@blxzer/cursor-trellis 0.2.9 → 0.3.2

package/dist/templates/markdown/spec/guides/durable-learning-decision-guide.md.txt

@@ -1,8 +1,8 @@
-# Durable Learning Decision Guide
+# Durable Learning Decision Guide
 
-> **Purpose**: Decide whether a completed task should update `.trellis/spec/` or can archive with an explicit **no durable learning** line.
+> **Purpose**: Decide whether a completed task should update `.cstl/spec/` or can archive with an explicit **no durable learning** line.
 
-This guide is a **thinking checklist**. It does not replace code-spec files under `.trellis/spec/<layer>/`.
+This guide is a **thinking checklist**. It does not replace code-spec files under `.cstl/spec/<layer>/`.
 
 ---
 
@@ -13,11 +13,11 @@ Pick **one** grep-friendly line before `archive --check`:
 | Outcome | Example line in `verify.md` |
 | --- | --- |
 | No reusable insight | `Durable learning decision: no durable learning` (or any line containing `no durable learning`) |
-| Spec was updated | `Spec update evidence: .trellis/spec/Trellis/framework/index.md` |
-| Insight already documented | `Learning artifact: .trellis/tasks/<task>/handoff.md` |
-| Retrospective captured | `Learning artifact: .trellis/workspace/...` or `retrospective.md: <path>` |
+| Spec was updated | `Spec update evidence: .cstl/spec/Trellis/framework/index.md` |
+| Insight already documented | `Learning artifact: .cstl/tasks/<task>/handoff.md` |
+| Retrospective captured | `Learning artifact: .cstl/workspace/...` or `retrospective.md: <path>` |
 
-Optional planning note (not sufficient alone): `Spec update needed: <reason>` — still record **spec update evidence** after `/trellis:update-spec`.
+Optional planning note (not sufficient alone): `Spec update needed: <reason>` — still record **spec update evidence** after `/cstl:update-spec`.
 
 ---
 
@@ -33,7 +33,7 @@ Optional planning note (not sufficient alone): `Spec update needed: <reason>`
 
 - New or changed CLI/API signature or gate behavior
 - Repeated parent review **changes** on the same class of mistake
-- Workflow bug that should not recur (after `/trellis:break-loop` analysis)
+- Workflow bug that should not recur (after `/cstl:break-loop` analysis)
 - Cross-layer contract clarification
 
 ### Learning artifact
@@ -47,22 +47,22 @@ Optional planning note (not sufficient alone): `Spec update needed: <reason>`
 
 ```bash
 # Draft missing archive sections (append-only)
-python ./.trellis/scripts/task.py prepare-archive-evidence .trellis/tasks/<task>
+python ./.cstl/scripts/task.py prepare-archive-evidence .cstl/tasks/<task>
 
 # Print spec-capture checklist (stdout only; does not edit specs)
-python ./.trellis/scripts/task.py prepare-learning-scaffold .trellis/tasks/<task> --trigger "parent review changes"
+python ./.cstl/scripts/task.py prepare-learning-scaffold .cstl/tasks/<task> --trigger "parent review changes"
 
 # Parent review surfaces missing child learning lines
-python ./.trellis/scripts/task.py review-child <parent> <child> --check
+python ./.cstl/scripts/task.py review-child <parent> <child> --check
 ```
 
 ---
 
 ## Skills
 
-- **`/trellis:update-spec`** — edit code-spec after reviewer confirmation
-- **`/trellis:break-loop`** — deep bug analysis; often leads to spec updates
-- **`/trellis:finish-work`** — archive after learning line is present in `verify.md`
+- **`/cstl:update-spec`** — edit code-spec after reviewer confirmation
+- **`/cstl:break-loop`** — deep bug analysis; often leads to spec updates
+- **`/cstl:finish-work`** — archive after learning line is present in `verify.md`
 
 ---
 

package/dist/templates/markdown/spec/guides/execution-strategy.md.txt

@@ -8,7 +8,7 @@
 
 | Field | Question |
 | --- | --- |
-| `execution_mode` | **Who** implements and checks? (`inline` main session, `worker` trellis-implement/check agents, `child-task` Child worker) |
+| `execution_mode` | **Who** implements and checks? (`inline` main session, `worker` cstl-implement/check agents, `child-task` Child worker) |
 | `isolation` | **Where** are files edited? (`main-worktree` vs `git-worktree` for Child) |
 
 Non-git repo roots do **not** force `inline` for code Full tasks; they only affect whether `git-worktree` / `prepare-child-worktree` is recommended.
@@ -16,8 +16,8 @@ Non-git repo roots do **not** force `inline` for code Full tasks; they only affe
 ## Suggest (planning)
 
 ```bash
-python3 ./.trellis/scripts/task.py suggest-execution-strategy <task-dir>
-python3 ./.trellis/scripts/task.py suggest-execution-strategy <task-dir> --json
+python3 ./.cstl/scripts/task.py suggest-execution-strategy <task-dir>
+python3 ./.cstl/scripts/task.py suggest-execution-strategy <task-dir> --json
 ```
 
 Run during brainstorm / before finalizing the YAML block in `implement.md`. Reconcile suggestion with product intent; the contract in `implement.md` is authoritative after approval.
@@ -32,7 +32,7 @@ Run during brainstorm / before finalizing the YAML block in `implement.md`. Reco
 | Parent / has children | `inline` | `main-worktree` |
 | Child (`task.json` parent set) | `child-task` | `git-worktree` when git package root resolves; else `main-worktree` + WARN |
 
-`touches_code` is deterministic: code `optional_capabilities`, `package`/`scope` path segments (`src`, `packages`, `scripts`, …), or Full with `design.md` and non-doc-only capabilities. Rules live in `.trellis/config/execution-strategy-rules.json`.
+`touches_code` is deterministic: code `optional_capabilities`, `package`/`scope` path segments (`src`, `packages`, `scripts`, …), or Full with `design.md` and non-doc-only capabilities. Rules live in `.cstl/config/execution-strategy-rules.json`.
 
 ## Drift warning (preflight)
 
@@ -40,4 +40,4 @@ Run during brainstorm / before finalizing the YAML block in `implement.md`. Reco
 
 ## Phase 2 alignment
 
-See `workflow.md` Phase 2.1 / 2.2 tables: spawn `trellis-implement` / `trellis-check` only when `execution_mode: worker`.
+See `workflow.md` Phase 2.1 / 2.2 tables: spawn `cstl-implement` / `cstl-check` only when `execution_mode: worker`.

package/dist/templates/markdown/spec/guides/index.md.txt

@@ -1,4 +1,4 @@
-# Thinking Guides
+# Thinking Guides
 
 > **Purpose**: Expand your thinking to catch things you might not have considered.
 
@@ -21,10 +21,11 @@ These guides help you **ask the right questions before coding**.
 
 | Guide | Purpose | When to Use |
 |-------|---------|-------------|
-| [Durable Learning Decision Guide](./durable-learning-decision-guide.md) | Choose no-learning vs spec update vs learning artifact before archive | Finishing a task, parent review, or after `/trellis:break-loop` |
+| [Durable Learning Decision Guide](./durable-learning-decision-guide.md) | Choose no-learning vs spec update vs learning artifact before archive | Finishing a task, parent review, or after `/cstl:break-loop` |
 | [Code Reuse Thinking Guide](./code-reuse-thinking-guide.md) | Identify patterns and reduce duplication | When you notice repeated patterns |
 | [Cross-Layer Thinking Guide](./cross-layer-thinking-guide.md) | Think through data flow across layers | Features spanning multiple layers |
 | [Retrieval daily guide](./retrieval-daily-guide.md) | rg / codegraph / fast-context / smart-search / pack / router | Planning, research, finish verification |
+| [Cursor semantic compliance](./cursor-semantic-compliance.md) | Native planned vs executed semantic (`SemanticSearch`, classify_tool_calls) | Retrieval eval, OC-15 compliance runs, telemetry interpretation |
 | [Cursor subagent policy](./cursor-subagent-policy.md) | Task tool scenes, Agent mode, `model_policy: cursor-configured`, Cursor++ | Parent/Child dispatch, research/implement/check, parallel execution |
 | [Execution strategy](./execution-strategy.md) | `suggest-execution-strategy`, rules JSON, inline vs worker vs child-task | Writing `implement.md` contract, Phase 2 dispatch |
 | [Cursor context injection guide](./cursor-context-injection-guide.md) | Which Cursor channels reach the model (sessionStart bug, .cursor/rules, AGENTS.md) | "Agent ignored instructions" on Cursor, adding always-visible rules |

package/dist/templates/markdown/spec/guides/retrieval-daily-guide.md.txt

@@ -46,13 +46,13 @@ When `projectFileCount > 2000`, the router promotes structural (codegraph) route
 ## Commands
 
 ```powershell
-python ./.trellis/scripts/search_artifacts.py --query "<topic>" --json
-python ./.trellis/scripts/search_memory.py --query "<topic>" --json
-python ./.trellis/scripts/run_smart_search.py "<question>" --intent deep-research --json
-python ./.trellis/scripts/route_codebase_retrieval.py "<question>" --json
-python ./.trellis/scripts/route_codebase_retrieval.py "<question>" --instructions
-python ./.trellis/scripts/get_context.py --mode retrieval-pack --json --input evidence.json
-python ./.trellis/scripts/codegraph_session_smoke.py --json
+python ./.cstl/scripts/search_artifacts.py --query "<topic>" --json
+python ./.cstl/scripts/search_memory.py --query "<topic>" --json
+python ./.cstl/scripts/run_smart_search.py "<question>" --intent deep-research --json
+python ./.cstl/scripts/route_codebase_retrieval.py "<question>" --json
+python ./.cstl/scripts/route_codebase_retrieval.py "<question>" --instructions
+python ./.cstl/scripts/get_context.py --mode retrieval-pack --json --input evidence.json
+python ./.cstl/scripts/codegraph_session_smoke.py --json
 ```
 
 ## Codegraph session readiness (eval / dogfood)
@@ -60,7 +60,7 @@ python ./.trellis/scripts/codegraph_session_smoke.py --json
 Before a **cold benchmark** or structural-heavy run:
 
 1. **MCP**: In Cursor project MCP settings, enable the **codegraph** server for the workspace (or eval checkout).
-2. **Index on disk**: Run `python ./.trellis/scripts/codegraph_session_smoke.py` (exit 0 = at least one `.codegraph/` under workspace root or a top-level subproject). Use `--root <eval-checkout>` when the agent root is not the harness.
+2. **Index on disk**: Run `python ./.cstl/scripts/codegraph_session_smoke.py` (exit 0 = at least one `.codegraph/` under workspace root or a top-level subproject). Use `--root <eval-checkout>` when the agent root is not the harness.
 3. **Live MCP smoke** (manual): one `codegraph_search` with a known symbol in that repo; stale-index banner → re-read affected files.
 
 Paste into the **run report header** (markdown):
@@ -76,7 +76,7 @@ Paste into the **run report header** (markdown):
 
 When `smart-search doctor` is not ok or `run_smart_search.py` status is `not_configured` / `failed` (including **search timeout**), use **Cursor WebSearch/WebFetch**, then persist to `{TASK}/research/` with `source: cursor-web-fallback` in frontmatter. See `smart-search-cli` skill §4b.
 
-**CLI discovery (Cursor):** `TRELLIS_SMART_SEARCH_COMMAND` / `smart_search.command` → PATH `smart-search` → project `node_modules/.bin/smart-search` (when installed as a dependency). Agent entrypoint is always `./.trellis/scripts/run_smart_search.py`.
+**CLI discovery (Cursor):** `TRELLIS_SMART_SEARCH_COMMAND` / `smart_search.command` → PATH `smart-search` → project `node_modules/.bin/smart-search` (when installed as a dependency). Agent entrypoint is always `./.cstl/scripts/run_smart_search.py`.
 
 **Research flags (smart-search ≥ 0.1.15):** pass through `run_smart_search.py` for `--intent deep-research`:
 
@@ -107,7 +107,7 @@ After Grep/codegraph/semantic produce **path candidates**, reorder before choosi
 | `env-config-literal` | Prefer `scripts/`, `e2e/`, `bench/`, `test/` over generic `src/auth` / `src/paths`. |
 
 - **Agent plans**: `render_agent_instructions` / `inject-retrieval-plan.py` append a **结果层排序** block when these intents appear.
-- **Offline reorder**: `python ./.trellis/scripts/rank_retrieval_candidates.py --candidates fixtures.json --intents caller-chain --top-k 5 --pretty`
+- **Offline reorder**: `python ./.cstl/scripts/rank_retrieval_candidates.py --candidates fixtures.json --intents caller-chain --top-k 5 --pretty`
 - **Library**: `common/retrieval_result_ranking.py` (Python mirror used by router and rank script).
 
 Do **not** claim aggregate openclaw score gains from ranking alone without fresh telemetry (`candidate_pool_recall` vs final Top-K).

package/dist/templates/markdown/workspace-index.md

@@ -38,7 +38,7 @@ workspace/
 Run the initialization script:
 
 ```bash
-python3 ./.trellis/scripts/init_developer.py <your-name>
+python3 ./.cstl/scripts/init_developer.py <your-name>
 ```
 
 This will:
@@ -51,12 +51,12 @@ This will:
 
 1. Get your developer name:
    ```bash
-   python3 ./.trellis/scripts/get_developer.py
+   python3 ./.cstl/scripts/get_developer.py
    ```
 
 2. Read your personal index:
    ```bash
-   cat .trellis/workspace/$(python3 ./.trellis/scripts/get_developer.py)/index.md
+   cat .cstl/workspace/$(python3 ./.cstl/scripts/get_developer.py)/index.md
    ```
 
 ---

package/dist/templates/markdown/worktree.yaml.txt

@@ -22,7 +22,7 @@ copy:
   # - .env
   # - .env.local
   # Workflow config
-  - .trellis/.developer
+  - .cstl/.developer
 
 #-------------------------------------------------------------------------------
 # Post-Create Hooks

package/dist/templates/shared-hooks/index.d.ts

@@ -1,7 +1,7 @@
 /**
  * Shared hook templates — platform-independent Python hook scripts.
  *
- * These scripts read only from .trellis/ paths (JSONL, prd.md, spec/) and
+ * These scripts read only from .cstl/ paths (JSONL, prd.md, spec/) and
  * have no platform-specific placeholders. They can be written as-is to any
  * platform's hooks directory.
  */
@@ -16,7 +16,7 @@ export type SharedHookPlatform = "claude" | "cursor" | "codex" | "gemini" | "qod
 /**
  * Which shared hooks each platform actually invokes. Single source of truth
  * for shared-hook distribution — both `writeSharedHooks` (runtime install)
- * and `collectSharedHooks` (`trellis update` diff) read from this table.
+ * and `collectSharedHooks` (`cstl update` diff) read from this table.
  *
  * Routing rules encoded here:
  * - `session-start.py` — shipped by every platform with a SessionStart

package/dist/templates/shared-hooks/index.js

@@ -1,7 +1,7 @@
 /**
  * Shared hook templates — platform-independent Python hook scripts.
  *
- * These scripts read only from .trellis/ paths (JSONL, prd.md, spec/) and
+ * These scripts read only from .cstl/ paths (JSONL, prd.md, spec/) and
  * have no platform-specific placeholders. They can be written as-is to any
  * platform's hooks directory.
  */
@@ -16,7 +16,7 @@ function readTemplate(relativePath) {
 /**
  * Which shared hooks each platform actually invokes. Single source of truth
  * for shared-hook distribution — both `writeSharedHooks` (runtime install)
- * and `collectSharedHooks` (`trellis update` diff) read from this table.
+ * and `collectSharedHooks` (`cstl update` diff) read from this table.
  *
  * Routing rules encoded here:
  * - `session-start.py` — shipped by every platform with a SessionStart

package/dist/templates/shared-hooks/inject-retrieval-plan.py

@@ -4,10 +4,10 @@
 DEGRADED MODE (2026-06-24): beforeSubmitPrompt hook's additional_context does
 not reach the model in current Cursor versions (L1: event often not fired;
 L2: additional_context not delivered). This hook now runs in telemetry-only
-mode: logs routing decisions to .trellis/.runtime/retrieval-plan-events.log
+mode: logs routing decisions to .cstl/.runtime/retrieval-plan-events.log
 for post-session analysis but does NOT inject plan blocks.
 
-See .trellis/tasks/06-24-handle-beforesubmitprompt-unreliability/prd.md for
+See .cstl/tasks/06-24-handle-beforesubmitprompt-unreliability/prd.md for
 probe results and mitigation strategy.
 
 Silent exit 0 (no stdout) when:
@@ -48,7 +48,7 @@ if sys.platform.startswith("win"):
             except Exception:
                 pass
 
-DIR_WORKFLOW = ".trellis"
+DIR_WORKFLOW = ".cstl"
 PLAN_MARKER_ZH = "## 代码库检索计划"
 PLAN_MARKER_EN = "## Codebase retrieval plan"
 TELEMETRY_LOG = ".runtime/retrieval-plan-events.log"

package/dist/templates/shared-hooks/inject-shell-session-context.py

@@ -2,9 +2,9 @@
 """Cursor beforeShellExecution hook: bridge conversation identity to task.py.
 
 Cursor's shell command environment does not inherit SessionStart data. This
-hook writes a short-lived runtime ticket before Cursor runs a shell command
-that calls `task.py select/selected/exit`. The task script then consumes the
-ticket only when it has no native session environment.
+hook writes a short-lived runtime ticket before Cursor runs a shell command
+that calls `task.py select/selected/exit`. The task script then consumes the
+ticket only when it has no native session environment.
 """
 from __future__ import annotations
 
@@ -18,10 +18,10 @@ from pathlib import Path
 from typing import Any
 
 
-DIR_WORKFLOW = ".trellis"
+DIR_WORKFLOW = ".cstl"
 DIR_RUNTIME = ".runtime"
 DIR_CURSOR_SHELL = "cursor-shell"
-SESSION_SUBCOMMANDS = {"select", "selected", "exit"}
+SESSION_SUBCOMMANDS = {"select", "selected", "exit"}
 TICKET_TTL_SECONDS = 30
 CONTEXT_IDENTITY_KEYS = (
     "session_id",
@@ -80,8 +80,8 @@ def _extract_task_subcommands(command: str) -> list[dict[str, str]]:
         if name not in SESSION_SUBCOMMANDS:
             continue
         item = {"name": name}
-        if name == "select" and index + 2 < len(tokens):
-            item["task_ref"] = tokens[index + 2]
+        if name == "select" and index + 2 < len(tokens):
+            item["task_ref"] = tokens[index + 2]
         subcommands.append(item)
     return subcommands
 

package/dist/templates/shared-hooks/inject-subagent-context.py

@@ -26,11 +26,11 @@ if sys.platform.startswith("win"):
     elif hasattr(sys.stdout, "detach"):
         sys.stdout = _io.TextIOWrapper(sys.stdout.detach(), encoding="utf-8", errors="replace")  # type: ignore[union-attr]
 
-DIR_WORKFLOW = ".trellis"
+DIR_WORKFLOW = ".cstl"
 
-AGENT_IMPLEMENT = "trellis-implement"
-AGENT_CHECK = "trellis-check"
-AGENT_RESEARCH = "trellis-research"
+AGENT_IMPLEMENT = "cstl-implement"
+AGENT_CHECK = "cstl-check"
+AGENT_RESEARCH = "cstl-research"
 AGENTS_ALL = (AGENT_IMPLEMENT, AGENT_CHECK, AGENT_RESEARCH)
 AGENTS_REQUIRE_TASK = (AGENT_IMPLEMENT, AGENT_CHECK)
 

package/dist/templates/shared-hooks/inject-workflow-state.py

@@ -1,9 +1,9 @@
 #!/usr/bin/env python3
 """Trellis per-turn breadcrumb hook (UserPromptSubmit / BeforeAgent equivalent).
 
-Runs on every user prompt. Resolves the selected task through Trellis'
-session-aware selected task resolver and emits a short <workflow-state>
-block reminding the main AI what task is selected and its expected flow.
+Runs on every user prompt. Resolves the selected task through Trellis'
+session-aware selected task resolver and emits a short <workflow-state>
+block reminding the main AI what task is selected and its expected flow.
 
 The emitted ``hookEventName`` field is platform-aware: most hosts expect
 ``UserPromptSubmit`` (Claude Code naming, also accepted by Cursor / Qoder /
@@ -23,7 +23,7 @@ hook entry point). Written to each platform's hooks directory via
 writeSharedHooks() at init time.
 
 Silent exit 0 cases (no output):
-  - No .trellis/ directory found (not a Trellis project)
+  - No .cstl/ directory found (not a Trellis project)
   - task.json malformed or missing status
 """
 from __future__ import annotations
@@ -58,11 +58,11 @@ if sys.platform.startswith("win"):
 from typing import Optional
 
 
-# Bootstrap notice for Codex while the session has no selected task. Codex does not
+# Bootstrap notice for Codex while the session has no selected task. Codex does not
 # get the full SessionStart overview; this short reminder points the main session
 # at the start skill once and leaves the per-turn state block compact.
 CODEX_NO_TASK_BOOTSTRAP_NOTICE = """<trellis-bootstrap>
-If you have not already loaded Trellis context this session, read the `trellis-start` skill once.
+If you have not already loaded Trellis context this session, read the `cstl-start` skill once.
 </trellis-bootstrap>"""
 
 
@@ -71,21 +71,21 @@ If you have not already loaded Trellis context this session, read the `trellis-s
 # ---------------------------------------------------------------------------
 
 def find_trellis_root(start: Path) -> Optional[Path]:
-    """Walk up from start to find directory containing .trellis/.
+    """Walk up from start to find directory containing .cstl/.
 
     Handles CWD drift: subdirectory launches, monorepo packages, etc.
-    Returns None if no .trellis/ found (silent no-op).
+    Returns None if no .cstl/ found (silent no-op).
     """
     cur = start.resolve()
     while cur != cur.parent:
-        if (cur / ".trellis").is_dir():
+        if (cur / ".cstl").is_dir():
             return cur
         cur = cur.parent
     return None
 
 
 # ---------------------------------------------------------------------------
-# Selected task discovery
+# Selected task discovery
 # ---------------------------------------------------------------------------
 
 def _detect_platform(input_data: dict) -> str | None:
@@ -124,18 +124,18 @@ def _detect_platform(input_data: dict) -> str | None:
     return None
 
 
-def _resolve_selected_task(root: Path, input_data: dict):
-    scripts_dir = root / ".trellis" / "scripts"
-    if str(scripts_dir) not in sys.path:
-        sys.path.insert(0, str(scripts_dir))
-    from common.active_task import resolve_selected_task  # type: ignore[import-not-found]
-
-    return resolve_selected_task(root, input_data, platform=_detect_platform(input_data))
-
-
-def get_selected_task(root: Path, input_data: dict) -> Optional[tuple[str, str, str]]:
-    """Return (task_id, status, source) from the selected task."""
-    active = _resolve_selected_task(root, input_data)
+def _resolve_selected_task(root: Path, input_data: dict):
+    scripts_dir = root / ".cstl" / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+    from common.active_task import resolve_selected_task  # type: ignore[import-not-found]
+
+    return resolve_selected_task(root, input_data, platform=_detect_platform(input_data))
+
+
+def get_selected_task(root: Path, input_data: dict) -> Optional[tuple[str, str, str]]:
+    """Return (task_id, status, source) from the selected task."""
+    active = _resolve_selected_task(root, input_data)
     if not active.task_path:
         return None
 
@@ -180,7 +180,7 @@ def load_breadcrumbs(root: Path) -> dict[str, str]:
     in build_breadcrumb so users see the broken state and fix
     workflow.md, rather than the hook silently masking the issue.
     """
-    workflow = root / ".trellis" / "workflow.md"
+    workflow = root / ".cstl" / "workflow.md"
     if not workflow.is_file():
         return {}
     try:
@@ -198,12 +198,12 @@ def load_breadcrumbs(root: Path) -> dict[str, str]:
 
 
 def _read_trellis_config(root: Path) -> dict:
-    """Load .trellis/config.yaml via the bundled trellis_config helper.
+    """Load .cstl/config.yaml via the bundled trellis_config helper.
 
-    The helper lives in .trellis/scripts/common; the hook lives outside the
+    The helper lives in .cstl/scripts/common; the hook lives outside the
     scripts tree, so we extend sys.path before importing.
     """
-    scripts_dir = root / ".trellis" / "scripts"
+    scripts_dir = root / ".cstl" / "scripts"
     if str(scripts_dir) not in sys.path:
         sys.path.insert(0, str(scripts_dir))
     try:
@@ -219,7 +219,7 @@ def _read_trellis_config(root: Path) -> dict:
 def _codex_mode_banner(config: dict) -> str:
     """Emit a `<codex-mode>` banner for the additionalContext payload.
 
-    Reads `codex.dispatch_mode` from .trellis/config.yaml; defaults to
+    Reads `codex.dispatch_mode` from .cstl/config.yaml; defaults to
     `inline` when missing or invalid because Codex sub-agents run with
     `fork_turns="none"` isolation and can't inherit the parent session's
     task context. The banner makes the active mode explicit to Codex AI
@@ -254,7 +254,7 @@ def resolve_breadcrumb_key(
 
     Codex defaults to ``inline`` because sub-agents run with ``fork_turns="none"``
     isolation and can't inherit the parent session's task context. Users can
-    opt into ``codex.dispatch_mode: sub-agent`` in ``.trellis/config.yaml``
+    opt into ``codex.dispatch_mode: sub-agent`` in ``.cstl/config.yaml``
     to use the parallel ``<status>-inline`` tag → ``<status>`` flip. Invalid
     or missing values fall back to inline.
 
@@ -292,11 +292,11 @@ def build_breadcrumb(
         body = templates.get(status)
     if body is None:
         body = "Refer to workflow.md for current step."
-    header = (
-        f"Selected task: none\nStatus: {status}"
-        if task_id is None
-        else f"Selected task: {task_id} ({status})"
-    )
+    header = (
+        f"Selected task: none\nStatus: {status}"
+        if task_id is None
+        else f"Selected task: {task_id} ({status})"
+    )
     return f"<workflow-state>\n{header}\n{body}\n</workflow-state>"
 
 
@@ -323,15 +323,15 @@ def main() -> int:
     templates = load_breadcrumbs(root)
     platform = _detect_platform(data)
     config = _read_trellis_config(root)
-    task = get_selected_task(root, data)
+    task = get_selected_task(root, data)
     if task is None:
-        # No selected task — still emit the framework-entry breadcrumb.
-        no_task_key = resolve_breadcrumb_key("no_task", platform, config)
+        # No selected task — still emit the framework-entry breadcrumb.
+        no_task_key = resolve_breadcrumb_key("no_task", platform, config)
         breadcrumb = build_breadcrumb(
             None, "no_task", templates, breadcrumb_key=no_task_key
         )
     else:
-        task_id, status, source = task
+        task_id, status, source = task
         status_key = resolve_breadcrumb_key(status, platform, config)
         source_for_breadcrumb = None if platform == "codex" else source
         breadcrumb = build_breadcrumb(

package/dist/templates/shared-hooks/research-end-retrieval-pack.py

@@ -31,9 +31,9 @@ if sys.platform.startswith("win"):
             sys.stdout.detach(), encoding="utf-8", errors="replace"
         )
 
-DIR_WORKFLOW = ".trellis"
+DIR_WORKFLOW = ".cstl"
 OUTPUT_BASENAME = "retrieval-pack-latest.json"
-MARKER = "<!-- trellis-research-end-pack -->"
+MARKER = "<!-- cstl-research-end-pack -->"
 
 
 def _repo_root(cwd: str) -> Path | None:

package/dist/templates/shared-hooks/session-start.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python3
+#!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 """
 Session Start Hook - Inject structured context
@@ -308,7 +308,7 @@ def _normalize_task_ref(task_ref: str) -> str:
         normalized = normalized[2:]
 
     if normalized.startswith("tasks/"):
-        return f".trellis/{normalized}"
+        return f".cstl/{normalized}"
 
     return normalized
 
@@ -318,7 +318,7 @@ def _resolve_task_dir(trellis_dir: Path, task_ref: str) -> Path:
     path_obj = Path(normalized)
     if path_obj.is_absolute():
         return path_obj
-    if normalized.startswith(".trellis/"):
+    if normalized.startswith(".cstl/"):
         return trellis_dir.parent / path_obj
     return trellis_dir / "tasks" / path_obj
 
@@ -341,7 +341,7 @@ def _get_task_status(trellis_dir: Path, input_data: dict) -> str:
         return (
             f"Trellis framework: active\nSelected task: {task_ref}\n"
             "Status: STALE SELECTION\n"
-            f"Next-Action: Run `{_PYTHON_CMD} ./.trellis/scripts/task.py exit` to clear the stale selection, "
+            f"Next-Action: Run `{_PYTHON_CMD} ./.cstl/scripts/task.py exit` to clear the stale selection, "
             "then ask the user what to work on next."
         )
 
@@ -365,7 +365,7 @@ def _get_task_status(trellis_dir: Path, input_data: dict) -> str:
         return (
             f"Status: COMPLETED\nTask: {task_title}\n"
             f"Present: {present_line}\n"
-            "Next-Action: Run `/trellis:finish-work`. If the working tree is dirty, return to Phase 3.4 first."
+            "Next-Action: Run `/cstl:finish-work`. If the working tree is dirty, return to Phase 3.4 first."
         )
 
     has_prd = (task_dir / "prd.md").is_file()
@@ -382,7 +382,7 @@ def _get_task_status(trellis_dir: Path, input_data: dict) -> str:
         return (
             f"Status: PLANNING\nTask: {task_title}\n"
             f"Present: {present_line}\n"
-            "Next-Action: Load `trellis-brainstorm` and write `prd.md`. Stay in planning."
+            "Next-Action: Load `cstl-brainstorm` and write `prd.md`. Stay in planning."
         )
 
     if task_status == "planning":
@@ -570,7 +570,7 @@ def _collect_spec_index_paths(trellis_dir: Path, allowed_pkgs: set | None) -> li
     paths: list[str] = []
     guides_index = trellis_dir / "spec" / "guides" / "index.md"
     if guides_index.is_file():
-        paths.append(".trellis/spec/guides/index.md")
+        paths.append(".cstl/spec/guides/index.md")
 
     spec_dir = trellis_dir / "spec"
     if not spec_dir.is_dir():
@@ -582,7 +582,7 @@ def _collect_spec_index_paths(trellis_dir: Path, allowed_pkgs: set | None) -> li
 
         index_file = sub / "index.md"
         if index_file.is_file():
-            paths.append(f".trellis/spec/{sub.name}/index.md")
+            paths.append(f".cstl/spec/{sub.name}/index.md")
             continue
 
         if allowed_pkgs is not None and sub.name not in allowed_pkgs:
@@ -592,7 +592,7 @@ def _collect_spec_index_paths(trellis_dir: Path, allowed_pkgs: set | None) -> li
                 continue
             nested_index = nested / "index.md"
             if nested_index.is_file():
-                paths.append(f".trellis/spec/{sub.name}/{nested.name}/index.md")
+                paths.append(f".cstl/spec/{sub.name}/{nested.name}/index.md")
 
     return paths
 
@@ -641,7 +641,7 @@ def _build_compact_current_state(
         try:
             task_count = sum(1 for _ in iter_active_tasks(get_tasks_dir(repo_root)))
             lines.append(
-                f"Active tasks: {task_count} total. Use the Task Dashboard for routing; use `{_PYTHON_CMD} ./.trellis/scripts/task.py list --mine` only for raw inspection."
+                f"Active tasks: {task_count} total. Use the Task Dashboard for routing; use `{_PYTHON_CMD} ./.cstl/scripts/task.py list --mine` only for raw inspection."
             )
         except Exception:
             pass
@@ -672,7 +672,7 @@ def _build_task_dashboard(trellis_dir: Path, input_data: dict) -> str:
             _detect_platform(input_data),
         )
     except Exception:
-        return f"Task Dashboard unavailable. Run: {_PYTHON_CMD} ./.trellis/scripts/task.py dashboard"
+        return f"Task Dashboard unavailable. Run: {_PYTHON_CMD} ./.cstl/scripts/task.py dashboard"
 
 
 def _extract_range(content: str, start_header: str, end_header: str) -> str:
@@ -739,7 +739,7 @@ def _build_workflow_overview(workflow_path: Path) -> str:
 
     out_lines = [
         "# Development Workflow - Session Summary",
-        f"Full guide: .trellis/workflow.md. Step detail: `{_PYTHON_CMD} ./.trellis/scripts/get_context.py --mode phase --step <X.Y>`.",
+        f"Full guide: .cstl/workflow.md. Step detail: `{_PYTHON_CMD} ./.cstl/scripts/get_context.py --mode phase --step <X.Y>`.",
         "",
     ]
 
@@ -781,7 +781,7 @@ def main():
     if project_dir is None:
         project_dir = Path(_normalize_windows_shell_path(hook_input.get("cwd", "."))).resolve()
 
-    trellis_dir = project_dir / ".trellis"
+    trellis_dir = project_dir / ".cstl"
     context_key = _resolve_context_key(trellis_dir, hook_input)
     _persist_context_key_for_bash(context_key)
 
@@ -836,17 +836,17 @@ Trellis compact SessionStart context. Use it to orient the session; load details
 
     output.write(
         "Discover more via: "
-        f"`{_PYTHON_CMD} ./.trellis/scripts/get_context.py --mode packages`\n"
+        f"`{_PYTHON_CMD} ./.cstl/scripts/get_context.py --mode packages`\n"
     )
     if _detect_platform(hook_input) == "cursor":
         output.write(
             "\n**External web research (Cursor):** run "
-            f"`{_PYTHON_CMD} ./.trellis/scripts/run_smart_search.py \"<question>\" "
+            f"`{_PYTHON_CMD} ./.cstl/scripts/run_smart_search.py \"<question>\" "
             "--intent deep-research --json` first (Trellis evidence wrapper → "
             "`smart-search` CLI). CLI discovery: `TRELLIS_SMART_SEARCH_COMMAND` / "
             "`smart_search.command`, then PATH `smart-search`, then project "
             "`node_modules/.bin/smart-search`, then optional repo-local layouts "
-            "(see `.trellis/spec/guides/retrieval-daily-guide.md`). "
+            "(see `.cstl/spec/guides/retrieval-daily-guide.md`). "
             "`smart-search-cli` is an internal workflow skill name — not a file under `.cursor/skills/` on Cursor. "
             "If `run_smart_search.py` status is `not_configured` or `failed` (incl. timeout), "
             "use **WebSearch/WebFetch**, persist `{TASK}/research/*.md` with "

package/dist/templates/trellis/config/execution-strategy-rules.json

@@ -20,7 +20,7 @@
     {
       "execution_mode": "worker",
       "isolation": "git-worktree",
-      "message": "worker usually runs in main-worktree; git-worktree is rare for trellis-implement"
+      "message": "worker usually runs in main-worktree; git-worktree is rare for cstl-implement"
     },
     {
       "execution_mode": "inline",