@dug-21/unimatrix 0.5.9 → 0.6.0

package/skills/uni-release/SKILL.md

@@ -141,11 +141,74 @@ If this fails, stop with: **"Build check failed after version update. Review cha
 
 ---
 
+## Step 7a: Sync protocols/ Distribution Copies
+
+Copy the four protocol files from the internal `.claude/protocols/uni/` directory
+to two locations: the repo-root `protocols/` (for repo users) and
+`packages/unimatrix/protocols/` (for npm — npm resolves `files` relative to the
+package directory, not the repo root):
+
+```bash
+# Repo-root copy (for users who clone the repo)
+cp .claude/protocols/uni/uni-design-protocol.md protocols/uni-design-protocol.md
+cp .claude/protocols/uni/uni-delivery-protocol.md protocols/uni-delivery-protocol.md
+cp .claude/protocols/uni/uni-bugfix-protocol.md protocols/uni-bugfix-protocol.md
+cp .claude/protocols/uni/uni-agent-routing.md protocols/uni-agent-routing.md
+cp protocols/README.md protocols/README.md  # already exists; update if changed
+
+# npm package copy (what npm pack actually includes)
+cp .claude/protocols/uni/uni-design-protocol.md packages/unimatrix/protocols/uni-design-protocol.md
+cp .claude/protocols/uni/uni-delivery-protocol.md packages/unimatrix/protocols/uni-delivery-protocol.md
+cp .claude/protocols/uni/uni-bugfix-protocol.md packages/unimatrix/protocols/uni-bugfix-protocol.md
+cp .claude/protocols/uni/uni-agent-routing.md packages/unimatrix/protocols/uni-agent-routing.md
+cp protocols/README.md packages/unimatrix/protocols/README.md
+```
+
+Verify each copy is identical to its source (run for both destinations):
+
+```bash
+diff .claude/protocols/uni/uni-design-protocol.md protocols/uni-design-protocol.md
+diff .claude/protocols/uni/uni-delivery-protocol.md protocols/uni-delivery-protocol.md
+diff .claude/protocols/uni/uni-bugfix-protocol.md protocols/uni-bugfix-protocol.md
+diff .claude/protocols/uni/uni-agent-routing.md protocols/uni-agent-routing.md
+diff protocols/uni-design-protocol.md packages/unimatrix/protocols/uni-design-protocol.md
+diff protocols/uni-delivery-protocol.md packages/unimatrix/protocols/uni-delivery-protocol.md
+diff protocols/uni-bugfix-protocol.md packages/unimatrix/protocols/uni-bugfix-protocol.md
+diff protocols/uni-agent-routing.md packages/unimatrix/protocols/uni-agent-routing.md
+diff protocols/README.md packages/unimatrix/protocols/README.md
+```
+
+All diffs must produce zero output. The `.claude/protocols/uni/` directory is the
+source of truth — apply any needed corrections there first, then re-copy both.
+
+---
+
+## Step 7b: Sync uni-retro Distribution Copies
+
+Copy the uni-retro skill to two locations: the repo-root `skills/uni-retro/` (for
+repo users) and `packages/unimatrix/skills/uni-retro/` (for npm):
+
+```bash
+cp .claude/skills/uni-retro/SKILL.md skills/uni-retro/SKILL.md
+cp .claude/skills/uni-retro/SKILL.md packages/unimatrix/skills/uni-retro/SKILL.md
+```
+
+Verify both copies are identical to their source:
+
+```bash
+diff .claude/skills/uni-retro/SKILL.md skills/uni-retro/SKILL.md
+diff .claude/skills/uni-retro/SKILL.md packages/unimatrix/skills/uni-retro/SKILL.md
+```
+
+Both diffs must produce zero output.
+
+---
+
 ## Step 7: Create Release Commit
 
 Stage only the release-related files:
 ```bash
-git add Cargo.toml packages/unimatrix/package.json packages/unimatrix-linux-x64/package.json packages/unimatrix-linux-arm64/package.json CHANGELOG.md
+git add Cargo.toml packages/unimatrix/package.json packages/unimatrix-linux-x64/package.json packages/unimatrix-linux-arm64/package.json CHANGELOG.md protocols/ skills/uni-retro/ packages/unimatrix/protocols/ packages/unimatrix/skills/uni-retro/
 ```
 
 Commit with the release message:
@@ -187,6 +250,10 @@ Files modified:
   - packages/unimatrix-linux-x64/package.json
   - packages/unimatrix-linux-arm64/package.json
   - CHANGELOG.md
+  - protocols/ (synced from .claude/protocols/uni/ — repo-root copy)
+  - packages/unimatrix/protocols/ (npm-distributed copy)
+  - skills/uni-retro/SKILL.md (synced from .claude/skills/uni-retro/ — repo-root copy)
+  - packages/unimatrix/skills/uni-retro/SKILL.md (npm-distributed copy)
 
 Git:
   - Commit: release: v{new_version}

package/skills/uni-retro/SKILL.md

@@ -7,7 +7,7 @@ description: "Post-merge retrospective — extracts patterns, procedures, and le
 
 ## What This Skill Does
 
-Analyzes a shipped feature and extracts reusable knowledge — patterns, procedures, and lessons — into Unimatrix. This is how the project learns.
+Analyzes a shipped feature and shares valuable feedback with the human, reports Unimatrix usage, and extracts reusable knowledge — patterns, procedures, and lessons — into Unimatrix. This is how the project learns.
 
 ---
 
@@ -20,13 +20,27 @@ From the invoker:
 
 ---
 
+## When to Go Lightweight
+
+Not every feature needs a full retro:
+
+| Situation | Action |
+|---|---|
+| Zero gate failures, no rework, zero hotspots | Skip lesson extraction. Focus on patterns/procedures only. |
+| Minor enhancement (1-2 components) | Check for pattern drift only, skip procedure review. |
+| New infrastructure introduced | Full retro — high likelihood of new patterns and procedures. |
+| Multiple SCOPE FAILs or heavy rework | Full retro — prioritize lesson extraction. |
+| Many Warning hotspots or baseline outliers | Full retro — prioritize hotspot-driven lessons and procedure updates. |
+
+---
+
 ## Phase 1: Data Gathering & Retrospective Analysis
 
 Gather all evidence about the shipped feature:
 
 1. **Run retrospective analysis** (if observation data exists):
    ```
-   mcp__unimatrix__context_retrospective(feature_cycle: "{feature-id}")
+   mcp__unimatrix__context_cycle_review({"feature_cycle": "{feature-id}", "format": "markdown"})
    ```
    This returns structured data: metrics, hotspots, baseline comparisons, narratives, and recommendations.
 
@@ -36,7 +50,7 @@ Gather all evidence about the shipped feature:
       - `Warning` hotspots → potential lessons or procedure gaps
       - `Info` hotspots → note trends, may not need action
       - Key hotspot types to watch:
-        - `permission_retries` → settings.json allowlist may need updating
+        - `orphaned_calls` → tool invocations with no terminal event — check context overflow or parallel call management
         - `sleep_workarounds` → agents using sleep instead of run_in_background
         - `cold_restart` → context loss after gaps, agents re-reading files
         - `coordinator_respawns` → SM lifetime/handoff issues
@@ -74,38 +88,7 @@ Gather all evidence about the shipped feature:
    ```
    Look for rework commits (`fix(gate):`) — these indicate where the process struggled.
 
----
-
-## Phase 1b: Stewardship Quality Review
-
-Before extracting new patterns, review the quality of entries agents stored during this feature cycle.
-
-1. **Query entries stored during the feature**:
-   ```
-   mcp__unimatrix__context_search(
-     query: "{feature-id}",
-     k: 20
-   )
-   ```
-   Also search by feature_cycle tag if available. Use content/title matching as fallback — not all agents tag consistently.
-
-2. **Assess each entry against its category template**:
-   - **Patterns**: Has what/why/scope structure? Is "why" substantive (not "it works")?
-   - **Lessons**: Has what-happened/root-cause/takeaway? Is takeaway actionable?
-   - **Procedures**: Has numbered steps? Are steps specific (not generic)?
-
-3. **Curate**:
-   - **Low-quality entries** (missing structure, no substantive "why", API docs disguised as patterns): deprecate via `context_deprecate` with reason.
-   - **High-quality entries** confirmed by successful delivery: note for the architect to validate during pattern extraction.
-   - **Miscategorized entries** (lesson stored as pattern, or vice versa): note for correction.
-
-4. **Report** the stewardship review results before proceeding to Phase 2:
-   ```
-   Stewardship Quality Review:
-   - Entries found: {N}
-   - Quality: {N} good, {N} deprecated (low quality), {N} flagged for recategorization
-   - Details: {list each entry with assessment}
-   ```
+6. **Share the interim results**: Provide cleanesed view of the context_cycle_review output with key observations before moving forward.  At a MINIMUM show the ##Phase Narrative and ##Phase Timeline.  Also Highlight a specific section of content retrieved during the cycle... (This reinforces the Unimatrix Value Prop)
 
 ---
 
@@ -144,7 +127,7 @@ Agent(uni-architect, "
   MODE: retrospective (not design)
   Feature: {feature-id}
 
-  You are reviewing a SHIPPED feature to extract reusable knowledge.
+  You are reviewing a SHIPPED feature to extract reusable knowledge.  More entries not better.  You are looking for aspects future agents will benefit from.  Be selective.
   You are NOT designing anything new.
 
   Read these artifacts:
@@ -159,12 +142,23 @@ Agent(uni-architect, "
 
   YOUR TASKS:
 
+  0. STEWARDSHIP REVIEW — Before extracting new knowledge, assess entries already stored during this cycle:
+     a. Query: `mcp__unimatrix__context_search({"query": "{feature-id}", "k": 20})`. Also try feature_cycle tag if available.
+     b. For each entry, assess against its category template:
+        - **Patterns**: Has what/why/scope? Is "why" substantive (not "it works")?
+        - **Lessons**: Has what-happened/root-cause/takeaway? Is takeaway actionable?
+        - **Procedures**: Has numbered steps? Are steps specific (not generic)?
+     c. Low-quality entries (missing structure, no substantive "why", API docs disguised as patterns):
+        correct via `context_correct` or remove via `context_deprecate` as appropriate.
+     d. Miscategorized entries: correct category via `context_correct`.
+     e. High-quality entries confirmed by delivery: carry forward into steps 1-4 as evidence.
+
   1. PATTERN EXTRACTION — For each component implemented:
      a. Use /uni-query-patterns to find existing patterns for the affected crate(s)
      b. If the component followed an existing pattern: verify it's still accurate.
         If the pattern drifted, use /uni-store-procedure or context_correct to update it.
      c. If the component established a NEW reusable structure (used in 2+ features
-        or clearly generic): store it via context_store(category: 'pattern').
+        or clearly generic): store it via mcp__unimatrix__context_store({"category": "pattern", ...}).
      d. If the component was one-off: skip — don't store patterns for unique work.
 
   2. PROCEDURE REVIEW — Check if any HOW-TO changed:
@@ -181,7 +175,7 @@ Agent(uni-architect, "
   4. LESSON EXTRACTION — Two sources:
 
      A. From gate failures and rework:
-        a. What went wrong? (root cause, not symptoms)
+        a. Are there items future agents can learn from? (Don't just report failures)
         b. Is the lesson generalizable beyond this feature?
         c. If yes: use /uni-store-lesson.
 
@@ -189,12 +183,7 @@ Agent(uni-architect, "
         For each Warning-severity hotspot, ask:
         - Is this a recurring problem (check baseline — is it consistently above threshold)?
         - Can it be prevented by a procedure change or config update?
-        - If yes: store as lesson (/uni-store-lesson) or procedure (/uni-store-procedure).
-
-        For each recommendation from the retrospective:
-        - Check if a matching procedure already exists (/uni-query-patterns).
-        - If not, and the recommendation is actionable: store as procedure.
-        - If it updates existing guidance: use context_correct.
+        - If yes: If HUMAN must take the action - report only (don't store). If future agents need to know: store as lesson (/uni-store-lesson) or procedure (/uni-store-procedure).
 
      C. From baseline outliers:
         - Positive outliers (improvements): note what changed and why — may be a new pattern.
@@ -210,25 +199,8 @@ Agent(uni-architect, "
 
 ---
 
-## Phase 3: ADR Supersession (if flagged)
-
-If the architect flagged any ADRs for supersession:
 
-1. Present each flagged ADR to the human:
-   ```
-   ADR #{entry-id}: "{title}"
-   Architect's finding: {why it should be superseded}
-   Proposed replacement: {what the new decision should be}
-
-   Approve supersession?
-   ```
-
-2. If human approves: spawn architect to perform the supersession via `/uni-store-adr`.
-3. If human disagrees: note as "ADR validated with caveat".
-
----
-
-## Phase 4: Worktree Cleanup
+## Phase 3: Worktree Cleanup
 
 Worker agents spawned with `isolation: "worktree"` create directories under `.claude/worktrees/`. Each contains a full `target/` build directory (~1-2GB). Clean up after merge.
 
@@ -247,22 +219,22 @@ If a worktree has uncommitted changes, warn the human — do NOT force-remove.
 
 ---
 
-## Phase 5: Summary & Outcome
+## Phase 4: Summary & Outcome
 
 Collect all knowledge base changes from Phases 2-3.
 
-Use `/uni-record-outcome` with:
-- Feature: `{feature-id}`
-- Type: `retro`
-- Phase: `retro`
-- Result: `pass`
-- Content: `Retrospective complete. {N} patterns, {N} procedures, {N} lessons extracted. {N} ADRs validated. Hotspots: {count} ({warning_count} warnings). Outliers: {list outlier metric names}.`
+**Commit retro artifacts** before recording outcome:
+```bash
+git add product/features/{id}/agents/
+git commit -m "chore: add retro artifacts ({feature-id})"
+git push origin main
+```
 
 **Return format:**
 ```
 RETROSPECTIVE COMPLETE — Knowledge base updated.
 
-Feature: {feature-id}
+Cycle: {feature-id}
 PR: #{pr-number} (merged)
 
 Retrospective summary:
@@ -270,7 +242,10 @@ Retrospective summary:
 - Hotspots: {count} ({warning_count} warnings, {info_count} info)
 - Baseline outliers: {list metric names and status}
 
-Knowledge extracted:
+Knowledge delivered:
+- {N} entries served across {N} sessions. Example: #{id} "{title}" retrieved in {phase} — {one sentence on how it shaped the work}.
+
+Knowledge curated:
 - Patterns: {count} new, {count} updated
 - Procedures: {count} new, {count} updated
 - Lessons learned: {count} new ({count} from hotspots, {count} from gate failures)
@@ -280,17 +255,3 @@ Knowledge extracted:
 Details:
 {list each entry with Unimatrix ID, title, and whether new or updated}
 ```
-
----
-
-## When to Go Lightweight
-
-Not every feature needs a full retro:
-
-| Situation | Action |
-|---|---|
-| Zero gate failures, no rework, zero hotspots | Skip lesson extraction. Focus on patterns/procedures only. |
-| Minor enhancement (1-2 components) | Check for pattern drift only, skip procedure review. |
-| New infrastructure introduced | Full retro — high likelihood of new patterns and procedures. |
-| Multiple SCOPE FAILs or heavy rework | Full retro — prioritize lesson extraction. |
-| Many Warning hotspots or baseline outliers | Full retro — prioritize hotspot-driven lessons and procedure updates. |

package/skills/uni-review-pr/SKILL.md

@@ -88,6 +88,20 @@ If any blocking item → `Merge readiness: BLOCKED` with specific items listed
 
 ---
 
+## Step 3b: Commit Security Reviewer Report
+
+After the security reviewer returns, commit its report to the PR branch so it is included in the merge:
+
+```bash
+git add product/features/{id}/agents/{feature-id}-security-reviewer-report.md
+git commit -m "chore: add security reviewer report ({feature-id}) (#{issue})"
+git push
+```
+
+If the PR is already merged and you are on `main`, commit directly to main instead.
+
+---
+
 ## Step 4: Report
 
 Post security review result to GH Issue:

package/skills/uni-seed/SKILL.md

@@ -9,7 +9,7 @@ description: "Populate Unimatrix with foundational repository knowledge through
 
 Before running this skill:
 
-1. **MCP server running**: The Unimatrix MCP server (`unimatrix-server`) must be running and wired in your Claude Code `settings.json`. This skill calls `context_status`, `context_search`, and `context_store` — all require an operational MCP server.
+1. **MCP server running**: The Unimatrix MCP server (`unimatrix`) must be running and wired in your Claude Code `settings.json`. This skill calls `context_status`, `context_search`, and `context_store` — all require an operational MCP server.
 2. **Recommended**: Run `/uni-init` first to set up the CLAUDE.md knowledge block. Seeding works without it, but the CLAUDE.md block provides ongoing awareness.
 
 If `context_status` fails at startup, the MCP server is not available. Consult the installation documentation for wiring setup.
@@ -18,6 +18,8 @@ If `context_status` fails at startup, the MCP server is not available. Consult t
 
 ## What This Skill Does
 
+A fresh Unimatrix install starts with an empty database; this skill provides an initial curated knowledge set.
+
 Guides you through populating Unimatrix with foundational knowledge about your repository. The skill explores your repo structure in bounded levels, proposes knowledge entries, and stores only what you approve.
 
 **Depth limit**: Level 0 (automatic) + up to 2 opt-in levels. No deeper. You control how far to go.
@@ -46,12 +48,16 @@ Follow these steps in strict order. At every gate marked with **STOP**, halt and
 
 **This must be the very first action. Do not read any files before this step.**
 
-Call `context_status()`.
+> **Important:** Run once per new project before the first delivery session.
+> Do not re-run on an established installation — seed entries will duplicate
+> existing knowledge.
+
+Call `mcp__unimatrix__context_status({})`.
 
 - **If the call fails or returns an error**: Print the following and halt immediately. Do not proceed to any further steps.
   ```
   Unimatrix MCP is not available.
-  Ensure unimatrix-server is running and wired in your Claude settings.json.
+  Ensure unimatrix is running and wired in your Claude settings.json.
   See installation documentation for setup instructions.
   ```
 
@@ -64,9 +70,9 @@ Call `context_status()`.
 Check whether seed entries already exist to avoid near-duplicates.
 
 Call `context_search` for each seeding category:
-- `context_search(query: "repository", category: "convention", k: 5)`
-- `context_search(query: "repository", category: "pattern", k: 5)`
-- `context_search(query: "repository", category: "procedure", k: 5)`
+- `mcp__unimatrix__context_search({"query": "repository", "category": "convention", "k": 5})`
+- `mcp__unimatrix__context_search({"query": "repository", "category": "pattern", "k": 5})`
+- `mcp__unimatrix__context_search({"query": "repository", "category": "procedure", "k": 5})`
 
 Count the total results across all three searches.
 
@@ -146,14 +152,14 @@ Approve all entries? (approve / reject)
 
 - **If approved**: Store each entry via `context_store`:
   ```
-  context_store(
-    title: "{what}",
-    content: "What: {what}\nWhy: {why}\nScope: {scope}",
-    topic: "{repo name or top-level context}",
-    category: "{convention|pattern|procedure}",
-    tags: ["seed", "level-0"],
-    agent_id: "uni-seed"
-  )
+  mcp__unimatrix__context_store({
+    "title": "{what}",
+    "content": "What: {what}\nWhy: {why}\nScope: {scope}",
+    "topic": "{repo name or top-level context}",
+    "category": "{convention|pattern|procedure}",
+    "tags": ["seed", "level-0"],
+    "agent_id": "uni-seed"
+  })
   ```
   Report success or failure for each entry individually. If a `context_store` call fails, report which entry failed and continue storing the remaining entries.
 

package/skills/uni-store-adr/SKILL.md

@@ -18,7 +18,7 @@ Stores an architectural decision record in Unimatrix as the **sole authoritative
 ### Step 1: Search for prior ADRs in the same domain (MANDATORY)
 
 ```
-mcp__unimatrix__context_search(query: "{decision domain}", category: "decision", k: 5)
+mcp__unimatrix__context_search({"query": "{decision domain}", "category": "decision", "k": 5})
 ```
 
 Check if any existing ADR covers the same concern. If so, you may need to supersede it (see "How to Supersede" below).
@@ -26,16 +26,16 @@ Check if any existing ADR covers the same concern. If so, you may need to supers
 ### Step 2: Store the ADR
 
 ```
-mcp__unimatrix__context_store(
-  title: "ADR-NNN: {decision title}",
-  content: "## Context\n{why this decision is needed}\n\n## Decision\n{what we decided}\n\n## Consequences\n{what follows from this decision}",
-  topic: "{feature-id}",
-  category: "decision",
-  tags: ["adr", "{phase-prefix}", "{domain-tags}"],
-  source: "architect",
-  feature_cycle: "{feature-id}",
-  agent_id: "{your role name, e.g. uni-architect}"
-)
+mcp__unimatrix__context_store({
+  "title": "ADR-NNN: {decision title}",
+  "content": "## Context\n{why this decision is needed}\n\n## Decision\n{what we decided}\n\n## Consequences\n{what follows from this decision}",
+  "topic": "{feature-id}",
+  "category": "decision",
+  "tags": ["adr", "{phase-prefix}", "{domain-tags}"],
+  "source": "architect",
+  "feature_cycle": "{feature-id}",
+  "agent_id": "{your role name, e.g. uni-architect}"
+})
 ```
 
 ### Step 3: Record the entry ID
@@ -63,7 +63,7 @@ When a new decision replaces a prior one:
 ### Step 1: Find the old ADR
 
 ```
-mcp__unimatrix__context_search(query: "{domain of old decision}", category: "decision")
+mcp__unimatrix__context_search({"query": "{domain of old decision}", "category": "decision"})
 ```
 
 Note the old entry's ID.
@@ -71,12 +71,12 @@ Note the old entry's ID.
 ### Step 2: Use context_correct to supersede
 
 ```
-mcp__unimatrix__context_correct(
-  original_id: {old entry ID},
-  content: "## Context\n{why the old decision is being replaced}\n\n## Decision\n{new decision}\n\n## Consequences\n{what changes}",
-  title: "ADR-NNN: {new decision title}",
-  reason: "Superseded by {feature-id}: {short explanation}"
-)
+mcp__unimatrix__context_correct({
+  "original_id": 1234,  // integer — never quote it
+  "content": "## Context\n{why the old decision is being replaced}\n\n## Decision\n{new decision}\n\n## Consequences\n{what changes}",
+  "title": "ADR-NNN: {new decision title}",
+  "reason": "Superseded by {feature-id}: {short explanation}"
+})
 ```
 
 This automatically:

package/skills/uni-store-lesson/SKILL.md

@@ -18,11 +18,11 @@ Stores a lesson learned in Unimatrix. Lessons capture what went wrong, why, and
 ### Step 1: Check for existing lessons in the same area
 
 ```
-mcp__unimatrix__context_search(
-  query: "{what went wrong}",
-  category: "lesson-learned",
-  k: 3
-)
+mcp__unimatrix__context_search({
+  "query": "{what went wrong}",
+  "category": "lesson-learned",
+  "k": 3
+})
 ```
 
 If a matching lesson already exists, go to Step 2b (supersede) instead of creating a duplicate.
@@ -30,24 +30,24 @@ If a matching lesson already exists, go to Step 2b (supersede) instead of creati
 ### Step 2a: Store NEW lesson (no prior exists)
 
 ```
-mcp__unimatrix__context_store(
-  title: "{concise description of what went wrong}",
-  content: "{structured lesson content}",
-  topic: "{feature-id or crate}",
-  category: "lesson-learned",
-  tags: ["{domain}", "{failure-type}"],
-  agent_id: "{your role name, e.g. uni-architect}"
-)
+mcp__unimatrix__context_store({
+  "title": "{concise description of what went wrong}",
+  "content": "{structured lesson content}",
+  "topic": "{feature-id or crate}",
+  "category": "lesson-learned",
+  "tags": ["{domain}", "{failure-type}"],
+  "agent_id": "{your role name, e.g. uni-architect}"
+})
 ```
 
 ### Step 2b: Supersede EXISTING lesson (prior exists but is incomplete or outdated)
 
 ```
-mcp__unimatrix__context_correct(
-  original_id: {old entry ID},
-  content: "{updated lesson with new evidence or broader scope}",
-  reason: "Updated: {what new evidence or context was added}"
-)
+mcp__unimatrix__context_correct({
+  "original_id": 1234,  // integer — never quote it
+  "content": "{updated lesson with new evidence or broader scope}",
+  "reason": "Updated: {what new evidence or context was added}"
+})
 ```
 
 This deprecates the old lesson and creates a corrected version with a supersession chain. Future searches return the latest version.
@@ -57,7 +57,7 @@ This deprecates the old lesson and creates a corrected version with a supersessi
 If a lesson is simply wrong or no longer applies (e.g., the underlying code was redesigned):
 
 ```
-mcp__unimatrix__context_deprecate(id: {entry ID}, reason: "{why it no longer applies}")
+mcp__unimatrix__context_deprecate({"id": 1234, "reason": "{why it no longer applies}"})  // id is an integer — never quote it
 ```
 
 ---

package/skills/uni-store-pattern/SKILL.md

@@ -30,11 +30,11 @@ Stores a reusable pattern in Unimatrix. Patterns capture implementation gotchas,
 ### Step 1: Check for existing patterns in the same area
 
 ```
-mcp__unimatrix__context_search(
-  query: "{what the pattern is about}",
-  category: "pattern",
-  k: 3
-)
+mcp__unimatrix__context_search({
+  "query": "{what the pattern is about}",
+  "category": "pattern",
+  "k": 3
+})
 ```
 
 If a matching pattern already exists, go to Step 2b (supersede) instead of creating a duplicate.
@@ -48,24 +48,24 @@ Assemble the content from three required fields:
 - **Scope**: Where it applies — crate name, module, or context.
 
 ```
-mcp__unimatrix__context_store(
-  title: "{concise what statement}",
-  content: "What: {what}\nWhy: {why}\nScope: {scope}",
-  topic: "{crate name or module — e.g., 'unimatrix-store'}",
-  category: "pattern",
-  tags: ["{domain}", "{feature_cycle if known}"],
-  agent_id: "{your role name, e.g. uni-rust-dev}"
-)
+mcp__unimatrix__context_store({
+  "title": "{concise what statement}",
+  "content": "What: {what}\nWhy: {why}\nScope: {scope}",
+  "topic": "{crate name or module — e.g., 'unimatrix-store'}",
+  "category": "pattern",
+  "tags": ["{domain}", "{feature_cycle if known}"],
+  "agent_id": "{your role name, e.g. uni-rust-dev}"
+})
 ```
 
 ### Step 2b: Supersede EXISTING pattern (prior exists but is incomplete or outdated)
 
 ```
-mcp__unimatrix__context_correct(
-  original_id: {old entry ID},
-  content: "What: {updated what}\nWhy: {updated why}\nScope: {updated scope}",
-  reason: "Updated: {what changed and why}"
-)
+mcp__unimatrix__context_correct({
+  "original_id": 1234,  // integer — never quote it
+  "content": "What: {updated what}\nWhy: {updated why}\nScope: {updated scope}",
+  "reason": "Updated: {what changed and why}"
+})
 ```
 
 This deprecates the old pattern and creates a corrected version with a supersession chain.

package/skills/uni-store-procedure/SKILL.md

@@ -30,11 +30,11 @@ If it has **numbered steps**, it's a procedure. If it's a **rule**, it's a conve
 ### Step 1: Check for existing procedure
 
 ```
-mcp__unimatrix__context_search(
-  query: "{what the procedure covers}",
-  category: "procedure",
-  k: 3
-)
+mcp__unimatrix__context_search({
+  "query": "{what the procedure covers}",
+  "category": "procedure",
+  "k": 3
+})
 ```
 
 If an existing procedure covers the same task, use Step 2 (Update) instead.
@@ -42,24 +42,24 @@ If an existing procedure covers the same task, use Step 2 (Update) instead.
 ### Step 2a: Store NEW procedure
 
 ```
-mcp__unimatrix__context_store(
-  title: "How to {task description}",
-  content: "{step-by-step content}",
-  topic: "{crate or area — e.g., 'unimatrix-server'}",
-  category: "procedure",
-  tags: ["{domain}", "{consuming-roles}"],
-  agent_id: "{your role name, e.g. uni-architect}"
-)
+mcp__unimatrix__context_store({
+  "title": "How to {task description}",
+  "content": "{step-by-step content}",
+  "topic": "{crate or area — e.g., 'unimatrix-server'}",
+  "category": "procedure",
+  "tags": ["{domain}", "{consuming-roles}"],
+  "agent_id": "{your role name, e.g. uni-architect}"
+})
 ```
 
 ### Step 2b: UPDATE existing procedure (supersedes old version)
 
 ```
-mcp__unimatrix__context_correct(
-  original_id: {old entry ID},
-  content: "{updated step-by-step content}",
-  reason: "Updated: {what changed and why}"
-)
+mcp__unimatrix__context_correct({
+  "original_id": 1234,  // integer — never quote it
+  "content": "{updated step-by-step content}",
+  "reason": "Updated: {what changed and why}"
+})
 ```
 
 This deprecates the old entry and creates a new one with a supersession chain. Agents querying later will get the latest version.