most plausibly needs to run.
+- [`git_history`](tools/git_history.md) — Bounded direct Git history without launching git.
+- [`cross_repo_git`](tools/cross_repo_git.md) — Parallel histories, shared commits, or diffs across local repositories.
+- [`verified_change`](tools/verified_change.md) — Composite pre-commit evidence and conservative verdict.
+- [`graph_diff`](tools/graph_diff.md) — Compare the current snapshot with an immutable Git revision.
 
 ## Quality and architecture
 
-- `run_audit`: repository Health and evidence completeness.
-- `find_dead_code`: conservative production-symbol review queue.
-- `find_duplicates`: Type-1, Type-2, and Type-3 clone families.
-- `coverage_map`: measured reports and separately labeled static reachability.
-- `hot_path_review`: static performance-review candidates.
-- `get_architecture_contract`, `prepare_change`, `verify_architecture`,
-  `explain_architecture_violation`, `propose_architecture_exception`:
-  architecture workflow.
-
-## Repository and optional analysis
-
-- `open_repo`, `list_known_repos`: local retargeting and cross-repository set.
-- `rebuild_graph`: explicit graph refresh or mode change.
-- `vector_search`, `semantic_link`, `seo_link_suggestions`, `memory_context`:
-  supplied-vector and supplied-event workflows.
+- [`find_duplicates`](tools/find_duplicates.md) — Deterministic Type-1/2/3 clone families.
+- [`find_dead_code`](tools/find_dead_code.md) — Conservative unreferenced-symbol review queue.
+- [`run_audit`](tools/run_audit.md) — Repository structure and evidence completeness audit.
+- [`coverage_map`](tools/coverage_map.md) — Measured coverage discovery or explicit static reachability.
+- [`hot_path_review`](tools/hot_path_review.md) — Rank high-connectivity and large source symbols.
+- [`get_architecture_contract`](tools/get_architecture_contract.md) — Read or preview the local target-architecture contract.
+- [`prepare_change`](tools/prepare_change.md) — Select architecture rules for intended changed files.
+- [`verify_architecture`](tools/verify_architecture.md) — Verify graph dependencies against the active contract.
+- [`verify_capabilities`](tools/verify_capabilities.md) — Resolve declared capabilities against exposed endpoint evidence.
+- [`explain_architecture_violation`](tools/explain_architecture_violation.md) — Explain one active contract violation.
+- [`propose_architecture_exception`](tools/propose_architecture_exception.md) — Return a reviewable exception proposal without writing it.
+
+## APIs and transports
+
+- [`list_endpoints`](tools/list_endpoints.md) — Inventory statically extracted HTTP endpoints.
+- [`trace_endpoint`](tools/trace_endpoint.md) — Resolve an endpoint and its bounded call neighborhood.
+- [`trace_api_contract`](tools/trace_api_contract.md) — Cross-repository HTTP, GraphQL, gRPC and event-transport contract evidence.
+
+## Repositories and refresh
+
+- [`open_repo`](tools/open_repo.md) — Retarget to another local repository.
+- [`list_known_repos`](tools/list_known_repos.md) — List repositories opened by this server process.
+- [`rebuild_graph`](tools/rebuild_graph.md) — Rebuild the derived in-memory graph without source writes.
+
+## Optional supplied-data analysis
+
+- [`semantic_link`](tools/semantic_link.md) — Build inferred semantic graph evidence from supplied vectors.
+- [`vector_search`](tools/vector_search.md) — Exact or bounded approximate nearest-neighbor search.
+- [`seo_link_suggestions`](tools/seo_link_suggestions.md) — Directional SEO internal-link evidence from supplied page profiles.
+- [`memory_context`](tools/memory_context.md) — Compile bounded temporal memory context from supplied events.

package/skill/references/tools/build_graph.md

@@ -0,0 +1,26 @@
+# `build_graph`
+
+Workspace, target and runner topology from manifest evidence.
+
+## When to use
+
+Inspect workspace members, targets, aggregators, and runner topology extracted from manifests.
+
+## Inputs
+
+- `max_members` (integer, min 0).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+
+## Minimal call
+
+```json
+{
+  "name": "build_graph",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/change_impact.md

@@ -0,0 +1,37 @@
+# `change_impact`
+
+Read-only Git change impact with graph evidence.
+
+## When to use
+
+Map a working-tree diff, explicit files, or Git revisions onto affected graph nodes.
+
+Static impact is not proof that selected behavior executed.
+
+## Inputs
+
+- `base` (string).
+- `base_ref` (string).
+- `depth` (integer, min 0).
+- `diff` (string).
+- `files` (array<string>).
+- `head_ref` (string).
+- `max_nodes` (integer, min 0).
+- `max_references` (integer, min 0).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `precision` ("graph").
+- `timeout_ms` (integer, min 0).
+
+## Minimal call
+
+```json
+{
+  "name": "change_impact",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/context_bundle.md

@@ -0,0 +1,36 @@
+# `context_bundle`
+
+Compact graph and source bundle for one symbol.
+
+## When to use
+
+Assemble a ranked, token-bounded workset around one task or target.
+
+## Inputs
+
+- `label` (string, required).
+- `context_lines` (integer, min 0).
+- `include_classified` (boolean).
+- `max_reexports` (integer, min 0).
+- `max_references` (integer, min 0).
+- `max_related` (integer, min 0).
+- `max_source_files` (integer, min 0).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `precision` (string).
+- `timeout_ms` (integer, min 0).
+- `token_budget` (integer, min 1) — Approximate output ceiling in tokens (serialized bytes / 4); result arrays are trimmed from the tail to fit and the report states what was dropped.
+
+## Minimal call
+
+```json
+{
+  "name": "context_bundle",
+  "arguments": {
+    "label": "<exact node label>",
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/coverage_map.md

@@ -0,0 +1,29 @@
+# `coverage_map`
+
+Measured coverage discovery or explicit static reachability.
+
+## When to use
+
+Attach measured coverage reports to graph nodes and keep static reachability separately labeled.
+
+A missing measured report must not be described as clean coverage.
+
+## Inputs
+
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `path` (string).
+- `top_n` (integer, min 0).
+
+## Minimal call
+
+```json
+{
+  "name": "coverage_map",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/cross_repo_git.md

@@ -0,0 +1,35 @@
+# `cross_repo_git`
+
+Parallel histories, shared commits, or diffs across local repositories.
+
+## When to use
+
+Compare histories, shared commits, or diffs across explicitly supplied local repository roots.
+
+## Inputs
+
+- `repositories` (array<object>, required).
+- `action` ("histories" | "shared_commits" | "diff").
+- `base_ref` (string).
+- `first_parent` (boolean).
+- `head_ref` (string).
+- `left` (string).
+- `max_commits` (integer, min 0).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `revision` (string).
+- `right` (string).
+
+## Minimal call
+
+```json
+{
+  "name": "cross_repo_git",
+  "arguments": {
+    "repositories": [{}],
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/explain_architecture_violation.md

@@ -0,0 +1,27 @@
+# `explain_architecture_violation`
+
+Explain one active contract violation.
+
+## When to use
+
+Retrieve bounded evidence for one active architecture-violation fingerprint.
+
+## Inputs
+
+- `fingerprint` (string, required).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+
+## Minimal call
+
+```json
+{
+  "name": "explain_architecture_violation",
+  "arguments": {
+    "fingerprint": "<violation fingerprint>",
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/find_dead_code.md

@@ -0,0 +1,33 @@
+# `find_dead_code`
+
+Conservative unreferenced-symbol review queue.
+
+## When to use
+
+Build a conservative dead-code review queue with entry-point, test, config, dynamic, and external-use evidence.
+
+Never delete from this result alone; confirm source and framework registration points.
+
+## Inputs
+
+- `include_classified` (boolean).
+- `include_tests` (boolean).
+- `kinds` (array<string>).
+- `min_confidence` (integer, min 0, max 100).
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `path` (string).
+- `top_n` (integer, min 0).
+
+## Minimal call
+
+```json
+{
+  "name": "find_dead_code",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/find_duplicates.md

@@ -0,0 +1,34 @@
+# `find_duplicates`
+
+Deterministic Type-1/2/3 clone families.
+
+## When to use
+
+Review bounded Type-1, Type-2, or Type-3 clone families before confirming candidates in source.
+
+## Inputs
+
+- `include_boilerplate` (boolean).
+- `include_classified` (boolean).
+- `include_declarative` (boolean, default true) — High-recall by default; false suppresses data-only catalogs but retains model, schema, and contract clones.
+- `include_strings` (boolean, default false) — Also compare multi-line string payloads - inline SQL, templates, embedded scripts - which the code pass sees as a single token.
+- `include_tests` (boolean).
+- `min_similarity` (number, min 0, max 100) — 0..1 is a fraction; values above 1 through 100 are percentages.
+- `min_tokens` (integer, min 0).
+- `mode` ("strict" | "exact" | "renamed" | "near_miss").
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+- `top_n` (integer, min 0).
+
+## Minimal call
+
+```json
+{
+  "name": "find_duplicates",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.