weavatrix 1.8.0 → 1.9.1

package/skill/references/tools/get_architecture_contract.md

@@ -0,0 +1,29 @@
+# `get_architecture_contract`
+
+Read or preview the local target-architecture contract.
+
+## When to use
+
+Read or preview the local target-architecture contract.
+
+## Inputs
+
+- `action` ("preview").
+- `baseline_mode` (string).
+- `candidate_contract` (object).
+- `confirm_token` (string).
+- `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": "get_architecture_contract",
+  "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/get_community.md

@@ -0,0 +1,29 @@
+# `get_community`
+
+Return one weak graph component.
+
+## When to use
+
+Inspect one deterministic weak graph component by its id.
+
+## Inputs
+
+- `community_id` (integer, required, min 0).
+- `cursor` (string).
+- `max_nodes` (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": "get_community",
+  "arguments": {
+    "community_id": 1,
+    "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/get_dependents.md

@@ -0,0 +1,33 @@
+# `get_dependents`
+
+Bounded transitive reverse blast radius.
+
+## When to use
+
+Measure a bounded transitive reverse blast radius from one exact node.
+
+## Inputs
+
+- `label` (string, required).
+- `depth` (integer, min 0).
+- `include_container_importers` (boolean).
+- `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": "get_dependents",
+  "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/get_neighbors.md

@@ -0,0 +1,33 @@
+# `get_neighbors`
+
+Direct typed incoming and outgoing relationships.
+
+## When to use
+
+Inspect only the direct typed incoming and outgoing relationships of one exact node.
+
+For transitive reverse impact use `get_dependents`; for bounded multi-hop exploration use `query_graph`.
+
+## Inputs
+
+- `label` (string, required).
+- `cursor` (string).
+- `max_results` (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.
+- `relation_filter` (string | array<string>).
+- `response_detail` ("compact" | "full").
+
+## Minimal call
+
+```json
+{
+  "name": "get_neighbors",
+  "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/get_node.md

@@ -0,0 +1,27 @@
+# `get_node`
+
+Resolve one exact graph node.
+
+## When to use
+
+Resolve one exact graph label after another tool has supplied an unambiguous file, symbol, endpoint, or node id.
+
+## Inputs
+
+- `label` (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": "get_node",
+  "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/git_history.md

@@ -0,0 +1,34 @@
+# `git_history`
+
+Bounded direct Git history without launching git.
+
+## When to use
+
+Inspect bounded commit history, churn, and co-change inside the active repository.
+
+## Inputs
+
+- `first_parent` (boolean).
+- `include_analytics` (boolean).
+- `max_commits` (integer, min 0).
+- `max_pairs` (integer, min 0).
+- `min_pair_count` (integer, min 0).
+- `months` (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).
+- `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.
+- `top_n` (integer, min 0).
+
+## Minimal call
+
+```json
+{
+  "name": "git_history",
+  "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/god_nodes.md

@@ -0,0 +1,27 @@
+# `god_nodes`
+
+Rank high-connectivity production nodes.
+
+## When to use
+
+Find unusually connected production nodes for architecture or change-risk review.
+
+## Inputs
+
+- `include_classified` (boolean).
+- `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": "god_nodes",
+  "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/graph_diff.md

@@ -0,0 +1,32 @@
+# `graph_diff`
+
+Compare the current snapshot with an immutable Git revision.
+
+## When to use
+
+Compare the current graph snapshot with an immutable Git revision.
+
+## Inputs
+
+- `base_ref` (string, required).
+- `detail` ("file_pairs" | "edges", default "file_pairs") — Aggregate edge churn by source file, target file, and relation by default; request edges for individual edge provenance.
+- `head_ref` (string).
+- `max_results` (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.
+- `path` (string).
+- `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": "graph_diff",
+  "arguments": {
+    "base_ref": "HEAD~1",
+    "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/graph_stats.md

@@ -0,0 +1,26 @@
+# `graph_stats`
+
+Graph size, evidence and build freshness.
+
+## When to use
+
+Confirm the active repository, graph revision, freshness, counts, and available capabilities before deeper graph work.
+
+## Inputs
+
+- `include_capabilities` (boolean).
+- `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": "graph_stats",
+  "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/hot_path_review.md

@@ -0,0 +1,34 @@
+# `hot_path_review`
+
+Rank high-connectivity and large source symbols.
+
+## When to use
+
+Rank static performance-review candidates using connectivity and change signals.
+
+## Inputs
+
+- `call_threshold` (string).
+- `cyclomatic_threshold` (string).
+- `include_classified` (boolean).
+- `include_tests` (boolean).
+- `loop_depth_threshold` (integer, min 0).
+- `min_score` (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.
+- `path` (string).
+- `time_rank_threshold` (string).
+- `top_n` (integer, min 0).
+
+## Minimal call
+
+```json
+{
+  "name": "hot_path_review",
+  "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/inspect_symbol.md

@@ -0,0 +1,32 @@
+# `inspect_symbol`
+
+Definition, direct relationships and source evidence.
+
+## When to use
+
+Collect one symbol declaration, owner, callers, callees, and source evidence.
+
+## Inputs
+
+- `label` (string, required).
+- `context_lines` (integer, min 0).
+- `max_containers` (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` (string).
+- `timeout_ms` (integer, min 0).
+
+## Minimal call
+
+```json
+{
+  "name": "inspect_symbol",
+  "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/list_communities.md

@@ -0,0 +1,27 @@
+# `list_communities`
+
+List deterministic weak graph components.
+
+## When to use
+
+List the largest deterministic weak graph components before choosing one to inspect.
+
+## Inputs
+
+- `include_non_product` (boolean).
+- `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": "list_communities",
+  "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/list_endpoints.md

@@ -0,0 +1,29 @@
+# `list_endpoints`
+
+Inventory statically extracted HTTP endpoints.
+
+## When to use
+
+Inventory statically extracted HTTP endpoints with optional method and path filters.
+
+## Inputs
+
+- `include_classified` (boolean).
+- `max_results` (integer, min 0).
+- `method` (string).
+- `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).
+
+## Minimal call
+
+```json
+{
+  "name": "list_endpoints",
+  "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/list_known_repos.md

@@ -0,0 +1,25 @@
+# `list_known_repos`
+
+List repositories opened by this server process.
+
+## When to use
+
+List repositories previously opened by this server process.
+
+## 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.
+
+## Minimal call
+
+```json
+{
+  "name": "list_known_repos",
+  "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/map_stacktrace.md

@@ -0,0 +1,28 @@
+# `map_stacktrace`
+
+Map stack-trace text onto repository files and symbols.
+
+## When to use
+
+Map pasted Node, JVM, Python, or Rust stack frames to repository files and nearest symbols.
+
+## Inputs
+
+- `text` (string, required).
+- `max_frames` (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": "map_stacktrace",
+  "arguments": {
+    "text": "<stack trace>",
+    "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/memory_context.md

@@ -0,0 +1,29 @@
+# `memory_context`
+
+Compile bounded temporal memory context from supplied events.
+
+## When to use
+
+Compile bounded temporal context from events and a request supplied by the caller.
+
+## Inputs
+
+- `events` (array<object>, required).
+- `request` (object, 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": "memory_context",
+  "arguments": {
+    "events": [{}],
+    "request": {},
+    "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/module_map.md

@@ -0,0 +1,27 @@
+# `module_map`
+
+Production folder and dependency map.
+
+## When to use
+
+Orient in an unfamiliar repository through production folders and their dependency relationships.
+
+## Inputs
+
+- `include_non_product` (boolean).
+- `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": "module_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/open_repo.md

@@ -0,0 +1,30 @@
+# `open_repo`
+
+Retarget to another local repository.
+
+## When to use
+
+Retarget the process-local server to another local repository.
+
+## Inputs
+
+- `path` (string, required).
+- `build` (boolean).
+- `mode` ("full" | "no-tests" | "tests-only").
+- `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).
+
+## Minimal call
+
+```json
+{
+  "name": "open_repo",
+  "arguments": {
+    "path": "<path>",
+    "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/prepare_change.md

@@ -0,0 +1,28 @@
+# `prepare_change`
+
+Select architecture rules for intended changed files.
+
+## When to use
+
+Select the architecture rules relevant to intended changed files before editing.
+
+## Inputs
+
+- `files` (array<string>, required).
+- `intent` (string).
+- `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": "prepare_change",
+  "arguments": {
+    "files": ["<value>"],
+    "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/propose_architecture_exception.md

@@ -0,0 +1,30 @@
+# `propose_architecture_exception`
+
+Return a reviewable exception proposal without writing it.
+
+## When to use
+
+Prepare a reviewable exception proposal without writing it to the repository.
+
+## Inputs
+
+- `fingerprint` (string, required).
+- `reason` (string, required).
+- `expires` (string).
+- `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": "propose_architecture_exception",
+  "arguments": {
+    "fingerprint": "<violation fingerprint>",
+    "reason": "<reason>",
+    "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/query_graph.md

@@ -0,0 +1,40 @@
+# `query_graph`
+
+Bounded BFS or DFS around exact or textual seeds.
+
+## When to use
+
+Traverse a bounded BFS or DFS when a question needs several hops, direction controls, or multiple seeds.
+
+Start with exact seeds and a small depth, node cap, and `token_budget`.
+
+## Inputs
+
+- `augment_seeds` (boolean).
+- `context_filter` (array<string>).
+- `depth` (integer, min 0).
+- `flow_direction` ("forward" | "backward" | "both").
+- `include_classified` (boolean).
+- `include_low_signal` (boolean).
+- `max_nodes` (integer, min 0).
+- `mode` ("bfs" | "dfs").
+- `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.
+- `question` (string).
+- `relation_filter` (string | array<string>).
+- `seed_files` (array<string>).
+- `seed_symbols` (array<string>).
+- `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": "query_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.