opencodekit 0.21.9 → 0.21.10

package/dist/index.js

@@ -20,7 +20,7 @@ var __require = /* @__PURE__ */ createRequire(import.meta.url);
 
 //#endregion
 //#region package.json
-var version = "0.21.9";
+var version = "0.21.10";
 
 //#endregion
 //#region src/utils/license.ts

package/dist/template/.opencode/AGENTS.md

@@ -451,7 +451,7 @@ When user intent is clear, load the appropriate skills:
 
 ## Edit Protocol
 
-`str_replace` failures are the #1 source of LLM coding failures. Use the `edit` tool (str_replace) and `patch` tool as the **primary** editing method. Use `tilth_tilth_edit` (hash-anchored edits) only as a **fallback** when str_replace fails. For all edits, follow the structured edit flow:
+`str_replace` failures are the #1 source of LLM coding failures. Use the `edit` tool (str_replace) and `patch` tool as the **primary** editing method. For all edits, follow the structured edit flow:
 
 1. **LOCATE** — Use LSP tools (goToDefinition, findReferences) to find exact positions
 2. **READ** — Get fresh file content around target (offset: line-10, limit: 30)
@@ -483,18 +483,6 @@ Files over ~500 lines become hard to maintain and review. Extract helpers, split
 
 **Use the `structured-edit` skill for complex edits.**
 
-### Hash-Anchored Edits (MCP)
-
-When tilth MCP is available with `--edit` mode, use hash-anchored edits as a **fallback** when str_replace fails:
-
-1. **READ** via `tilth_read` — output includes `line:hash|content` format per line
-2. **EDIT** via `tilth_edit` — reference lines by their `line:hash` anchor
-3. **REJECT** — if file changed since last read, hashes won't match; re-read and retry
-
-**Benefits**: Eliminates `str_replace` failures entirely. If the file changed between read and edit, the operation fails safely (no silent corruption).
-
-**Fallback**: Without tilth, use the standard LOCATE→READ→VERIFY→EDIT→CONFIRM flow above.
-
 ---
 
 ## Output Style

package/dist/template/.opencode/agent/build.md

@@ -90,7 +90,7 @@ When entering a new task or codebase area:
 - Parallelize discovery: search symbols + grep patterns + read key files simultaneously
 - **Early stop** — once you can name the exact files and symbols to modify, stop exploring
 - Trace only the symbols you'll actually modify; avoid transitive expansion into unrelated code
-- Prefer `tilth --map --scope <dir>` for structural overview, then drill into specific files
+- Prefer `srcwalk map --scope <dir>` for structural overview, then drill into specific files
 
 ### Quality Bar
 

package/dist/template/.opencode/agent/explore.md

@@ -50,14 +50,14 @@ Find relevant files, symbols, and usage paths quickly for the caller.
 
 ## Tools — Use These for Local Code Search
 
-**Prefer tilth CLI** (`npx -y tilth`) for symbol search and file reading — it combines grep + tree-sitter + cat into one call. See `code-search-patterns` skill for full syntax.
+**Prefer srcwalk CLI** (`srcwalk`) for symbol search and file reading — it combines grep + tree-sitter + cat into one call. See `code-search-patterns` skill for full syntax.
 
 | Tool                   | Use For                                         | Example                                                                    |
 | ---------------------- | ----------------------------------------------- | -------------------------------------------------------------------------- |
-| `tilth` (symbol)       | AST-aware symbol search (definitions + usages)  | `npx -y tilth handleAuth --scope src/`                                     |
-| `tilth` (read)         | Smart file reading with outline for large files | `npx -y tilth src/auth.ts --section 44-89`                                 |
-| `tilth` (glob)         | Find files by pattern with token estimates      | `npx -y tilth "*.test.ts" --scope src/`                                    |
-| `tilth` (map)          | Codebase structural overview                    | `npx -y tilth --map --scope src/`                                          |
+| `srcwalk` (symbol)     | AST-aware symbol search (definitions + usages)  | `srcwalk find handleAuth --scope src/`                                     |
+| `srcwalk` (read)       | Smart file reading with outline for large files | `srcwalk src/auth.ts --section 44-89`                                      |
+| `srcwalk` (files)      | Find files by pattern with token estimates      | `srcwalk files "*.test.ts" --scope src/`                                   |
+| `srcwalk` (map)        | Codebase structural overview                    | `srcwalk map --scope src/`                                                 |
 | `grep`                 | Find text/regex patterns in files               | `grep(pattern: "PatchEntry", include: "*.ts")`                             |
 | `glob`                 | Find files by name/pattern                      | `glob(pattern: "src/**/*.ts")`                                             |
 | `lsp` (goToDefinition) | Jump to symbol definition                       | `lsp(operation: "goToDefinition", filePath: "...", line: N, character: N)` |
@@ -66,24 +66,24 @@ Find relevant files, symbols, and usage paths quickly for the caller.
 | `read`                 | Read file content                               | `read(filePath: "src/utils/patch.ts")`                                     |
 
 **NEVER** use `websearch`, `webfetch`, or `codesearch` — those search the internet, not your project.
-**NEVER** modify files or run destructive commands — bash is for tilth CLI and read-only operations only.
+**NEVER** modify files or run destructive commands — bash is for srcwalk CLI and read-only operations only.
 
 ## Rules
 
 - Never modify files — read-only is a hard constraint
-- Bash is enabled **only** for tilth CLI (`npx -y tilth`) — do not use bash for anything else
+- Bash is enabled **only** for srcwalk CLI (`srcwalk`) — do not use bash for anything else
 - Return absolute paths in final output
 - Cite `file:line` evidence whenever possible
-- **Prefer tilth** for symbol search, then fall back to `grep` or `glob`
+- **Prefer srcwalk** for symbol search, then fall back to `grep` or `glob`
 - Use LSP for precise navigation after finding candidate locations
 - Stop when you can answer with concrete evidence
 
 ## Navigation Patterns
 
-1. **tilth first, grep second**: `npx -y tilth <symbol> --scope src/` finds definitions AND usages in one call; fall back to `grep` if tilth is unavailable
+1. **srcwalk first, grep second**: `srcwalk find <symbol> --scope src/` finds definitions AND usages in one call; fall back to `grep` if srcwalk is unavailable
 2. **Don't re-read**: If you already read a file, reference what you learned — don't read it again
-3. **Follow the chain**: definition → usages → callers via tilth symbol search or LSP findReferences
-4. **Target ≤3 tool calls per symbol**: tilth search → read section → done
+3. **Follow the chain**: definition → usages → callers via srcwalk symbol search or LSP findReferences
+4. **Target ≤3 tool calls per symbol**: srcwalk find → read section → done
 
 ## Retrieval Budget
 
@@ -94,10 +94,10 @@ Find relevant files, symbols, and usage paths quickly for the caller.
 
 ## Workflow
 
-1. `npx -y tilth <symbol> --scope src/` or `grep`/`glob` to discover symbols and files
-2. `npx -y tilth <file> --section <range>` or `read` for targeted file sections
+1. `srcwalk find <symbol> --scope src/` or `grep`/`glob` to discover symbols and files
+2. `srcwalk <file> --section <range>` or `read` for targeted file sections
 3. `lsp` goToDefinition/findReferences for precise cross-file navigation when needed
-4. `npx -y tilth --map --scope <dir>` for structural overview of unfamiliar areas
+4. `srcwalk map --scope <dir>` for structural overview of unfamiliar areas
 5. Return findings with file:line evidence
 
 ## Output
@@ -108,7 +108,7 @@ Find relevant files, symbols, and usage paths quickly for the caller.
 
 ## Failure Handling
 
-- If tilth is unavailable, fall back to `grep` + `glob` + targeted `read`
+- If srcwalk is unavailable, fall back to `grep` + `glob` + targeted `read`
 - If LSP is unavailable, fall back to `grep` + targeted `read`
 - If results are ambiguous, list assumptions and best candidate paths
 - Never guess — mark uncertainty explicitly

package/dist/template/.opencode/agent/general.md

@@ -161,13 +161,13 @@ Before claiming task done:
 
 ## Workflow
 
-1. Read relevant files (prefer `npx -y tilth <symbol> --scope src/` for fast symbol lookup)
+1. Read relevant files (prefer `srcwalk find <symbol> --scope src/` for fast symbol lookup)
 2. Confirm scope is small and clear
 3. Make surgical edits
 4. Run validation (lint/typecheck/tests as applicable)
 5. Report changed files with `file:line` references
 
-**Code navigation:** Use tilth CLI for AST-aware search when available — see `code-search-patterns` skill for syntax. Prefer `npx -y tilth <symbol> --scope <dir>` over grep for symbol definitions.
+**Code navigation:** Use srcwalk for AST-aware search — see `code-search-patterns` skill for syntax. Prefer `srcwalk find <symbol> --scope <dir>` over grep for symbol definitions.
 
 ## Progress Updates
 

package/dist/template/.opencode/agent/plan.md

@@ -389,13 +389,13 @@ When planning under constraint:
 
 ## Workflow
 
-1. **Ground**: Read bead artifacts (`prd.md`, `plan.md` if present); use `npx -y tilth --map --scope src/` for codebase overview only when needed
+1. **Ground**: Read bead artifacts (`prd.md`, `plan.md` if present); use `srcwalk map --scope src/` for codebase overview only when needed
 2. **Calibrate**: Understand goal, constraints, and success criteria
-3. **Transform**: Launch parallel research (`task` subagents) when uncertainty remains; use `npx -y tilth <symbol> --scope src/` for fast codebase discovery; decompose into phases/tasks with explicit dependencies
+3. **Transform**: Launch parallel research (`task` subagents) when uncertainty remains; use `srcwalk find <symbol> --scope src/` for fast codebase discovery; decompose into phases/tasks with explicit dependencies
 4. **Release**: Write actionable plan with exact file paths, commands, verification, failure behavior, privacy/security notes, and open questions
 5. **Reset**: End with a concrete next command (`/ship <id>`, `/start <child-id>`, etc.)
 
-**Code navigation:** Use tilth CLI for AST-aware search and `--map` for structural overview — see `code-search-patterns` skill.
+**Code navigation:** Use srcwalk for AST-aware search and `map` for structural overview — see `code-search-patterns` skill.
 
 ## Output
 

package/dist/template/.opencode/agent/review.md

@@ -183,12 +183,12 @@ return <div>No messages</div>  // State exists but not used
 
 ## Workflow
 
-1. Read changed files and nearby context (prefer `npx -y tilth <symbol> --scope src/` for fast cross-file tracing)
+1. Read changed files and nearby context (prefer `srcwalk find <symbol> --scope src/` for fast cross-file tracing)
 2. Identify and validate findings by severity (P0, P1, P2, P3)
 3. For each finding: explain why, when it happens, and impact
 4. If no qualifying findings exist, say so explicitly
 
-**Code navigation:** Use tilth CLI for AST-aware symbol search when tracing cross-file dependencies — see `code-search-patterns` skill. Prefer `npx -y tilth <symbol> --scope <dir>` over grep for understanding call chains.
+**Code navigation:** Use srcwalk for AST-aware symbol search when tracing cross-file dependencies — see `code-search-patterns` skill. Prefer `srcwalk find <symbol> --scope <dir>` over grep for understanding call chains.
 
 ## Output
 

package/dist/template/.opencode/agent/scout.md

@@ -1,5 +1,5 @@
 ---
-description: External research specialist for library docs and patterns
+description: External research specialist for library docs, dependency source, and patterns
 mode: subagent
 temperature: 0.2
 steps: 30
@@ -32,40 +32,46 @@ You are OpenCode, the best coding agent on the planet.
 
 # Scout Agent
 
-**Purpose**: Knowledge seeker — you find the signal in the noise of external information.
+**Purpose**: Knowledge seeker — you find the signal in the noise of external information. You inspect dependency source, compare local code against upstream, and return evidence-backed findings.
 
 > _"Good research doesn't dump facts; it creates actionable clarity."_
 
 ## Identity
 
-You are a read-only research agent. You output concise recommendations backed by verifiable sources only.
+You are a read-only research agent. You output concise recommendations backed by verifiable sources only. Do not modify the user's workspace.
 
 ## Task
 
-Find trustworthy external references quickly and return concise, cited guidance.
+Find trustworthy external references quickly and return concise, cited guidance — starting with the direct answer, then the evidence.
 
 ## Success Criteria
 
+- **Lead with the answer** — state the finding first, then the evidence
 - Answer the research question with the smallest set of authoritative sources that supports the recommendation
 - Lock factual claims to retrieved sources; do not rely on model memory for current facts, APIs, specs, or release status
 - Separate verified facts from assumptions, estimates, and lower-confidence context
 - State source conflicts explicitly and prefer higher-ranked sources
 - Stop when more searching is unlikely to change the recommendation
+- If a repository or resource is inaccessible, say so explicitly and continue with whatever evidence is still available
 
 ## Rules
 
 - Never modify project files
 - Never invent URLs; only use verified links
-- Cite every non-trivial claim
+- Cite every non-trivial claim with exact file paths and line references when available
 - Prefer high-signal synthesis over long dumps
 - **Never refer to tools by name** — say "I'm going to search for..." not "I'll use the websearch tool"
+- When reading a cloned repo, note that findings reflect the default clone state unless the caller specifies a branch/commit
 
 ## When to Use Scout
 
+- Inspecting dependency repositories or library source code
+- Comparing local code against upstream implementations
 - Finding library docs, API references, or framework patterns
 - Comparing alternatives or evaluating package options
 - Researching external integrations before implementation
 - Getting latest ecosystem info, release notes, or migration guides
+- Explaining how a library or framework works by reading its source
 
 ## When NOT to Use Scout
 
@@ -107,10 +113,19 @@ If lower-ranked sources conflict with higher-ranked sources, follow higher-ranke
 1. Check memory first:
 
    ```typescript
-   memory-search({ query: "<topic keywords>", limit: 3 });
+   memory - search({ query: "<topic keywords>", limit: 3 });
    ```
 
-2. If memory is insufficient, choose tools by need:
+2. If memory is insufficient, choose the primary approach by task type:
+
+   **Task involves a GitHub repo or dependency source code:**
+   - Use `grepsearch` or `codesearch` for targeted code search across public repos (no clone needed)
+   - Use `webclaw` scrape on `raw.githubusercontent.com` URLs to read specific files directly
+   - For deep inspection: `git clone <url> /tmp/<name>` via bash, then use glob/grep/read on the cloned path
+   - Use official docs only as a supplement when source alone is insufficient
+   - If multiple repos are relevant, inspect each before drawing conclusions
+
+   **Task involves docs, APIs, or ecosystem research:**
    | Need | Tool |
    |------|------|
    | docs/API | `context7`, `codesearch` |
@@ -124,19 +139,23 @@ If lower-ranked sources conflict with higher-ranked sources, follow higher-ranke
    **Web content priority:** Always try `webclaw` tools first for URL extraction. They handle 403s, bot protection, and produce 67% fewer tokens than raw HTML. Fall back to `webfetch` only if webclaw is unavailable.
 
 3. Run independent calls in parallel
-4. Return concise recommendations with sources
+4. Return findings: direct answer first, then evidence organized by repo/source
 
 ## Examples
 
-| Good                                                                 | Bad                                        |
-| -------------------------------------------------------------------- | ------------------------------------------ |
-| "Use pattern X; cited docs + 2 production examples with permalinks." | "Best practice is Y" with no source links. |
+| Good                                                                             | Bad                                        |
+| -------------------------------------------------------------------------------- | ------------------------------------------ |
+| "The function is at `lib/auth.ts:42`. It validates JWT via RS256." + source link | "Best practice is Y" with no source links. |
+| "Use pattern X; cited docs + 2 production examples with permalinks."             | Dumping raw file contents without analysis |
+| "Repo was inaccessible; continuing with official docs found at [url]..."         | Blocking on inaccessible resource silently |
 
 ## Output
 
-- Summary (2-5 bullets)
-- Recommended approach
-- Sources
-- Risks/tradeoffs
+**Structure every response in this order:**
+
+1. **Direct answer** — the finding or recommendation, upfront
+2. **Evidence** — organized by repo or source, with file:line references
+3. **Sources** — verified URLs or paths
+4. **Risks/tradeoffs** — if relevant
 
 **IMPORTANT:** Only your final message is returned to the main agent. Make it comprehensive and self-contained — include all key findings, not just a summary of what you explored.

package/dist/template/.opencode/command/design.md

@@ -32,10 +32,10 @@ skill({ name: "ux-quality-gates" }); // IA, forms, recovery, loading, usability
 
 ## Phase 1: Detect Existing Design System
 
-```typescript
-tilth_tilth_files({ pattern: "**/tailwind.config.{js,ts,mjs}" });
-tilth_tilth_files({ pattern: "**/globals.css" });
-tilth_tilth_files({ pattern: "**/components.json" }); // shadcn
+```bash
+srcwalk files "**/tailwind.config.{js,ts,mjs}"
+srcwalk files "**/globals.css"
+srcwalk files "**/components.json"  # shadcn
 ```
 
 Read what exists. Don't design in a vacuum — build on the project's current system.

package/dist/template/.opencode/command/init-context.md

@@ -44,11 +44,11 @@ const args = {
 
 ### 1.1 Check Existing Context
 
-Use tilth or Read to check for existing files:
+Use srcwalk or Read to check for existing files:
 
-```typescript
-tilth_tilth_files({ pattern: "*.md", scope: ".opencode/memory/project" });
-// Or: Read({ filePath: ".opencode/memory/project/project.md", limit: 20 });
+```bash
+srcwalk files "*.md" --scope .opencode/memory/project
+# Or: Read({ filePath: ".opencode/memory/project/project.md", limit: 20 });
 ```
 
 **If planning context exists:**
@@ -202,9 +202,9 @@ If `--brownfield` analysis was run:
 
 ### 4.1 Verify Documents Created
 
-```typescript
-tilth_tilth_files({ pattern: "*.md", scope: ".opencode/memory/project" });
-// Verify each file exists and has content
+```bash
+srcwalk files "*.md" --scope .opencode/memory/project
+# Verify each file exists and has content
 Read({ filePath: ".opencode/memory/project/project.md", limit: 5 });
 Read({ filePath: ".opencode/memory/project/roadmap.md", limit: 5 });
 Read({ filePath: ".opencode/memory/project/state.md", limit: 5 });

package/dist/template/.opencode/command/review-codebase.md

@@ -38,7 +38,7 @@ skill({ name: "verification-gates" });
 | `explore`            | Finding patterns in codebase, prior art |
 | `scout`              | External research, best practices       |
 | `lsp`                | Finding symbol definitions, references  |
-| `tilth_tilth_search` | Finding code patterns                   |
+| `srcwalk find`       | Finding code patterns                   |
 | `codesearch`         | Real-world usage examples               |
 
 ## Phase 1: Gather Context

package/dist/template/.opencode/command/ship.md

@@ -48,7 +48,7 @@ skill({ name: "reflection-checkpoints" }); // Mid-point + completion checks duri
 | `explore`            | Finding patterns in codebase, prior art   |
 | `scout`              | External research, best practices         |
 | `lsp`                | Finding symbol definitions, references    |
-| `tilth_tilth_search` | Finding code patterns                     |
+| `srcwalk find`       | Finding code patterns                     |
 | `task`               | Spawning subagents for parallel execution |
 
 ## Phase 1: Guards

package/dist/template/.opencode/dcp.jsonc

@@ -1,18 +1,22 @@
 {
 	"$schema": "https://raw.githubusercontent.com/Opencode-DCP/opencode-dynamic-context-pruning/master/dcp.schema.json",
 	"enabled": true,
+	// Disable auto-update for config stability — update explicitly when pinning new versions
+	// (v3.1.10+: auto-update is supported; set true if you want rolling bug fixes)
+	"autoUpdate": false,
 	"debug": false,
 	// "off" | "minimal" | "detailed" — keep minimal for low-noise dev flow
 	"pruneNotification": "minimal",
 	// "chat" (in-conversation) or "toast" (system notification)
 	"pruneNotificationType": "toast",
-	// Slash commands: /dcp context, /dcp stats, /dcp sweep, /dcp compress, /dcp decompress, /dcp recompress
+	// Slash commands: /dcp context, /dcp stats, /dcp sweep, /dcp compress,
+	//                 /dcp decompress, /dcp recompress, /dcp manual
 	"commands": {
 		"enabled": true,
 		// Additional tools to protect from /dcp sweep (supports glob wildcards)
 		"protectedTools": ["observation", "memory-*"]
 	},
-	// Manual mode: disables autonomous context management
+	// Manual mode: when enabled, tools only run via /dcp commands — no autonomous pruning
 	"manualMode": {
 		"enabled": false,
 		"automaticStrategies": true
@@ -22,17 +26,14 @@
 		"enabled": false,
 		"turns": 4
 	},
-	// Glob patterns for files that should never be auto-pruned
-	// Keep tight: broad patterns reduce DCP effectiveness
-	// .opencode/** and .beads/** removed — memory-* and tilth_* outputs
-	// already survive compression via compress.protectedTools
+	// Glob patterns matched against tool parameters.filePath — keep tight
+	// Broad patterns reduce DCP effectiveness
 	"protectedFilePatterns": [
 		"**/.env*",
 		"**/AGENTS.md",
 		"**/package.json",
 		"**/tsconfig.json"
 	],
-	// Unified context compression tool (v3.1.0)
 	"compress": {
 		// "range" (stable) compresses spans into block summaries
 		// "message" (experimental) compresses individual raw messages
@@ -40,45 +41,14 @@
 		// "allow" (no prompt) | "ask" (prompt) | "deny" (tool not registered)
 		"permission": "allow",
 		"showCompression": false,
-		// v3.1.0: active summary tokens extend effective maxContextLimit
+		// v3.1.0+: active summary tokens extend effective maxContextLimit
 		"summaryBuffer": true,
+		// v3.1.10+: percentage strings now use the model input budget directly —
+		// safe for GitHub Copilot and all other providers (no modelContextLimit required)
 		// Soft upper threshold: above this, strong compression nudges fire
-		// Use numeric values — percentage requires modelContextLimit from runtime
-		// which may be unavailable for some provider/model combos (e.g. GitHub Copilot)
-		// Rule: must be BELOW OpenCode emergency threshold (model_max - reserved - max_output)
-		// For Copilot Claude (216k ctx, 64k out, 16k reserved): emergency = 136k
-		// So DCP must start compressing well before 136k
-		"maxContextLimit": 100000,
-		// Per-model override for maxContextLimit (takes priority over global)
-		"modelMaxLimits": {
-			// Claude: 216k ctx, 64k out → emergency at 136k → DCP starts at 110k
-			"github-copilot/claude-opus-4.6": 110000,
-			"github-copilot/claude-opus-4.5": 110000,
-			"github-copilot/claude-sonnet-4.6": 110000,
-			"github-copilot/claude-sonnet-4.5": 110000,
-			"github-copilot/claude-sonnet-4": 110000,
-			// Haiku: smaller model, be more conservative
-			"github-copilot/claude-haiku-4.5": 90000,
-			// GPT/Gemini: assume similar 200k+ windows
-			"github-copilot/gpt-5.4": 110000,
-			"github-copilot/gpt-5.3-codex": 110000,
-			"github-copilot/gemini-3.1-pro-preview": 110000
-		},
+		"maxContextLimit": "75%",
 		// Soft lower threshold: below this, turn/iteration reminders are off
-		// Use numeric values — same reason as maxContextLimit above
-		"minContextLimit": 50000,
-		// Per-model override for minContextLimit (takes priority over global)
-		"modelMinLimits": {
-			"github-copilot/claude-opus-4.6": 65000,
-			"github-copilot/claude-opus-4.5": 65000,
-			"github-copilot/claude-sonnet-4.6": 65000,
-			"github-copilot/claude-sonnet-4.5": 65000,
-			"github-copilot/claude-sonnet-4": 65000,
-			"github-copilot/claude-haiku-4.5": 50000,
-			"github-copilot/gpt-5.4": 65000,
-			"github-copilot/gpt-5.3-codex": 65000,
-			"github-copilot/gemini-3.1-pro-preview": 65000
-		},
+		"minContextLimit": "30%",
 		// How often context-limit nudge fires above maxContextLimit (1 = every fetch)
 		"nudgeFrequency": 5,
 		// Messages since last user message before adding compression reminders
@@ -87,11 +57,13 @@
 		"nudgeForce": "soft",
 		// Keep user messages compressible to avoid permanent context growth
 		"protectUserMessages": false,
-		// Auto-protected by DCP: task, skill, todowrite, todoread, compress, batch, plan_enter, plan_exit, write, edit
+		// v3.1.11+: preserve text wrapped in <protect>...</protect> during compression
+		"protectTags": false,
+		// Auto-protected by DCP: task, skill, todowrite, todoread, compress, batch,
+		//                        plan_enter, plan_exit, write, edit
 		// Only list ADDITIONAL tools whose outputs should be appended to compression summaries
-		"protectedTools": ["observation", "memory-*", "tilth_*"]
+		"protectedTools": ["observation", "memory-*"]
 	},
-	// Experimental features
 	"experimental": {
 		// Allow DCP processing in subagent sessions (default: false)
 		"allowSubAgents": false,

package/dist/template/.opencode/memory/project/user.md

@@ -30,8 +30,7 @@ updated: 2025-01-06
 ## Editing Tool Preferences
 
 - **Primary**: `edit` tool (str_replace) and `patch` tool
-- **Secondary/Fallback**: `tilth_tilth_edit` (hash-anchored edits) — only when str_replace fails
-- **Reading/Search**: `tilth_tilth_read` and `tilth_tilth_search` are fine to use freely
+- **Reading/Search**: `srcwalk` CLI via bash — `srcwalk find <symbol>`, `srcwalk <file>`, `srcwalk map`
 
 ## Rules to Always Follow
 

package/dist/template/.opencode/opencode.json

@@ -1,9 +1,10 @@
 {
   "$schema": "https://opencode.ai/config.json",
+  "lsp": true,
   "agent": {
     "build": {
       "description": "Primary development agent with full codebase access",
-      "model": "github-copilot/gpt-5.5"
+      "model": "github-copilot/gpt-5.4"
     },
     "compaction": {
       "description": "Session summarizer for context continuity across compactions"
@@ -39,8 +40,8 @@
   },
   "autoupdate": false,
   "compaction": {
-    "auto": false,
-    "reserved": 16000
+    "auto": true,
+    "reserved": 2048
   },
   "formatter": {
     "biome": {
@@ -61,25 +62,6 @@
     "laravel-pint": {
       "command": ["npx", "laravel-pint", "--preset", "psr12", "$FILE"],
       "extensions": [".php"]
-    },
-    "oxfmt": {
-      "command": ["npx", "oxfmt", "--write", "$FILE"],
-      "extensions": [
-        ".js",
-        ".jsx",
-        ".ts",
-        ".tsx",
-        ".json",
-        ".jsonc",
-        ".html",
-        ".css",
-        ".scss",
-        ".sass",
-        ".md",
-        ".mdx",
-        ".yaml",
-        ".yml"
-      ]
     }
   },
   "instructions": [
@@ -90,6 +72,9 @@
   ],
   "keybinds": {
     "leader": "ctrl+x",
+    "session_child_first": "<leader>down",
+    "session_child_cycle": "right",
+    "session_child_cycle_reverse": "left",
     "session_parent": "up"
   },
   "mcp": {
@@ -99,15 +84,6 @@
       "timeout": 120000,
       "type": "local"
     },
-    "tilth": {
-      "command": ["npx", "-y", "tilth", "--mcp", "--edit"],
-      "enabled": true,
-      "environment": {
-        "TILTH_THREADS": "8"
-      },
-      "timeout": 120000,
-      "type": "local"
-    },
     "webclaw": {
       "command": ["webclaw-mcp"],
       "enabled": true,
@@ -115,7 +91,7 @@
       "type": "local"
     }
   },
-  "model": "github-copilot/gpt-5.5",
+  "model": "github-copilot/gpt-5.4",
   "permission": {
     "bash": {
       "*": "allow",
@@ -197,11 +173,11 @@
             }
           }
         },
-        "claude-opus-4.5": {
+        "claude-opus-4.7": {
           "attachment": true,
           "limit": {
             "context": 216000,
-            "output": 32000
+            "output": 64000
           },
           "options": {
             "reasoningEffort": "medium"
@@ -210,16 +186,6 @@
           "temperature": true,
           "tool_call": true,
           "variants": {
-            "high": {
-              "options": {
-                "reasoningEffort": "high"
-              }
-            },
-            "low": {
-              "options": {
-                "reasoningEffort": "low"
-              }
-            },
             "medium": {
               "options": {
                 "reasoningEffort": "medium"
@@ -257,36 +223,6 @@
             }
           }
         },
-        "claude-sonnet-4.5": {
-          "attachment": true,
-          "limit": {
-            "context": 216000,
-            "output": 32000
-          },
-          "options": {
-            "reasoningEffort": "medium"
-          },
-          "reasoning": true,
-          "temperature": true,
-          "tool_call": true,
-          "variants": {
-            "high": {
-              "options": {
-                "reasoningEffort": "high"
-              }
-            },
-            "low": {
-              "options": {
-                "reasoningEffort": "low"
-              }
-            },
-            "medium": {
-              "options": {
-                "reasoningEffort": "medium"
-              }
-            }
-          }
-        },
         "claude-sonnet-4.6": {
           "attachment": true,
           "limit": {
@@ -317,16 +253,6 @@
             }
           }
         },
-        "gemini-2.5-pro": {
-          "attachment": true,
-          "limit": {
-            "context": 173000,
-            "output": 64000
-          },
-          "reasoning": true,
-          "temperature": true,
-          "tool_call": true
-        },
         "gemini-3-flash-preview": {
           "attachment": true,
           "limit": {
@@ -357,82 +283,6 @@
           "temperature": true,
           "tool_call": true
         },
-        "gpt-5.2": {
-          "attachment": true,
-          "limit": {
-            "context": 192000,
-            "output": 128000
-          },
-          "options": {
-            "reasoningEffort": "medium",
-            "reasoningSummary": "auto",
-            "textVerbosity": "medium"
-          },
-          "reasoning": true,
-          "temperature": true,
-          "tool_call": true,
-          "variants": {
-            "xhigh": {
-              "include": ["reasoning.encrypted_content"],
-              "reasoningEffort": "xhigh",
-              "reasoningSummary": "auto"
-            },
-            "high": {
-              "include": ["reasoning.encrypted_content"],
-              "reasoningEffort": "high",
-              "reasoningSummary": "auto"
-            },
-            "low": {
-              "reasoningEffort": "low",
-              "reasoningSummary": "auto"
-            },
-            "medium": {
-              "reasoningEffort": "medium",
-              "reasoningSummary": "auto"
-            }
-          }
-        },
-        "gpt-5.2-codex": {
-          "attachment": true,
-          "limit": {
-            "context": 400000,
-            "input": 400000,
-            "output": 128000
-          },
-          "options": {
-            "reasoningEffort": "medium",
-            "reasoningSummary": "auto",
-            "textVerbosity": "medium"
-          },
-          "reasoning": true,
-          "temperature": true,
-          "tool_call": true,
-          "variants": {
-            "fast": {
-              "disabled": true
-            },
-            "xhigh": {
-              "include": ["reasoning.encrypted_content"],
-              "reasoningEffort": "xhigh",
-              "reasoningSummary": "auto"
-            },
-            "high": {
-              "include": ["reasoning.encrypted_content"],
-              "reasoningEffort": "high",
-              "reasoningSummary": "auto",
-              "textVerbosity": "medium"
-            },
-            "low": {
-              "reasoningEffort": "low",
-              "reasoningSummary": "auto"
-            },
-            "medium": {
-              "reasoningEffort": "medium",
-              "reasoningSummary": "auto",
-              "textVerbosity": "medium"
-            }
-          }
-        },
         "gpt-5.3-codex": {
           "attachment": true,
           "limit": {
@@ -595,120 +445,12 @@
               "reasoningSummary": "auto"
             }
           }
-        },
-        "grok-code-fast": {
-          "attachment": true,
-          "limit": {
-            "context": 173000,
-            "output": 64000
-          },
-          "reasoning": true,
-          "temperature": true,
-          "tool_call": true
-        },
-        "grok-code-fast-1": {
-          "attachment": true,
-          "limit": {
-            "context": 173000,
-            "output": 64000
-          },
-          "reasoning": true,
-          "temperature": true,
-          "tool_call": true
-        },
-        "minimax-m2.5": {
-          "attachment": true,
-          "limit": {
-            "context": 204800,
-            "output": 16384
-          },
-          "options": {
-            "temperature": 1,
-            "top_k": 40,
-            "top_p": 0.95
-          },
-          "reasoning": true,
-          "temperature": true,
-          "tool_call": true
         }
       },
       "options": {
         "timeout": 600000
       }
     },
-    "kimi-for-coding": {
-      "models": {
-        "k2p5": {
-          "limit": {
-            "context": 262144,
-            "output": 32768
-          },
-          "options": {
-            "interleaved": {
-              "field": "reasoning_content"
-            },
-            "thinking": {
-              "budgetTokens": 8192,
-              "reasoning_effort": "high",
-              "type": "enabled"
-            }
-          },
-          "reasoning": true,
-          "temperature": true,
-          "tool_call": true,
-          "variants": {
-            "high": {
-              "interleaved": {
-                "field": "reasoning_content"
-              },
-              "options": {
-                "reasoning_effort": "high",
-                "thinkingBudget": 16384,
-                "type": "enabled"
-              }
-            },
-            "max": {
-              "interleaved": {
-                "field": "reasoning_content"
-              },
-              "options": {
-                "reasoning_effort": "high",
-                "thinkingBudget": 32768,
-                "type": "enabled"
-              }
-            }
-          }
-        }
-      }
-    },
-    "modal": {
-      "models": {
-        "zai-org/GLM-5-FP8": {
-          "modalities": {
-            "input": ["text", "image", "pdf"],
-            "output": ["text"]
-          },
-          "name": "GLM-5",
-          "options": {
-            "maxOutputTokens": 131072,
-            "reasoningEffort": "high",
-            "reasoningSummary": "true",
-            "temperature": 1,
-            "thinking": {
-              "type": "enabled"
-            },
-            "top_k": 40,
-            "top_p": 0.95
-          },
-          "reasoning": true
-        }
-      },
-      "name": "Modal",
-      "options": {
-        "apiKey": "{env:MODAL_API_KEY}",
-        "baseURL": "https://api.us-west-2.modal.direct/v1"
-      }
-    },
     "openai": {
       "models": {
         "gpt-5.2": {
@@ -816,19 +558,6 @@
         }
       }
     },
-    "opencode": {
-      "models": {
-        "big-pickle": {
-          "options": {
-            "reasoningEffort": "high",
-            "temperature": 1,
-            "top_k": 40,
-            "top_p": 0.95
-          },
-          "reasoning": true
-        }
-      }
-    },
     "proxypal": {
       "models": {
         "claude-opus-4.6": {
@@ -1080,57 +809,6 @@
         "baseURL": "http://127.0.0.1:8317/v1",
         "includeUsage": true
       }
-    },
-    "zai-coding-plan": {
-      "models": {
-        "glm-4.6": {
-          "limit": {
-            "context": 128000,
-            "output": 16384
-          },
-          "options": {
-            "temperature": 1,
-            "thinking": {
-              "type": "enabled"
-            }
-          },
-          "reasoning": true,
-          "temperature": true,
-          "tool_call": true
-        },
-        "glm-4.7": {
-          "id": "glm-4.7",
-          "interleaved": true,
-          "limit": {
-            "context": 200000,
-            "output": 128000
-          },
-          "name": "GLM-4.7",
-          "options": {
-            "temperature": 1,
-            "thinking": {
-              "type": "enabled"
-            }
-          },
-          "reasoning": true
-        },
-        "glm-5": {
-          "name": "GLM-5",
-          "options": {
-            "maxOutputTokens": 131072,
-            "reasoningEffort": "high",
-            "reasoningSummary": "true",
-            "temperature": 1,
-            "thinking": {
-              "type": "enabled"
-            },
-            "top_k": 40,
-            "top_p": 0.95
-          },
-          "reasoning": true
-        }
-      },
-      "name": "Z.AI Coding Plan"
     }
   },
   "share": "manual",

package/dist/template/.opencode/skill/agent-evals/SKILL.md

@@ -124,7 +124,7 @@ A single run can be lucky. For a skill you're seriously evaluating:
 | Anti-pattern avoidance | `grep` for the banned pattern → expect 0                          |
 | Required output shape  | JSON schema validation, presence of required sections             |
 | Code correctness       | run the code, run its tests, check exit code                      |
-| Behavior change        | call site count via `tilth_search`, file existence, line counts   |
+| Behavior change        | call site count via `srcwalk callers`, file existence, line counts |
 | UI / visual            | Playwright screenshot + pixel diff against expected, or DOM query |
 | Refusal / safety       | grep for forbidden phrases or correct refusal pattern             |
 

package/dist/template/.opencode/skill/code-search-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: code-search-patterns
-description: Use when navigating unfamiliar code with search-first patterns, combining built-in/LSP navigation with tilth MCP (main agent) and tilth CLI (subagents)
+description: Use when navigating unfamiliar code with search-first patterns, combining built-in/LSP navigation with srcwalk CLI
 version: 1.0.0
 tags: [workflow, code-quality, context, subagent]
 dependencies: []
@@ -8,10 +8,10 @@ dependencies: []
 
 # Code Search Patterns
 
-Unified navigation skill for fast, low-waste code understanding across both execution modes:
+Unified navigation skill for fast, low-waste code understanding:
 
-- **Main agent**: built-in tools + LSP + tilth MCP
-- **Subagents**: Bash + `npx -y tilth` CLI
+- **Main agent**: built-in tools + LSP + srcwalk CLI
+- **Subagents**: Bash + `srcwalk` CLI
 
 This skill merges practical navigation heuristics with concrete tool usage so you can locate behavior, trace impact, and edit safely with fewer calls.
 
@@ -42,7 +42,7 @@ Start with symbol/content search to find exact locations, then read only the nee
 - **Good**: `search -> targeted read`
 - **Avoid**: `read many files -> search later`
 
-Use LSP (`findReferences`, `outgoingCalls`) or tilth search first; read deep only after narrowing scope.
+Use LSP (`findReferences`, `outgoingCalls`) or srcwalk search first; read deep only after narrowing scope.
 
 ### 2) Multi-Symbol Search
 
@@ -65,7 +65,7 @@ Re-read only when you need:
 Before renaming/removing/changing signatures, inspect downstream impact first.
 
 - LSP: `findReferences`, `incomingCalls`
-- tilth: `tilth_tilth_deps` or `--deps`
+- srcwalk: `srcwalk impact <symbol>` or `srcwalk callers <symbol>`
 
 Then apply edits from dependents inward.
 
@@ -74,7 +74,7 @@ Then apply edits from dependents inward.
 Prefer nearby package/module scope first.
 
 - built-in search: constrain `path`
-- tilth: pass `scope` / `context`
+- srcwalk: pass `--scope <dir>` to restrict the scan area
 
 Locality reduces irrelevant matches and token churn.
 
@@ -83,7 +83,7 @@ Locality reduces irrelevant matches and token churn.
 For large files, inspect structure first (symbols/outline), then read only target sections.
 
 - LSP: `documentSymbol`
-- tilth read: smart outline by default, then section drill-in
+- srcwalk read: smart outline by default, then section drill-in
 
 ### 7) Follow Call Chain, Not File Tree
 
@@ -91,34 +91,18 @@ Start at entry behavior and walk calls (`definition -> outgoing -> next definiti
 
 This exposes real execution flow with fewer reads.
 
-## tilth MCP (Main Agent)
+## srcwalk CLI
 
-Use MCP variants when available in the main agent session:
-
-- `tilth_tilth_search`
-- `tilth_tilth_read`
-- `tilth_tilth_files`
-- `tilth_tilth_deps`
-
-### Built-in/LSP vs tilth MCP (when to choose which)
-
-| Need                    | Built-in / LSP                         | Prefer tilth MCP when                                       | Why tilth helps                     |
-| ----------------------- | -------------------------------------- | ----------------------------------------------------------- | ----------------------------------- |
-| Find symbols/usages     | `grep` / `lsp.findReferences`          | You want definitions + usages + expanded source in one call | Reduces search+read round trips     |
-| Read file content       | `read`                                 | File is large or you only need structure first              | Smart outline + section targeting   |
-| List candidate files    | `glob`                                 | You want quick glob results with token-aware relevance      | Faster triage for large directories |
-| Pre-change impact check | `lsp.incomingCalls` + manual follow-up | You need import + dependent view before breaking change     | Single blast-radius view via deps   |
-
-Guideline: if tilth MCP is active, use it as default for navigation; fall back to built-in/LSP when you need language-server-specific semantics or exact editor-position operations.
-
-## tilth CLI (Subagents)
-
-### Why this exists
-
-Subagents typically cannot call MCP tools directly. They can still use tilth through Bash:
+`srcwalk` is available to all agents (main agent and subagents) via Bash. It combines grep + tree-sitter AST into one CLI tool.
 
 ```bash
-npx -y tilth <query> [flags]
+srcwalk guide          # Print agent routing policy (run once per session)
+srcwalk find <symbol>  # Symbol search (definitions + usages)
+srcwalk <file>         # Smart file read (outline for large files)
+srcwalk map            # Codebase structural overview
+srcwalk files '<glob>' # Find files by pattern
+srcwalk callers <sym>  # Reverse call graph
+srcwalk impact <sym>   # Blast-radius heuristic
 ```
 
 ### Auto-detection
@@ -127,103 +111,90 @@ npx -y tilth <query> [flags]
 | --------------------------------- | ------------------------------------ |
 | Existing file path (`src/foo.ts`) | Read file (smart outline/full)       |
 | Identifier (`initCommand`)        | Symbol search (definitions + usages) |
-| Glob (`*.test.ts`)                | List files                           |
-| Plain text / phrase               | Content search                       |
-
-Use `--kind` to force a specific mode when needed.
+| `find <symbol>`                   | Explicit symbol search               |
+| `files <glob>`                    | File discovery                       |
 
 ### Core operations
 
 #### 1) Read file
 
 ```bash
-npx -y tilth src/index.ts
-npx -y tilth src/index.ts --full
-npx -y tilth src/index.ts --section 45-89
+srcwalk src/index.ts
+srcwalk src/index.ts --full
+srcwalk src/index.ts --section 45-89
 ```
 
 #### 2) Search symbols
 
 ```bash
-npx -y tilth initCommand --scope src/
-npx -y tilth "initCommand,detectMode" --scope src/
+srcwalk find initCommand --scope src/
+srcwalk find "initCommand,detectMode" --scope src/
 ```
 
 #### 3) Search text/regex
 
 ```bash
-npx -y tilth --kind content "TODO" --scope src/
-npx -y tilth --kind regex "/TODO.*fix/" --scope src/
+srcwalk find "TODO" --scope src/
+srcwalk find "/TODO.*fix/" --scope src/
 ```
 
 #### 4) Find callers
 
 ```bash
-npx -y tilth --kind callers initCommand --scope src/
+srcwalk callers initCommand --scope src/
 ```
 
 #### 5) List files
 
 ```bash
-npx -y tilth "*.test.ts" --scope src/
+srcwalk files "*.test.ts" --scope src/
 ```
 
-#### 6) Blast radius / deps
+#### 6) Blast radius
 
 ```bash
-npx -y tilth --deps src/commands/init.ts --scope src/
+srcwalk impact initCommand --scope src/
+srcwalk callers initCommand --scope src/
 ```
 
 #### 7) Codebase map
 
 ```bash
-npx -y tilth --map --scope src/
+srcwalk map --scope src/
 ```
 
 ### Useful flags
 
-| Flag              | Purpose                        | Example                      |
-| ----------------- | ------------------------------ | ---------------------------- | ------------------- | ----------------- | ---------------- |
-| `--scope <dir>`   | Restrict scan area             | `--scope src/commands/`      |
-| `--section <range | heading>`                      | Targeted file slice          | `--section 120-180` |
-| `--full`          | Force full file output         | `--full`                     |
-| `--budget <n>`    | Limit output size              | `--budget 2000`              |
-| `--json`          | Machine-readable output        | `--json`                     |
-| `--map`           | Structural project skeleton    | `--map --scope src/`         |
-| `--kind <symbol   | content                        | regex                        | callers>`           | Force search mode | `--kind callers` |
-| `--deps <file>`   | Import/dependent blast radius  | `--deps src/utils/errors.ts` |
-| `--expand <n>`    | Expand top matches with source | `--expand 3`                 |
-
-### MCP vs CLI
-
-| Capability                   | MCP (main agent)                                   | CLI (subagents)                            |
-| ---------------------------- | -------------------------------------------------- | ------------------------------------------ |
-| Access mode                  | Tool call                                          | Bash command                               |
-| Session dedup/context carry  | Yes                                                | No                                         |
-| Hash-anchored edit flow      | Yes (via MCP edit tools)                           | No                                         |
-| Symbol/content/regex/callers | Yes                                                | Yes                                        |
-| Deps/blast-radius            | Yes                                                | Yes                                        |
-| Codebase map                 | Limited by toolset                                 | Yes (`--map`)                              |
-| Best for                     | Interactive main-agent navigation + edit workflows | Subagent discovery/exploration without MCP |
+| Flag                    | Purpose                                       | Example                             |
+| ----------------------- | --------------------------------------------- | ----------------------------------- |
+| `--scope <dir>`         | Restrict scan area                            | `--scope src/commands/`             |
+| `--section <range\|sym>` | Targeted file slice (line range or symbol)   | `--section 120-180`, `--section fn` |
+| `--full`                | Force full file output (no outline)           | `--full`                            |
+| `--budget <n>`          | Limit output token size                       | `--budget 2000`                     |
+| `--json`                | Machine-readable output                       | `--json`                            |
+| `--filter <qualifiers>` | Filter find results by field:value            | `--filter kind:fn`                  |
+| `--glob <pattern>`      | File pattern filter within find               | `--glob "*.ts"`                     |
+| `--expand[=<n>]`        | Inline source for top N matches               | `--expand 3`                        |
+| `--depth <n>`           | Depth for callers/callees traversal           | `--depth 2`                         |
 
 ### Example subagent dispatch
 
 ```ts
 task({
   subagent_type: "general",
-  prompt: `Use tilth CLI via Bash for navigation.
+  prompt: `Use srcwalk via Bash for navigation.
 
 1) Locate symbol and usages:
-npx -y tilth initCommand --scope src/
+srcwalk find initCommand --scope src/
 
 2) Find callers:
-npx -y tilth --kind callers initCommand --scope src/
+srcwalk callers initCommand --scope src/
 
 3) Check blast radius before edits:
-npx -y tilth --deps src/commands/init.ts --scope src/
+srcwalk impact initCommand --scope src/
 
 4) Read only the relevant section:
-npx -y tilth src/commands/init.ts --section 500-620
+srcwalk src/commands/init.ts --section 500-620
 
 Then implement the requested change with minimal file edits.`,
 });
@@ -249,5 +220,5 @@ Target heuristic: understand a symbol and its direct impact in **≤3 calls** wh
 | Serially tracing one function at a time          | Multi-symbol search + callers/deps                                  |
 | Ignoring blast radius before API/signature edits | Run references/incoming/deps first                                  |
 | Unscoped repository-wide search                  | Use `path`/`--scope` to localize                                    |
-| Using CLI defaults when mode is ambiguous        | Force with `--kind`                                                 |
+| Using CLI defaults when mode is ambiguous        | Use explicit subcommand (`find`, `files`, `callers`) or `--filter kind:<label>` |
 | Overusing `--full` on large files                | Outline first, then `--section`                                     |

package/dist/template/.opencode/skill/context-initialization/SKILL.md

@@ -21,9 +21,9 @@ dependencies: []
 
 ### 1. Verify Templates
 
-```typescript
-tilth_tilth_files({ pattern: "*.md", scope: ".opencode/memory/_templates" });
-// Required templates: project.md, roadmap.md, state.md
+```bash
+srcwalk files "*.md" --scope .opencode/memory/_templates
+# Required templates: project.md, roadmap.md, state.md
 ```
 
 Stop if missing.
@@ -62,8 +62,8 @@ Skip if `--skip-questions` flag set.
 
 ### 4. Verify
 
-```typescript
-tilth_tilth_files({ pattern: "*.md", scope: ".opencode/memory/project" });
+```bash
+srcwalk files "*.md" --scope .opencode/memory/project
 ```
 
 Report created files with their injection status (auto-injected vs on-demand).

package/dist/template/.opencode/skill/rtk-command-compression/SKILL.md

@@ -22,7 +22,7 @@ Core rule: **opt in explicitly, verify rewrites, preserve raw evidence when corr
 
 ## When NOT to Use
 
-- Code inspection or editing: prefer `tilth_tilth_read`, `tilth_tilth_search`, LSP, Read, Grep, and Edit.
+- Code inspection or editing: prefer `srcwalk find`/`srcwalk <path>`, LSP, Read, Grep, and Edit.
 - Full verification evidence is required and compressed summaries would hide diagnostics.
 - The user has not approved installing binaries, changing global OpenCode config, or adding plugins.
 

package/dist/template/.opencode/tool/context7.ts

@@ -28,7 +28,7 @@ WHEN: Looking up library APIs, checking function signatures, finding usage examp
 SKIP: Searching your own codebase (use grep/LSP), general web research (use websearch).
 
 Common mistakes:
-- DON'T search for internal project code (use grep/tilth instead)
+- DON'T search for internal project code (use grep/srcwalk instead)
 - DON'T guess library versions — always resolve first, then query
 - DON'T use for general web research (use websearch instead)
 

package/dist/template/.opencode/tool/grepsearch.ts

@@ -18,7 +18,7 @@ export default tool({
 	description: `Search real-world code examples from GitHub repositories via grep.app. Replaces asking "how do others use X?" — use this for finding production patterns and real-world API usage.
 
 WHEN: Implementing unfamiliar APIs, looking for production patterns, understanding library integrations.
-SKIP: Searching your own codebase (use grep/tilth), looking up docs (use context7), general research (use websearch).
+SKIP: Searching your own codebase (use grep/srcwalk), looking up docs (use context7), general research (use websearch).
 
 Common mistakes:
 - DON'T search for keywords like "react tutorial" — search for literal code: "useState("

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "opencodekit",
-	"version": "0.21.9",
+	"version": "0.21.10",
 	"description": "CLI tool for bootstrapping and managing OpenCodeKit projects",
 	"keywords": [
 		"agents",