@blxzer/cursor-trellis 0.2.9 → 0.3.2

package/dist/templates/cursor/agents/{trellis-research.md → cstl-research.md}

@@ -1,5 +1,5 @@
 ---
-name: trellis-research
+name: cstl-research
 description: Trellis research agent. Use this exact agent for Trellis task research and research/ persistence. Do not use generic/default/generalPurpose agents for Trellis research.
 tools: Read, Write, Glob, Grep, Bash, WebSearch, WebFetch, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa, Skill, mcp__chrome-devtools__*
 ---
@@ -7,11 +7,11 @@ tools: Read, Write, Glob, Grep, Bash, WebSearch, WebFetch, mcp__exa__web_search_
 ## Entry points
 
 - **Agent session:** Open this agent file manually in a new chat — context from this file + your main-session prompt.
-- **Task dispatch:** Run `python ./.trellis/scripts/generate_dispatch_prompt.py --agent research` → pass stdout as `Task(..., prompt=...)` — context from the Layer 2 prompt.
+- **Task dispatch:** Run `python ./.cstl/scripts/generate_dispatch_prompt.py --agent research` → pass stdout as `Task(..., prompt=...)` — context from the Layer 2 prompt.
 
 ## Context source
 
-- **Layer 2 prompt = PRIMARY (guaranteed)** — always generate via CLI before `Task(trellis-research)`.
+- **Layer 2 prompt = PRIMARY (guaranteed)** — always generate via CLI before `Task(cstl-research)`.
 - **Hook `additional_context` = best-effort only** — Cursor #158452: not guaranteed to reach the model; optimization / fallback only.
 
 # Research Agent
@@ -21,7 +21,7 @@ You are the Research Agent in the Trellis workflow.
 ## Model policy
 
 - **Default:** no `model:` in this file → **inherit** parent session at spawn.
-- **Per dispatch:** main session asks the user, writes a **one-shot** `model:` here, runs `Task`, then **removes** `model:` (ephemeral overlay). See `.trellis/spec/guides/cursor-subagent-policy.md`.
+- **Per dispatch:** main session asks the user, writes a **one-shot** `model:` here, runs `Task`, then **removes** `model:` (ephemeral overlay). See `.cstl/spec/guides/cursor-subagent-policy.md`.
 - Dispatch: Cursor **Agent mode** (writable).
 
 ## Core Principle
@@ -50,7 +50,7 @@ Conversations get compacted; files don't. Every research output MUST end up as a
 
 ### Step 1: Resolve Selected Task
 
-Run `python ./.trellis/scripts/task.py selected --source` → selected task path. If no task is selected, ask the user where to write output; do NOT guess.
+Run `python ./.cstl/scripts/task.py selected --source` → selected task path. If no task is selected, ask the user where to write output; do NOT guess.
 
 Ensure `{TASK_DIR}/research/` exists:
 
@@ -68,9 +68,9 @@ Run independent searches in parallel (Glob + Grep + smart-search CLI for externa
 
 #### External search — provider relevance caveats
 
-- **Context7** and generic third-party library docs are often **irrelevant** to Trellis/Cursor platform questions. Prefer **Cursor / Cursor++ official documentation**, `docs.cursor.com`, and **local `.trellis/spec/`** before trusting Context7 hits.
+- **Context7** and generic third-party library docs are often **irrelevant** to Trellis/Cursor platform questions. Prefer **Cursor / Cursor++ official documentation**, `docs.cursor.com`, and **local `.cstl/spec/`** before trusting Context7 hits.
 - Every smart-search result you persist must **label the provider source** (e.g. `exa`, `context7`, `cursor-docs`, `tavily`) in the research file — in frontmatter or per bullet — so downstream check/finish can audit provenance.
-- Trellis harness facts: `./.trellis/scripts/run_smart_search.py` writes manifests under `{TASK}/research/smart-search/<run-id>/`; scored pack output (when built) is `{TASK}/research/retrieval-pack-latest.json`.
+- Trellis harness facts: `./.cstl/scripts/run_smart_search.py` writes manifests under `{TASK}/research/smart-search/<run-id>/`; scored pack output (when built) is `{TASK}/research/retrieval-pack-latest.json`.
 
 #### External search — manual query refinement
 
@@ -80,7 +80,7 @@ When the first smart-search pass returns irrelevant results, **refine before fal
 2. Add product scope: `+Trellis`, `+cursor-trellis`, or the exact API/hook name
 3. Switch route: `--intent official-source --include-domain cursor.com` or `--intent docs` for API reference
 4. Narrow time or topic: shorter query, version number, or feature name from local spec
-5. Re-run: `python ./.trellis/scripts/run_smart_search.py "<refined query>" --intent deep-research --json`
+5. Re-run: `python ./.cstl/scripts/run_smart_search.py "<refined query>" --intent deep-research --json`
 
 Only use Cursor WebSearch/WebFetch when smart-search is unavailable (`not_configured` / `failed` / timeout) — then persist with `source: cursor-web-fallback`.
 
@@ -110,8 +110,8 @@ Do NOT paste full research content into the reply. The files are the contract.
 ### Write FORBIDDEN
 
 - Code files (`src/`, `lib/`, …)
-- Spec files (`.trellis/spec/`) — main agent should use `update-spec` skill instead
-- `.trellis/scripts/`, `.trellis/workflow.md`, platform config (`.claude/`, `.cursor/`, etc.)
+- Spec files (`.cstl/spec/`) — main agent should use `update-spec` skill instead
+- `.cstl/scripts/`, `.cstl/workflow.md`, platform config (`.claude/`, `.cursor/`, etc.)
 - Other task directories
 - Any git operation (commit / push / branch / merge)
 
@@ -149,7 +149,7 @@ Each `{TASK_DIR}/research/<topic>.md` should follow:
 
 ### Related Specs
 
-- `.trellis/spec/xxx.md` — <description>
+- `.cstl/spec/xxx.md` — <description>
 
 ## Caveats / Not Found
 

package/dist/templates/cursor/commands/cursor2plus-setup.md

@@ -1,6 +1,6 @@
 # Trellis Cursor++ Subagent Model Setup
 
-Configure per-subagent-type model routing for Cursor++ BYOK. Run this after `trellis init` (when Cursor++ is selected), when providers change, or whenever you want to re-map which model each Trellis Task subagent uses.
+Configure per-subagent-type model routing for Cursor++ BYOK. Run this after `cstl init` (when Cursor++ is selected), when providers change, or whenever you want to re-map which model each Trellis Task subagent uses.
 
 Native Cursor API (no Cursor++): stop — this does not apply; agent frontmatter `model:` works natively.
 
@@ -10,21 +10,21 @@ Native Cursor API (no Cursor++): stop — this does not apply; agent frontmatter
 
 Confirm the Cursor++ data directory exists:
 
-- `~/.ccursor/providers.json` (or a custom path in `.trellis/local/cursor2plus/config.local.json`)
+- `~/.ccursor/providers.json` (or a custom path in `.cstl/local/cursor2plus/config.local.json`)
 
 If missing, Cursor++ is not set up — ask the user to install/configure it first.
 
 ## Step 2: List available models + roles
 
 ```bash
-python ./.trellis/local/cursor2plus/patch_wpelc8.py --list-models
-python ./.trellis/local/cursor2plus/patch_wpelc8.py --explain
+python ./.cstl/local/cursor2plus/patch_wpelc8.py --list-models
+python ./.cstl/local/cursor2plus/patch_wpelc8.py --explain
 ```
 
 `--list-models` shows the model catalog (apiModel / displayName / slug / provider) from `providers.json`.
 `--explain` lists the subagent types you can route:
 
-- `trellis-research`, `trellis-implement`, `trellis-check` (core Trellis roles)
+- `cstl-research`, `cstl-implement`, `cstl-check` (core Trellis roles)
 - `generalPurpose`, `shell`, `best-of-n-runner` (built-in Cursor Task types, optional)
 
 ## Step 3: Ask the user which model per role
@@ -35,27 +35,27 @@ The user may skip types they don't use — omit those from the map.
 
 ## Step 4: Write the routing map
 
-Write `~/.ccursor/trellis-task-models.json5` (or `~/.ccursor/` on Unix) using the structure from `.trellis/local/trellis-task-models.json5.example`:
+Write `~/.ccursor/trellis-task-models.json5` (or `~/.ccursor/` on Unix) using the structure from `.cstl/local/trellis-task-models.json5.example`:
 
 ```json5
 // Trellis + Cursor++ BYOK — per-subagent-type model routing
 {
   "models": {
     // <role comment>
-    "trellis-research": { "primary": "<model>", "fallback": "<model>" },
-    "trellis-implement": { "primary": "<model>", "fallback": "<model>" },
-    "trellis-check": { "primary": "<model>", "fallback": "<model>" }
+    "cstl-research": { "primary": "<model>", "fallback": "<model>" },
+    "cstl-implement": { "primary": "<model>", "fallback": "<model>" },
+    "cstl-check": { "primary": "<model>", "fallback": "<model>" }
   }
 }
 ```
 
-Project-level override (optional, wins on same key): `.trellis/local/subagent-models.json5`.
+Project-level override (optional, wins on same key): `.cstl/local/subagent-models.json5`.
 
 ## Step 5: Apply the patch + verify
 
 ```bash
-python ./.trellis/local/cursor2plus/patch_wpelc8.py --print-map
-python ./.trellis/local/cursor2plus/patch_wpelc8.py
+python ./.cstl/local/cursor2plus/patch_wpelc8.py --print-map
+python ./.cstl/local/cursor2plus/patch_wpelc8.py
 ```
 
 Then tell the user: **Developer: Reload Window** in Cursor (required once per patch for the resolver change to take effect).
@@ -76,7 +76,7 @@ Then tell the user: **Developer: Reload Window** in Cursor (required once per pa
 
 - User catalog: `~/.ccursor/providers.json`
 - User routing doc: `~/.ccursor/trellis-task-models.json5` (machine-local, gitignored)
-- Project override (optional): `.trellis/local/subagent-models.json5`
-- Patch bundle: `.trellis/local/cursor2plus/`
+- Project override (optional): `.cstl/local/subagent-models.json5`
+- Patch bundle: `.cstl/local/cursor2plus/`
 
-Policy: `.trellis/spec/guides/cursor-subagent-policy.md` (Method 2.5 / 2.6).
+Policy: `.cstl/spec/guides/cursor-subagent-policy.md` (Method 2.5 / 2.6).

package/dist/templates/cursor/fixtures/expected-rules.d.ts

@@ -3,7 +3,7 @@
  * Update alongside rule content changes in templates/cursor/rules/.
  */
 export interface ExpectedRule {
-    /** Filename including .mdc extension, e.g. "trellis-triage.mdc" */
+    /** Filename including .mdc extension, e.g. "cstl-triage.mdc" */
     filename: string;
     /** Substrings that must appear in rule body (case-sensitive) */
     requiredSections: string[];

package/dist/templates/cursor/fixtures/expected-rules.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"expected-rules.d.ts","sourceRoot":"","sources":["../../../../src/templates/cursor/fixtures/expected-rules.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,MAAM,WAAW,YAAY;IAC3B,mEAAmE;IACnE,QAAQ,EAAE,MAAM,CAAC;IACjB,gEAAgE;IAChE,gBAAgB,EAAE,MAAM,EAAE,CAAC;IAC3B,qDAAqD;IACrD,QAAQ,EAAE,MAAM,CAAC;CAClB;AAED,eAAO,MAAM,aAAa,EAAE,YAAY,EAoBvC,CAAC"}
+{"version":3,"file":"expected-rules.d.ts","sourceRoot":"","sources":["../../../../src/templates/cursor/fixtures/expected-rules.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,MAAM,WAAW,YAAY;IAC3B,gEAAgE;IAChE,QAAQ,EAAE,MAAM,CAAC;IACjB,gEAAgE;IAChE,gBAAgB,EAAE,MAAM,EAAE,CAAC;IAC3B,qDAAqD;IACrD,QAAQ,EAAE,MAAM,CAAC;CAClB;AAED,eAAO,MAAM,aAAa,EAAE,YAAY,EAoBvC,CAAC"}

package/dist/templates/cursor/fixtures/expected-rules.js

@@ -4,7 +4,7 @@
  */
 export const expectedRules = [
     {
-        filename: "trellis-triage.mdc",
+        filename: "cstl-triage.mdc",
         requiredSections: [
             "Decision tree",
             "Classification mark",
@@ -13,7 +13,7 @@ export const expectedRules = [
         minBytes: 500,
     },
     {
-        filename: "trellis-subagent-dispatch.mdc",
+        filename: "cstl-subagent-dispatch.mdc",
         requiredSections: ["Layer 2", "generate_dispatch_prompt", "CLI"],
         minBytes: 400,
     },

package/dist/templates/cursor/fixtures/expected-rules.js.map

@@ -1 +1 @@
-{"version":3,"file":"expected-rules.js","sourceRoot":"","sources":["../../../../src/templates/cursor/fixtures/expected-rules.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAWH,MAAM,CAAC,MAAM,aAAa,GAAmB;IAC3C;QACE,QAAQ,EAAE,oBAAoB;QAC9B,gBAAgB,EAAE;YAChB,eAAe;YACf,qBAAqB;YACrB,cAAc;SACf;QACD,QAAQ,EAAE,GAAG;KACd;IACD;QACE,QAAQ,EAAE,+BAA+B;QACzC,gBAAgB,EAAE,CAAC,SAAS,EAAE,0BAA0B,EAAE,KAAK,CAAC;QAChE,QAAQ,EAAE,GAAG;KACd;IACD;QACE,QAAQ,EAAE,uBAAuB;QACjC,gBAAgB,EAAE,CAAC,QAAQ,EAAE,MAAM,EAAE,WAAW,EAAE,cAAc,CAAC;QACjE,QAAQ,EAAE,GAAG;KACd;CACF,CAAC"}
+{"version":3,"file":"expected-rules.js","sourceRoot":"","sources":["../../../../src/templates/cursor/fixtures/expected-rules.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAWH,MAAM,CAAC,MAAM,aAAa,GAAmB;IAC3C;QACE,QAAQ,EAAE,iBAAiB;QAC3B,gBAAgB,EAAE;YAChB,eAAe;YACf,qBAAqB;YACrB,cAAc;SACf;QACD,QAAQ,EAAE,GAAG;KACd;IACD;QACE,QAAQ,EAAE,4BAA4B;QACtC,gBAAgB,EAAE,CAAC,SAAS,EAAE,0BAA0B,EAAE,KAAK,CAAC;QAChE,QAAQ,EAAE,GAAG;KACd;IACD;QACE,QAAQ,EAAE,uBAAuB;QACjC,gBAAgB,EAAE,CAAC,QAAQ,EAAE,MAAM,EAAE,WAAW,EAAE,cAAc,CAAC;QACjE,QAAQ,EAAE,GAAG;KACd;CACF,CAAC"}

package/dist/templates/cursor/rules/{trellis-subagent-dispatch.mdc → cstl-subagent-dispatch.mdc}

@@ -9,12 +9,12 @@ alwaysApply: true
 
 ## Rule
 
-Before calling `Task(subagent_type="trellis-research|trellis-implement|trellis-check", ...)` you MUST:
+Before calling `Task(subagent_type="cstl-research|cstl-implement|cstl-check", ...)` you MUST:
 
 1. Generate a complete dispatch prompt via CLI:
 
    ```powershell
-   python ./.trellis/scripts/generate_dispatch_prompt.py --agent <research|implement|check> --task "<task-path>" --repo-root "<repo-root>"
+   python ./.cstl/scripts/generate_dispatch_prompt.py --agent <research|implement|check> --task "<task-path>" --repo-root "<repo-root>"
    ```
 
 2. Use the CLI output as the `prompt` parameter value for `Task(...)`.
@@ -27,8 +27,8 @@ The generated prompt carries role identity ("You are the Trellis Research/Implem
 
 ## Auto-detection
 
-If `--task` is omitted, the script resolves the currently selected task. If `--repo-root` is omitted, it auto-detects via `.trellis` or `.git` upward search.
+If `--task` is omitted, the script resolves the currently selected task. If `--repo-root` is omitted, it auto-detects via `.cstl` or `.git` upward search.
 
 ## Exception
 
-This rule does NOT apply to `generalPurpose`, `explore`, `shell`, or other non-Trellis subagent types. Only `trellis-research`, `trellis-implement`, `trellis-check` require CLI-generated prompts.
+This rule does NOT apply to `generalPurpose`, `explore`, `shell`, or other non-Trellis subagent types. Only `cstl-research`, `cstl-implement`, `cstl-check` require CLI-generated prompts.

package/dist/templates/cursor/rules/{trellis-triage.mdc → cstl-triage.mdc}

@@ -10,7 +10,7 @@ You MUST classify every work-capable user request BEFORE acting. This is not a s
 ## Decision tree (first match wins)
 
 1. **No durable project change** (explanation, status, read-only lookup, one-liner Q&A) → `No Task`
-2. **Underspecified small request, no task yet** (needs clarification before work exists) → `Micro-Grill` (load `trellis-micro-grill`)
+2. **Underspecified small request, no task yet** (needs clarification before work exists) → `Micro-Grill` (load `cstl-micro-grill`)
 3. **Low-risk durable work, single file, local validation, no contract change** → `Lite Task`
 4. **Durable code/template/runtime/workflow change, cross-file behavior, or framework semantics** → `Full Task`
 5. **Multiple independent deliverables, staged/parallel execution, or integration authority** → `Parent Task`
@@ -33,6 +33,6 @@ If the user declines a task for a simple request, skip Trellis for this session.
 
 ## Why this rule exists
 
-Cursor's `sessionStart` hook has a confirmed bug (#158452): `additional_context` is never injected into the agent's system context. The Triage rules in `.trellis/workflow.md` therefore never reach you via that channel. This `.cursor/rules` file is the reliable workaround — Cursor prepends rules to your context before every prompt, independent of the broken sessionStart path.
+Cursor's `sessionStart` hook has a confirmed bug (#158452): `additional_context` is never injected into the agent's system context. The Triage rules in `.cstl/workflow.md` therefore never reach you via that channel. This `.cursor/rules` file is the reliable workaround — Cursor prepends rules to your context before every prompt, independent of the broken sessionStart path.
 
-Full decision-tree details, trigger-signal keywords, and the Task Ladder table: see `.trellis/workflow.md` → `### Request Triage`.
+Full decision-tree details, trigger-signal keywords, and the Task Ladder table: see `.cstl/workflow.md` → `### Request Triage`.

package/dist/templates/cursor/rules/retrieval-routing.mdc

@@ -18,13 +18,13 @@ If the user message or Trellis context contains a block starting with `## 代码
 Generate a fresh plan when needed:
 
 ```powershell
-python ./.trellis/scripts/route_codebase_retrieval.py "<question>" --instructions
+python ./.cstl/scripts/route_codebase_retrieval.py "<question>" --instructions
 ```
 
 JSON (includes `agentInstructions`):
 
 ```powershell
-python ./.trellis/scripts/route_codebase_retrieval.py "<question>" --json
+python ./.cstl/scripts/route_codebase_retrieval.py "<question>" --json
 ```
 
 ## Default tool order (no plan block)
@@ -36,7 +36,7 @@ python ./.trellis/scripts/route_codebase_retrieval.py "<question>" --json
 | Same name across packages (trap) | **codegraph_search** / **codegraph_explore** → Grep |
 | Extension symbols | **codegraph_search** under `extensions/` |
 | Conceptual / how does X work | **Native:** built-in `@codebase` / semantic search. **BYOK:** **fast_context_search** (fast-context MCP). Plans show `cursorEnv`. |
-| Policy / architecture / boundaries / storage rules | **Grep** on `AGENTS.md`, `**/AGENTS.md`, `.trellis/spec/**`, `README.md` (router `policy-docs-rg`) before implementation modules |
+| Policy / architecture / boundaries / storage rules | **Grep** on `AGENTS.md`, `**/AGENTS.md`, `.cstl/spec/**`, `README.md` (router `policy-docs-rg`) before implementation modules |
 | Definition jump | **codegraph_node** / **codegraph_search**, then **Read** (Agent does not expose GO_TO_DEFINITION / LSP) |
 | Wide cross-cutting explore | **Native:** DEEP_SEARCH or Explore subagent. **BYOK:** **Task explore** subagent, then Grep/codegraph/Read |
 
@@ -56,4 +56,4 @@ Use codegraph for **call chains**, **cross-package trap disambiguation**, **exte
 
 ## External facts
 
-Web/current events: **smart-search** first per `.trellis/spec/guides/retrieval-daily-guide.md`.
+Web/current events: **smart-search** first per `.cstl/spec/guides/retrieval-daily-guide.md`.

package/dist/templates/extract.d.ts

@@ -1,6 +1,6 @@
 type TemplateCategory = "scripts" | "markdown" | "commands";
 /**
- * Get the path to the trellis templates directory (.trellis/ scaffolding).
+ * Get the path to the trellis templates directory (.cstl/ scaffolding).
  */
 export declare function getTrellisTemplatePath(): string;
 /** @deprecated Use getTrellisTemplatePath() instead. */

package/dist/templates/extract.js

@@ -6,7 +6,7 @@ import { replacePythonCommandLiterals } from "../configurators/shared.js";
 const __filename = fileURLToPath(import.meta.url);
 const __dirname = path.dirname(__filename);
 /**
- * Get the path to the trellis templates directory (.trellis/ scaffolding).
+ * Get the path to the trellis templates directory (.cstl/ scaffolding).
  */
 export function getTrellisTemplatePath() {
     const templatePath = path.join(__dirname, "trellis");

package/dist/templates/markdown/agents.md

@@ -1,28 +1,28 @@
-<!-- TRELLIS:START -->
-# Trellis Instructions
+<!-- CSTL:START -->
+# Cursor-Trellis (cstl) Instructions
 
 These instructions are for AI assistants working in this project.
 
-This project is managed by Trellis. The working knowledge you need lives under `.trellis/`:
+This project is managed by cursor-trellis. The working knowledge you need lives under `.cstl/`:
 
-- `.trellis/workflow.md` — development phases, when to create tasks, skill routing
-- `.trellis/spec/` — package- and layer-scoped coding guidelines (read before writing code in a given layer)
-- `.trellis/workspace/` — per-developer journals and session traces
-- `.trellis/tasks/` — active and archived tasks (PRDs, research, jsonl context)
+- `.cstl/workflow.md` — development phases, when to create tasks, skill routing
+- `.cstl/spec/` — package- and layer-scoped coding guidelines (read before writing code in a given layer)
+- `.cstl/workspace/` — per-developer journals and session traces
+- `.cstl/tasks/` — active and archived tasks (PRDs, research, jsonl context)
 
-If a Trellis command is available on Cursor (e.g. `/trellis:finish-work`, `/trellis:continue`), prefer it over manual steps.
+If a cstl command is available on Cursor (e.g. `cstl-finish-work`, `cstl-continue`), prefer it over manual steps.
 
 ## Command surface (what is user-invocable vs internal)
 
 Only a handful of Trellis entry points are meant for **manual `/` invocation**. Everything else is an **internal auto-triggered skill** — the agent loads it via the skill matcher or workflow routing, not by being called directly. Do **not** manually invoke internal skills through the slash palette.
 
-- **User-invocable (manual)**: `/trellis-continue`, `/trellis-finish-work` (and `/trellis-start` when needed).
-- **Internal auto-triggered (do NOT call manually)**: `trellis-brainstorm`, `trellis-before-dev`, `trellis-check`, `trellis-break-loop`, `trellis-update-spec`, `trellis-micro-grill`, `trellis-meta`, `trellis-spec-bootstrap`, `trellis-skill-creator`, `smart-search-cli`. These activate on their own when the workflow/skill matcher decides they fit.
+- **User-invocable (manual)**: `cstl-continue`, `cstl-finish-work` (and `cstl-start` when needed).
+- **Internal auto-triggered (do NOT call manually)**: `cstl-brainstorm`, `cstl-before-dev`, `cstl-check`, `cstl-break-loop`, `cstl-update-spec`, `cstl-micro-grill`, `cstl-meta`, `cstl-spec-bootstrap`, `cstl-skill-creator`, `smart-search-cli`. These activate on their own when the workflow/skill matcher decides they fit.
 
 ## Web research routing (smart-search first)
 
-For **any external / current / web fact**, run **`python ./.trellis/scripts/run_smart_search.py "<question>" --intent deep-research --json`** first. That script is the **only** Trellis web-research evidence entrypoint (it shells out to the `smart-search` CLI). Do not guess paths under package source trees or sibling repos. Platform built-in web tools (Cursor `WebSearch` / `WebFetch`, or native web tools elsewhere) are **downgrade-only fallbacks**, used solely when smart-search is unavailable (`doctor` not ok, status `not_configured` / `failed`, or search timeout). Do not reach for built-in web search while smart-search is healthy. On Cursor, `smart-search-cli` is an **internal workflow skill name** only (not shipped under `.cursor/skills/`); follow `.trellis/spec/guides/retrieval-daily-guide.md` and `.cursor/rules/retrieval-routing.mdc` for the executable contract.
+For **any external / current / web fact**, run **`python ./.cstl/scripts/run_smart_search.py "<question>" --intent deep-research --json`** first. That script is the **only** Trellis web-research evidence entrypoint (it shells out to the `smart-search` CLI). Do not guess paths under package source trees or sibling repos. Platform built-in web tools (Cursor `WebSearch` / `WebFetch`, or native web tools elsewhere) are **downgrade-only fallbacks**, used solely when smart-search is unavailable (`doctor` not ok, status `not_configured` / `failed`, or search timeout). Do not reach for built-in web search while smart-search is healthy. On Cursor, `smart-search-cli` is an **internal workflow skill name** only (not shipped under `.cursor/skills/`); follow `.cstl/spec/guides/retrieval-daily-guide.md` and `.cursor/rules/retrieval-routing.mdc` for the executable contract.
 
-Managed by Trellis. Edits outside this block are preserved; edits inside may be overwritten by a future `trellis update`.
+Managed by cursor-trellis. Edits outside this block are preserved; edits inside may be overwritten by a future `cstl update`.
 
-<!-- TRELLIS:END -->
+<!-- CSTL:END -->

package/dist/templates/markdown/prompts/run-semantic-slice-12.md.txt

@@ -7,7 +7,7 @@
 For each query in `queries-semantic-slice.jsonl`:
 
 ```powershell
-python .trellis/scripts/route_codebase_retrieval.py "<question>" --json
+python .cstl/scripts/route_codebase_retrieval.py "<question>" --json
 ```
 
 Record `semantic_in_plan` / route list from the envelope.