wicked-brain 0.12.1 → 0.13.0

package/skills/wicked-brain-configure/SKILL.md

@@ -1,6 +1,11 @@
 ---
 name: wicked-brain:configure
-description: Read brain state and write contextual instructions into the active CLI's agent config file. Run after onboarding, major ingests, or consolidation.
+description: |
+  This skill should be used when the user says "configure brain CLI",
+  "update CLAUDE.md from brain", "write brain orientation", or
+  "regenerate brain config". Reads brain state and writes contextual
+  instructions into the active CLI's agent config file. Run after
+  onboarding, major ingests, or consolidation.
 ---
 
 # wicked-brain:configure
@@ -9,15 +14,10 @@ Writes a contextual `## wicked-brain` section into the active CLI/IDE's agent co
 
 ## Config
 
-Resolve the brain config via the shared resolution in
-wicked-brain:init § "Resolving the brain config". In short: try
-`~/.wicked-brain/projects/{cwd_basename}/_meta/config.json` first, fall back
-to `~/.wicked-brain/_meta/config.json` (legacy flat), else trigger
-wicked-brain:init. Read the resolved file for brain path and server port.
-
-Do NOT read a bare relative `_meta/config.json` — the model will resolve it
-against the current working directory and brain files will end up in the
-project root.
+Brain discovery + server lifecycle are handled by `wicked-brain-call`. Pass
+`--brain <path>` to override the auto-detected brain, or set
+`WICKED_BRAIN_PATH`. The CLI starts the server on first call (no manual
+init required) and writes an audit record to `{brain}/calls/` per call.
 
 ## Process
 
@@ -25,16 +25,12 @@ project root.
 
 1. Call server stats:
 ```bash
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"stats"}'
+npx wicked-brain-call stats
 ```
 
 2. Search for top topics — run a broad search to identify dominant tags:
 ```bash
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"search","params":{"query":"*","limit":50}}'
+npx wicked-brain-call search --param query=* --param limit=50
 ```
 Read frontmatter of top results, count `contains:` tag frequency. Top 10 tags = brain expertise.
 

package/skills/wicked-brain-confirm/SKILL.md

@@ -15,8 +15,9 @@ You adjust the confidence score of a brain link based on user feedback.
 
 ## Cross-Platform Notes
 
-Commands in this skill work on macOS, Linux, and Windows. `curl` is available
-on Windows 10+ and macOS/Linux — it is used here for API calls.
+This skill uses `npx wicked-brain-call` for all server interaction. The CLI
+works on macOS, Linux, and Windows; it discovers the brain, auto-starts the
+server, and writes a per-call audit record under `{brain}/calls/`.
 
 For the brain path default:
 - macOS/Linux: ~/.wicked-brain
@@ -24,15 +25,10 @@ For the brain path default:
 
 ## Config
 
-Resolve the brain config via the shared resolution in
-wicked-brain:init § "Resolving the brain config". In short: try
-`~/.wicked-brain/projects/{cwd_basename}/_meta/config.json` first, fall back
-to `~/.wicked-brain/_meta/config.json` (legacy flat), else trigger
-wicked-brain:init. Read the resolved file for brain path and server port.
-
-Do NOT read a bare relative `_meta/config.json` — the model will resolve it
-against the current working directory and brain files will end up in the
-project root.
+Brain discovery + server lifecycle are handled by `wicked-brain-call`. Pass
+`--brain <path>` to override the auto-detected brain, or set
+`WICKED_BRAIN_PATH`. The CLI starts the server on first call (no manual
+init required) and writes an audit record to `{brain}/calls/` per call.
 
 ## Parameters
 
@@ -50,9 +46,7 @@ Ensure `source_id`, `target_path`, and `verdict` are provided.
 ### Step 2: Submit the verdict to the server
 
 ```bash
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"confirm_link","params":{"source_id":"{source_id}","target_path":"{target_path}","verdict":"{verdict}"}}'
+npx wicked-brain-call confirm_link --param source_id={source_id} --param target_path={target_path} --param verdict={verdict}
 ```
 
 ### Step 3: Report the result

package/skills/wicked-brain-enhance/SKILL.md

@@ -10,7 +10,7 @@ description: |
 
 # wicked-brain:enhance
 
-You enhance the brain by dispatching a subagent that fills knowledge gaps.
+Enhances the brain by dispatching a subagent that fills knowledge gaps.
 
 ## Cross-Platform Notes
 
@@ -24,15 +24,10 @@ For the brain path default:
 
 ## Config
 
-Resolve the brain config via the shared resolution in
-wicked-brain:init § "Resolving the brain config". In short: try
-`~/.wicked-brain/projects/{cwd_basename}/_meta/config.json` first, fall back
-to `~/.wicked-brain/_meta/config.json` (legacy flat), else trigger
-wicked-brain:init. Read the resolved file for brain path and server port.
-
-Do NOT read a bare relative `_meta/config.json` — the model will resolve it
-against the current working directory and brain files will end up in the
-project root.
+Brain discovery + server lifecycle are handled by `wicked-brain-call`. Pass
+`--brain <path>` to override the auto-detected brain, or set
+`WICKED_BRAIN_PATH`. The CLI starts the server on first call (no manual
+init required) and writes an audit record to `{brain}/calls/` per call.
 
 ## Process
 
@@ -40,7 +35,7 @@ Dispatch an enhance subagent with these instructions:
 
 ```
 You are a knowledge enhancement agent for the digital brain at {brain_path}.
-Server: http://localhost:{port}/api
+Server interactions: use `npx wicked-brain-call <action> [--param k=v ...]`.
 
 ## Step 1: Find gaps
 
@@ -51,9 +46,7 @@ Read the recent event log using your Read tool on `{brain_path}/_meta/log.jsonl`
 
 Get stats:
 ```bash
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"stats","params":{}}'
+npx wicked-brain-call stats
 ```
 
 Read _meta/log.jsonl. Look for:

package/skills/wicked-brain-forget/SKILL.md

@@ -16,21 +16,19 @@ and the archive-rename convention used by wicked-brain:agent dispatch consolidat
 
 ## Cross-Platform Notes
 
-- Uses `curl` for server API calls (Windows 10+, macOS, Linux)
+This skill uses `npx wicked-brain-call` for all server interaction. The CLI
+works on macOS, Linux, and Windows; it discovers the brain, auto-starts the
+server, and writes a per-call audit record under `{brain}/calls/`.
+
 - Uses agent-native Read/Bash tools for file ops — no Unix-only shell features
 - Paths always use forward slashes
 
 ## Config
 
-Resolve the brain config via the shared resolution in
-wicked-brain:init § "Resolving the brain config". In short: try
-`~/.wicked-brain/projects/{cwd_basename}/_meta/config.json` first, fall back
-to `~/.wicked-brain/_meta/config.json` (legacy flat), else trigger
-wicked-brain:init. Read the resolved file for brain path and server port.
-
-Do NOT read a bare relative `_meta/config.json` — the model will resolve it
-against the current working directory and brain files will end up in the
-project root.
+Brain discovery + server lifecycle are handled by `wicked-brain-call`. Pass
+`--brain <path>` to override the auto-detected brain, or set
+`WICKED_BRAIN_PATH`. The CLI starts the server on first call (no manual
+init required) and writes an audit record to `{brain}/calls/` per call.
 
 ## Parameters
 
@@ -58,9 +56,7 @@ memory) inspect its frontmatter so the log entry can record type/tier.
 ### Step 3: Remove from index
 
 ```bash
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"remove","params":{"id":"{id}"}}'
+npx wicked-brain-call remove --param id={id}
 ```
 
 ### Step 4: Archive the file

package/skills/wicked-brain-ingest/SKILL.md

@@ -25,15 +25,10 @@ For the brain path default:
 
 ## Config
 
-Resolve the brain config via the shared resolution in
-wicked-brain:init § "Resolving the brain config". In short: try
-`~/.wicked-brain/projects/{cwd_basename}/_meta/config.json` first, fall back
-to `~/.wicked-brain/_meta/config.json` (legacy flat), else trigger
-wicked-brain:init. Read the resolved file for brain path and server port.
-
-Do NOT read a bare relative `_meta/config.json` — the model will resolve it
-against the current working directory and brain files will end up in the
-project root.
+Brain discovery + server lifecycle are handled by `wicked-brain-call`. Pass
+`--brain <path>` to override the auto-detected brain, or set
+`WICKED_BRAIN_PATH`. The CLI starts the server on first call (no manual
+init required) and writes an audit record to `{brain}/calls/` per call.
 
 ## Parameters
 
@@ -43,18 +38,15 @@ project root.
 
 ### Step 0: Ensure server is running
 
-Before doing anything else, health-check the server:
+`wicked-brain-call` auto-starts the server on first invocation, so an
+explicit health check is not required. If you want to be defensive, run:
 
 ```bash
-curl -s -f -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"health","params":{}}'
+npx wicked-brain-call health
 ```
 
-If this fails (connection refused or non-2xx), invoke `wicked-brain:server` to start it
-before continuing. Re-read `{brain_path}/_meta/config.json` (the resolved
-config from the Config section above) after the server starts to get the
-actual port it bound to.
+Exit code 0 means the server is up. Exit code 2 means an infra failure
+(server could not be reached or spawned) — surface the error to the user.
 
 ### Step 1: Assess scope
 
@@ -79,7 +71,7 @@ You are an ingest agent for the digital brain at {brain_path}.
 
 Source file: {source_path}
 Source name: {safe_name} (lowercase, hyphens for special chars)
-Server: http://localhost:{port}/api
+Server interactions: use `npx wicked-brain-call <action>` (auto-discovers brain + port).
 
 ## Detect file type
 
@@ -147,9 +139,10 @@ Example:
 
 ## After writing chunks, index them in the server:
 
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"index","params":{"id":"{chunk_path}","path":"{chunk_path}","content":"{chunk_content}","brain_id":"{brain_id}"}}'
+Pass the full payload as positional JSON because `content` is a long blob with
+quotes and newlines:
+
+npx wicked-brain-call index '{"id":"{chunk_path}","path":"{chunk_path}","content":"{chunk_content}","brain_id":"{brain_id}"}'
 
 ## Report back
 
@@ -171,7 +164,7 @@ Instead, write a batch script and run it. This preserves context and is dramatic
 2. Write a script to the brain's `_meta/` directory that:
    - Walks the source directory
    - Filters by file extension (text types for deterministic, binary types for listing)
-   - For each text file: reads content, splits into chunks, writes chunk .md files, curls the index API
+   - For each text file: reads content, splits into chunks, writes chunk .md files, calls the index API (via fetch in Node, or `npx wicked-brain-call index` in shell)
    - For binary files: lists them for separate vision-based ingest
    - Logs progress to stdout
    - Writes a summary at the end
@@ -400,9 +393,7 @@ Archived files are invisible to the file watcher, so the server won't clean them
 1. List all .md files in `{brain_path}/chunks/extracted/{safe_name}/`
 2. For each file, call the server to remove it from the index:
    ```bash
-   curl -s -X POST http://localhost:{port}/api \
-     -H "Content-Type: application/json" \
-     -d '{"action":"remove","params":{"id":"chunks/extracted/{safe_name}/chunk-NNN.md"}}'
+   npx wicked-brain-call remove --param id=chunks/extracted/{safe_name}/chunk-NNN.md
    ```
 3. Then rename the directory to archive it:
    - macOS/Linux: `mv "{brain_path}/chunks/extracted/{safe_name}" "{brain_path}/chunks/extracted/{safe_name}.archived-$(date +%s)"`

package/skills/wicked-brain-init/SKILL.md

@@ -10,7 +10,7 @@ description: |
 
 # wicked-brain:init
 
-You initialize a new digital brain on the filesystem and get it fully operational.
+Initializes a new digital brain on the filesystem and gets it fully operational.
 
 ## Cross-Platform Notes
 
@@ -49,6 +49,10 @@ For the brain path default:
 
 ## Resolving the brain config
 
+> Most consumer skills now invoke `wicked-brain-call` directly and don't
+> need to resolve the brain themselves — see the section below for the
+> canonical resolution this skill performs at init time.
+
 **This section is the canonical resolution logic. Other skills point here —
 keep it authoritative.** Never read a bare relative `_meta/config.json`: the
 model will resolve it against the current working directory and brain files
@@ -183,7 +187,7 @@ Stop and wait for their answer before continuing.
 
 ### Step 3: Create directory structure
 
-Use your native Write tool to create these directories (write a `.gitkeep` placeholder in each):
+Use the native Write tool to create these directories (write a `.gitkeep` placeholder in each):
 - `{brain_path}/raw`
 - `{brain_path}/chunks/extracted`
 - `{brain_path}/chunks/inferred`
@@ -238,33 +242,32 @@ the real port — never hardcode `4242` in downstream calls.
 
 ### Step 6: Initialize the event log
 
-Use your Write tool to create an empty file at `{brain_path}/_meta/log.jsonl`.
+Use the Write tool to create an empty file at `{brain_path}/_meta/log.jsonl`.
 
 ### Step 7: Start the server
 
-Invoke `wicked-brain:server` to start the server against this brain path.
-The server will pick a free port and write it back to `_meta/config.json`.
+Use `wicked-brain-call` to start and verify the server in one step. It picks
+a free port, writes it back to `_meta/config.json`, and waits for the server
+to answer:
 
 ```bash
-npx wicked-brain-server --brain {brain_path} &
+npx wicked-brain-call --start --brain {brain_path}
+npx wicked-brain-call health --brain {brain_path}
 ```
 
-Do NOT pass `--port` unless the user specifies one — let the server pick a
-free port. After the process starts, **re-read `{brain_path}/_meta/config.json`**
-to get the actual `server_port` the server bound to. Use that port for the
-health check and all subsequent API calls.
+Verify the health response includes `"brain_id"` matching this brain's id —
+this confirms you're talking to the right server (not an unrelated brain on
+the same machine).
 
-Then health-check to confirm it's up before continuing:
+If you need the raw spawn (e.g. to pass extra flags), the server binary is
+still available directly:
 
 ```bash
-curl -s -X POST http://localhost:{actual_port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"health"}'
+npx wicked-brain-server --brain {brain_path} &
 ```
 
-Verify the response includes `"brain_id"` matching this brain's id — this
-confirms you're talking to the right server (not an unrelated brain on the
-same machine).
+Do NOT pass `--port` unless the user specifies one — let the server pick a
+free port.
 
 ### Step 8: Ingest the project
 

package/skills/wicked-brain-lint/SKILL.md

@@ -11,7 +11,7 @@ description: |
 
 # wicked-brain:lint
 
-You check brain quality by dispatching a lint subagent.
+Checks brain quality by dispatching a lint subagent.
 
 ## Cross-Platform Notes
 
@@ -25,15 +25,10 @@ For the brain path default:
 
 ## Config
 
-Resolve the brain config via the shared resolution in
-wicked-brain:init § "Resolving the brain config". In short: try
-`~/.wicked-brain/projects/{cwd_basename}/_meta/config.json` first, fall back
-to `~/.wicked-brain/_meta/config.json` (legacy flat), else trigger
-wicked-brain:init. Read the resolved file for brain path and server port.
-
-Do NOT read a bare relative `_meta/config.json` — the model will resolve it
-against the current working directory and brain files will end up in the
-project root.
+Brain discovery + server lifecycle are handled by `wicked-brain-call`. Pass
+`--brain <path>` to override the auto-detected brain, or set
+`WICKED_BRAIN_PATH`. The CLI starts the server on first call (no manual
+init required) and writes an audit record to `{brain}/calls/` per call.
 
 ## Process
 
@@ -41,7 +36,7 @@ Dispatch a lint subagent with these instructions:
 
 ```
 You are a quality assurance agent for the digital brain at {brain_path}.
-Server: http://localhost:{port}/api
+Server interactions: use `npx wicked-brain-call <action> [--param k=v ...]`.
 
 ## Pass 1: Deterministic checks
 
@@ -92,9 +87,7 @@ Check each chunk has required frontmatter fields (source, chunk_id, confidence,
 Call the server to get all tag frequencies:
 
 ```bash
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"tag_frequency","params":{}}'
+npx wicked-brain-call tag_frequency
 ```
 
 The response contains `tags: [{tag, count}]`. Identify potential synonyms:
@@ -117,9 +110,7 @@ Only report pairs where both tags have at least 1 use.
 Call the server for link health:
 
 ```bash
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"link_health","params":{}}'
+npx wicked-brain-call link_health
 ```
 
 The response contains:
@@ -146,9 +137,7 @@ Read a sample of chunks and wiki articles. Check:
 - Are there factual contradictions between articles?
 - Check for `contradicts` typed links — query the server:
   ```bash
-  curl -s -X POST http://localhost:{port}/api \
-    -H "Content-Type: application/json" \
-    -d '{"action":"contradictions","params":{}}'
+  npx wicked-brain-call contradictions
   ```
   For each contradiction link, read both the source and target to determine
   if the contradiction is resolved. Flag unresolved contradictions as warnings.

package/skills/wicked-brain-lsp/SKILL.md

@@ -16,6 +16,10 @@ Universal code intelligence for any CLI/IDE via the brain's LSP client layer.
 
 ## Cross-Platform Notes
 
+This skill uses `npx wicked-brain-call` for all server interaction. The CLI
+works on macOS, Linux, and Windows; it discovers the brain, auto-starts the
+server, and writes a per-call audit record under `{brain}/calls/`.
+
 Commands in this skill work on macOS, Linux, and Windows. When a command has
 platform differences, alternatives are shown. Your native tools (Read, Write,
 Grep, Glob) work everywhere — prefer them over shell commands when possible.
@@ -24,7 +28,6 @@ For the brain path default:
 - macOS/Linux: ~/.wicked-brain
 - Windows: %USERPROFILE%\.wicked-brain
 
-- `curl` works on macOS, Linux, and Windows 10+
 - File paths must be absolute
 - On Windows, use forward slashes in file URIs passed to the server. Most LSP
   servers accept `file:///C:/Users/me/project/file.ts` (forward slashes, three
@@ -40,15 +43,10 @@ whether the language server process is running and review its stderr logs.
 
 ## Config
 
-Resolve the brain config via the shared resolution in
-wicked-brain:init § "Resolving the brain config". In short: try
-`~/.wicked-brain/projects/{cwd_basename}/_meta/config.json` first, fall back
-to `~/.wicked-brain/_meta/config.json` (legacy flat), else trigger
-wicked-brain:init. Read the resolved file for brain path and server port.
-
-Do NOT read a bare relative `_meta/config.json` — the model will resolve it
-against the current working directory and brain files will end up in the
-project root.
+Brain discovery + server lifecycle are handled by `wicked-brain-call`. Pass
+`--brain <path>` to override the auto-detected brain, or set
+`WICKED_BRAIN_PATH`. The CLI starts the server on first call (no manual
+init required) and writes an audit record to `{brain}/calls/` per call.
 
 ## Prerequisites — Source Path
 
@@ -148,16 +146,12 @@ Before calling `lsp-workspace-symbols` for the first time on any brain server:
 
 2. Call a file-specific action to trigger `ensureReady`:
    ```bash
-   curl -s -X POST http://localhost:{port}/api \
-     -H "Content-Type: application/json" \
-     -d '{"action":"lsp-symbols","params":{"file":"{absolute_path_to_real_file}"}}'
+   npx wicked-brain-call lsp-symbols --param file={absolute_path_to_real_file}
    ```
 
 3. Poll `lsp-health` until a server is `ready` (not `starting`):
    ```bash
-   curl -s -X POST http://localhost:{port}/api \
-     -H "Content-Type: application/json" \
-     -d '{"action":"lsp-health"}'
+   npx wicked-brain-call lsp-health
    ```
    Expected ready response:
    ```json
@@ -215,31 +209,31 @@ Based on what the user/agent needs, pick the appropriate action from the table a
 ### Step 2: Call the server
 
 ```bash
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"{action}","params":{params}}'
+npx wicked-brain-call <action> [--param k=v ...]
+# or for nested params:
+npx wicked-brain-call <action> '{"k":"v",...}'
 ```
 
 **Position-based actions** (definition, references, hover, implementation, call-hierarchy):
-```json
-{"action":"lsp-definition","params":{"file":"/absolute/path/to/file.ts","line":15,"col":10}}
+```bash
+npx wicked-brain-call lsp-definition --param file=/absolute/path/to/file.ts --param line=15 --param col=10
 ```
 Note: `line` and `col` are 0-indexed.
 
 **File-based actions** (symbols):
-```json
-{"action":"lsp-symbols","params":{"file":"/absolute/path/to/file.ts"}}
+```bash
+npx wicked-brain-call lsp-symbols --param file=/absolute/path/to/file.ts
 ```
 
 **Query-based actions** (workspace-symbols):
-```json
-{"action":"lsp-workspace-symbols","params":{"query":"PaymentService"}}
+```bash
+npx wicked-brain-call lsp-workspace-symbols --param query=PaymentService
 ```
 
 **No-params actions** (health, diagnostics without file):
-```json
-{"action":"lsp-health"}
-{"action":"lsp-diagnostics"}
+```bash
+npx wicked-brain-call lsp-health
+npx wicked-brain-call lsp-diagnostics
 ```
 
 ### Step 3: Handle errors — auto-install

package/skills/wicked-brain-memory/SKILL.md

@@ -14,22 +14,20 @@ Store and recall experiential learnings in the brain's memory system.
 
 ## Cross-Platform Notes
 
-- Uses `curl` for server API calls (available on Windows 10+, macOS, Linux)
+This skill uses `npx wicked-brain-call` for all server interaction. The CLI
+works on macOS, Linux, and Windows; it discovers the brain, auto-starts the
+server, and writes a per-call audit record under `{brain}/calls/`.
+
 - File writes use agent-native tools (Write/Edit), not shell commands
 - Path separator: always use forward slashes in `contains:` and `path` fields
 - Brain path default: `~/.wicked-brain/projects/{project-name}` (macOS/Linux), `%USERPROFILE%\.wicked-brain\projects\{project-name}` (Windows)
 
 ## Config
 
-Resolve the brain config via the shared resolution in
-wicked-brain:init § "Resolving the brain config". In short: try
-`~/.wicked-brain/projects/{cwd_basename}/_meta/config.json` first, fall back
-to `~/.wicked-brain/_meta/config.json` (legacy flat), else trigger
-wicked-brain:init. Read the resolved file for brain path and server port.
-
-Do NOT read a bare relative `_meta/config.json` — the model will resolve it
-against the current working directory and brain files will end up in the
-project root.
+Brain discovery + server lifecycle are handled by `wicked-brain-call`. Pass
+`--brain <path>` to override the auto-detected brain, or set
+`WICKED_BRAIN_PATH`. The CLI starts the server on first call (no manual
+init required) and writes an audit record to `{brain}/calls/` per call.
 
 ## Parameters
 
@@ -190,9 +188,7 @@ Fire-and-forget — if the bus is not installed, silently skip.
 ### Step 1: Search
 
 ```bash
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"search","params":{"query":"{query}","limit":10,"session_id":"{session_id}"}}'
+npx wicked-brain-call search --param query={query} --param limit=10 --param session_id={session_id}
 ```
 
 Pass a session_id with every search call. This enables access tracking for

package/skills/wicked-brain-migrate/SKILL.md

@@ -11,13 +11,13 @@ description: |
 
 # wicked-brain:migrate
 
-You migrate a flat brain (all data directly under `~/.wicked-brain/`) into the
+Migrates a flat brain (all data directly under `~/.wicked-brain/`) into the
 per-project layout (each brain under `~/.wicked-brain/projects/{project-name}/`).
 This was the layout change introduced in v0.4.7.
 
 ## Cross-Platform Notes
 
-Commands in this skill work on macOS, Linux, and Windows. Prefer your native
+Commands in this skill work on macOS, Linux, and Windows. Prefer the native
 Read/Write/Glob tools over shell commands when possible.
 
 - macOS/Linux home: `~`
@@ -45,9 +45,9 @@ under the same `~/.wicked-brain/projects/` umbrella (recommended — pick
 distinct project names) or under separate containers if the user prefers
 isolation.
 
-If the user asks "migrate all my brains," enumerate the flat brains you can
-find first (`find ~ -maxdepth 3 -name brain.json 2>/dev/null` on macOS/Linux)
-and confirm each with the user before running migration on it.
+If the user asks "migrate all my brains," enumerate the discoverable flat
+brains first (`find ~ -maxdepth 3 -name brain.json 2>/dev/null` on
+macOS/Linux) and confirm each with the user before running migration on it.
 
 ## Process
 
@@ -198,11 +198,9 @@ npx wicked-brain-server --brain "{target_path}" &
 Wait for the server to start, then re-read `{target_path}/_meta/config.json`
 to get the bound port.
 
-Health-check:
+Health-check (the CLI auto-resolves the new brain's port from its config):
 ```bash
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"health"}'
+npx wicked-brain-call health --brain "{target_path}"
 ```
 
 Verify the response includes `"brain_id"` matching the id from Step 1. If the
@@ -215,16 +213,14 @@ Run a stats call against the new server and confirm the document count is
 non-zero (assuming the flat brain had any documents):
 
 ```bash
-curl -s -X POST http://localhost:{port}/api \
-  -H "Content-Type: application/json" \
-  -d '{"action":"stats"}'
+npx wicked-brain-call stats --brain "{target_path}"
 ```
 
 If document counts are zero but `.brain.db` was moved, the SQLite file may have
 been truncated during the move or the server is looking at the wrong path.
 **Do NOT proceed to Step 9.** Stop the new server and investigate — the flat
-`_meta/` is still intact at this point, so you can roll back by moving files
-back to `{flat_path}`.
+`_meta/` is still intact at this point, so rollback is possible by moving
+files back to `{flat_path}`.
 
 ### Step 9: Clean up the flat path (only after Steps 7 and 8 pass)