opencodekit 0.20.4 → 0.20.6

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

@@ -175,23 +175,25 @@
 						"output": 32000
 					},
 					"options": {
-						"thinking_budget": 24000,
-						"type": "enabled"
+						"reasoningEffort": "high"
 					},
 					"reasoning": true,
 					"temperature": true,
 					"tool_call": true,
 					"variants": {
-						"high": {
+						"low": {
 							"options": {
-								"thinking_budget": 16000,
-								"type": "enabled"
+								"reasoningEffort": "low"
 							}
 						},
-						"max": {
+						"medium": {
 							"options": {
-								"thinking_budget": 32000,
-								"type": "enabled"
+								"reasoningEffort": "medium"
+							}
+						},
+						"high": {
+							"options": {
+								"reasoningEffort": "high"
 							}
 						}
 					}
@@ -203,20 +205,25 @@
 						"output": 32000
 					},
 					"options": {
-						"thinking_budget": 10000
+						"reasoningEffort": "medium"
 					},
 					"reasoning": true,
 					"temperature": true,
 					"tool_call": true,
 					"variants": {
-						"high": {
+						"low": {
 							"options": {
-								"thinking_budget": 16000
+								"reasoningEffort": "low"
 							}
 						},
-						"max": {
+						"medium": {
 							"options": {
-								"thinking_budget": 32000
+								"reasoningEffort": "medium"
+							}
+						},
+						"high": {
+							"options": {
+								"reasoningEffort": "high"
 							}
 						}
 					}
@@ -228,40 +235,25 @@
 						"output": 64000
 					},
 					"options": {
-						"thinking": {
-							"budget_tokens": 24000,
-							"type": "enabled"
-						}
+						"reasoningEffort": "high"
 					},
 					"reasoning": true,
 					"temperature": true,
 					"tool_call": true,
 					"variants": {
-						"adaptive": {
+						"low": {
 							"options": {
-								"max_tokens": 16000,
-								"output_config": {
-									"effort": "max"
-								},
-								"thinking": {
-									"type": "adaptive"
-								}
+								"reasoningEffort": "low"
 							}
 						},
-						"high": {
+						"medium": {
 							"options": {
-								"thinking": {
-									"budget_tokens": 24000,
-									"type": "enabled"
-								}
+								"reasoningEffort": "medium"
 							}
 						},
-						"max": {
+						"high": {
 							"options": {
-								"thinking": {
-									"budget_tokens": 32000,
-									"type": "enabled"
-								}
+								"reasoningEffort": "high"
 							}
 						}
 					}
@@ -273,20 +265,25 @@
 						"output": 16000
 					},
 					"options": {
-						"thinking_budget": 10000
+						"reasoningEffort": "medium"
 					},
 					"reasoning": true,
 					"temperature": true,
 					"tool_call": true,
 					"variants": {
-						"high": {
+						"low": {
 							"options": {
-								"thinking_budget": 16000
+								"reasoningEffort": "low"
 							}
 						},
-						"max": {
+						"medium": {
+							"options": {
+								"reasoningEffort": "medium"
+							}
+						},
+						"high": {
 							"options": {
-								"thinking_budget": 32000
+								"reasoningEffort": "high"
 							}
 						}
 					}
@@ -298,20 +295,25 @@
 						"output": 32000
 					},
 					"options": {
-						"thinking_budget": 10000
+						"reasoningEffort": "medium"
 					},
 					"reasoning": true,
 					"temperature": true,
 					"tool_call": true,
 					"variants": {
-						"high": {
+						"low": {
 							"options": {
-								"thinking_budget": 16000
+								"reasoningEffort": "low"
 							}
 						},
-						"max": {
+						"medium": {
 							"options": {
-								"thinking_budget": 32000
+								"reasoningEffort": "medium"
+							}
+						},
+						"high": {
+							"options": {
+								"reasoningEffort": "high"
 							}
 						}
 					}
@@ -323,40 +325,25 @@
 						"output": 32000
 					},
 					"options": {
-						"thinking": {
-							"budget_tokens": 24000,
-							"type": "enabled"
-						}
+						"reasoningEffort": "high"
 					},
 					"reasoning": true,
 					"temperature": true,
 					"tool_call": true,
 					"variants": {
-						"adaptive": {
+						"low": {
 							"options": {
-								"max_tokens": 16000,
-								"output_config": {
-									"effort": "max"
-								},
-								"thinking": {
-									"type": "adaptive"
-								}
+								"reasoningEffort": "low"
 							}
 						},
-						"high": {
+						"medium": {
 							"options": {
-								"thinking": {
-									"budget_tokens": 16000,
-									"type": "enabled"
-								}
+								"reasoningEffort": "medium"
 							}
 						},
-						"max": {
+						"high": {
 							"options": {
-								"thinking": {
-									"budget_tokens": 32000,
-									"type": "enabled"
-								}
+								"reasoningEffort": "high"
 							}
 						}
 					}

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

@@ -12,7 +12,7 @@
   },
   "dependencies": {
     "@google/stitch-sdk": "^0.0.3",
-    "@opencode-ai/plugin": "1.3.17"
+    "@opencode-ai/plugin": "1.4.0"
   },
   "devDependencies": {
     "@types/node": "^25.3.0",

package/dist/template/.opencode/skill/memory-grounding/SKILL.md

@@ -0,0 +1,68 @@
+---
+name: memory-grounding
+description: >
+  Use at the start of any command that needs prior context — searches memory for decisions, patterns, and handoffs before execution to avoid re-solving solved problems.
+version: 1.0.0
+tags: [memory, grounding, pre-flight]
+---
+
+# Memory Grounding
+
+Search institutional memory before executing any command that modifies state or makes decisions.
+
+## When to Use
+
+- At the start of `/ship`, `/plan`, `/create`, `/pr`, `/research`, `/resume`
+- Before any command that benefits from prior context
+- When you need to check if work was already done or decisions already made
+
+## When NOT to Use
+
+- Read-only commands that don't need historical context (e.g., `/status`)
+- Commands that explicitly skip grounding (e.g., `--no-memory` flag)
+
+## Protocol
+
+### Step 1: Search for relevant context
+
+```typescript
+// Primary: search by bead ID or topic
+memory-search({ query: "$ARGUMENTS" });
+
+// Secondary: search by keywords with limit
+memory-search({ query: "<feature or topic keywords>", limit: 5 });
+
+// Optional: filter by type for specific needs
+memory-search({ query: "<keywords>", type: "decision" });  // Past decisions
+memory-search({ query: "<keywords>", type: "bugfix" });    // Known issues
+```
+
+### Step 2: Check last session handoff
+
+```typescript
+memory-read({ file: "handoffs/last" });
+```
+
+### Step 3: Check session history (if resuming work)
+
+```typescript
+find_sessions({ query: "$ARGUMENTS", limit: 3 });
+```
+
+### Step 4: Apply findings
+
+- **If relevant findings exist:** Incorporate them directly. Don't re-solve solved problems.
+- **If prior decisions found:** Follow them unless there's a clear reason to diverge (document the divergence).
+- **If known issues found:** Account for them in the current approach.
+- **If nothing found:** Proceed normally — absence of memory is not a blocker.
+
+## Command-Specific Variations
+
+| Command     | Extra Focus                                            |
+| ----------- | ------------------------------------------------------ |
+| `/plan`     | Search bugfixes; check for existing plans to overwrite |
+| `/ship`     | Search for failed approaches to avoid repeating        |
+| `/create`   | Search for duplicate beads before creating             |
+| `/pr`       | Include findings in PR description                     |
+| `/research` | Search before spawning agents; narrow scope to gaps    |
+| `/resume`   | Read handoff file by bead ID; check session history    |

package/dist/template/.opencode/skill/reconcile/SKILL.md

@@ -0,0 +1,183 @@
+---
+name: reconcile
+description: >
+  Use when verifying implementation matches its specification — detects drift between PRD requirements
+  and actual code, identifies missing features, extra features, and diverged behavior. Load after /ship
+  or before closing a bead.
+version: 1.0.0
+tags: [workflow, verification, quality]
+dependencies: [verification-before-completion]
+---
+
+# Reconcile — Spec↔Code Drift Detection
+
+## When to Use
+
+- After `/ship` completes all tasks, before closing the bead
+- When you suspect implementation has drifted from the original spec
+- During `/review-codebase` to check spec adherence
+- Before creating a PR to verify completeness
+
+## When NOT to Use
+
+- During active implementation (wait until tasks are done)
+- For code quality issues (use `requesting-code-review` instead)
+- For structural config audits (use `/health` instead)
+
+## Overview
+
+Implementation drift is the silent killer of spec-driven development. Tasks can pass all verification gates while the overall feature drifts from its specification. This skill systematically compares PRD artifacts against code evidence.
+
+## Reconciliation Process
+
+### Step 1: Load Artifacts
+
+```bash
+# Read the PRD
+cat .beads/artifacts/$BEAD_ID/prd.md
+
+# Read the plan (if exists)
+cat .beads/artifacts/$BEAD_ID/plan.md 2>/dev/null
+
+# Determine comparison base (works with main, master, or any default branch)
+BASE=$(git rev-parse origin/main 2>/dev/null || git rev-parse origin/master 2>/dev/null || git merge-base HEAD $(git rev-parse --abbrev-ref HEAD@{upstream} 2>/dev/null || echo HEAD~10))
+
+# Get the actual diff
+git diff $BASE --name-only
+git diff $BASE --stat
+```
+
+### Step 2: Extract Spec Claims
+
+From the PRD, extract these verifiable claims:
+
+| Claim Type                  | Source Section                          | Example                             |
+| --------------------------- | --------------------------------------- | ----------------------------------- |
+| **Success Criteria**        | `## Success Criteria`                   | "User can see existing messages"    |
+| **Functional Requirements** | `## Requirements`                       | "WHEN user clicks X THEN Y happens" |
+| **Affected Files**          | `## Technical Context > Affected Files` | `src/api/users.ts`                  |
+| **Scope Boundaries**        | `## Scope`                              | "In-scope: X, Out-of-scope: Y"      |
+| **Task Deliverables**       | `## Tasks`                              | Each task's end-state description   |
+
+### Step 3: Verify Each Claim
+
+For each extracted claim, gather evidence:
+
+#### Success Criteria Verification
+
+```bash
+# For each success criterion, find code evidence
+# Example: "User can see existing messages"
+grep -r "messages" src/ --include="*.ts" --include="*.tsx" -l
+grep -r "fetchMessages\|getMessages\|listMessages" src/ -l
+```
+
+Map each criterion to:
+
+- **VERIFIED**: Code evidence confirms the criterion is met
+- **PARTIAL**: Some evidence exists but incomplete
+- **MISSING**: No code evidence found
+- **UNTESTABLE**: Cannot be verified via code search (needs manual check)
+
+#### Affected Files Verification
+
+```bash
+# Compare PRD affected files vs actual changed files
+# PRD claims these files would be modified:
+PRD_FILES=$(grep -A 50 "Affected Files" .beads/artifacts/$BEAD_ID/prd.md | grep "src/" | sed 's/.*`//' | sed 's/`.*//')
+
+# Actually modified files:
+ACTUAL_FILES=$(git diff $BASE --name-only)
+
+# Files in PRD but not modified (missing implementation):
+comm -23 <(echo "$PRD_FILES" | sort) <(echo "$ACTUAL_FILES" | sort)
+
+# Files modified but not in PRD (scope creep):
+comm -13 <(echo "$PRD_FILES" | sort) <(echo "$ACTUAL_FILES" | sort)
+```
+
+#### Scope Boundary Check
+
+- **In-scope items**: Verify each has corresponding code changes
+- **Out-of-scope items**: Verify NO code touches those areas (scope creep detection)
+
+### Step 4: Detect Drift Patterns
+
+| Drift Type                 | Detection Method                                       | Severity |
+| -------------------------- | ------------------------------------------------------ | -------- |
+| **Missing Feature**        | Success criterion with no code evidence                | HIGH     |
+| **Partial Implementation** | Criterion partially met (stub, TODO)                   | HIGH     |
+| **Scope Creep**            | Files modified that aren't in PRD affected files       | MEDIUM   |
+| **Spec Rot**               | PRD sections that contradict actual implementation     | MEDIUM   |
+| **Over-Engineering**       | Significant code not traceable to any PRD requirement  | LOW      |
+| **Diverged Behavior**      | Code does something different from WHEN/THEN scenarios | HIGH     |
+
+### Step 5: Calculate Drift Score
+
+```
+Drift Score Calculation:
+- Total claims: [N]
+- VERIFIED: [n] (×1.0)
+- PARTIAL: [n] (×0.5)
+- MISSING: [n] (×0.0)
+- UNTESTABLE: [n] (excluded from calculation)
+
+Adherence = (VERIFIED×1.0 + PARTIAL×0.5) / (Total - UNTESTABLE) × 100
+
+Scope Creep = Extra files modified / Total files modified × 100
+```
+
+## Drift Report Format
+
+```markdown
+## Reconciliation Report: <bead-id>
+
+**PRD:** `.beads/artifacts/<id>/prd.md`
+**Branch:** `<branch-name>`
+**Adherence Score:** [N]%
+**Scope Creep:** [N]%
+
+### Success Criteria
+
+| #   | Criterion        | Status      | Evidence                                   |
+| --- | ---------------- | ----------- | ------------------------------------------ |
+| 1   | [criterion text] | ✅ VERIFIED | `src/file.ts:42` — [what confirms it]      |
+| 2   | [criterion text] | ⚠️ PARTIAL  | `src/file.ts` exists but handler is a stub |
+| 3   | [criterion text] | ❌ MISSING  | No code evidence found                     |
+
+### File Reconciliation
+
+| Category                    | Files                      | Count |
+| --------------------------- | -------------------------- | ----- |
+| ✅ Expected & Modified      | `src/api/users.ts`, ...    | [N]   |
+| ❌ Expected but Untouched   | `src/models/user.ts`, ...  | [N]   |
+| ⚠️ Unexpected Modifications | `src/utils/helper.ts`, ... | [N]   |
+
+### Drift Issues
+
+| #   | Type            | Severity | Description      | Recommendation                                                 |
+| --- | --------------- | -------- | ---------------- | -------------------------------------------------------------- |
+| 1   | Missing Feature | HIGH     | [what's missing] | Implement or use `/iterate --scope reduce` to remove from spec |
+| 2   | Scope Creep     | MEDIUM   | [what's extra]   | Document in PRD or revert                                      |
+
+### Verdict
+
+| Score       | Meaning              | Action                                                 |
+| ----------- | -------------------- | ------------------------------------------------------ |
+| **90-100%** | Excellent adherence  | Ready to close                                         |
+| **70-89%**  | Good with minor gaps | Fix gaps or document as intentional deviations         |
+| **50-69%**  | Significant drift    | Use `/iterate` to reconcile spec and code              |
+| **<50%**    | Major drift          | **BLOCK** — spec and code are fundamentally misaligned |
+```
+
+## Integration Points
+
+- **`/ship` Phase 5**: Run reconcile after review, before close decision
+- **`/compound`**: Include adherence score in retrospective observations
+- **`/pr`**: Include drift report in PR description
+
+## Gotchas
+
+- Some criteria genuinely can't be verified by code search (UI behavior, UX feel) — mark as UNTESTABLE, don't count against score
+- Scope creep isn't always bad — sometimes good engineering requires touching adjacent files. Flag it, don't auto-block.
+- Run AFTER phantom completion detection — reconcile assumes code is substantive, not stubs

package/dist/template/.opencode/skill/verification-before-completion/SKILL.md

@@ -245,6 +245,81 @@ After ANY `task()` subagent returns with "success", follow the **Worker Distrust
 > check a file, verify a condition, reject if unmet. Don't rely on the agent
 > "remembering" to follow the rule.
 
+## Phantom Completion Detection
+
+Tasks can "pass" verification while containing stub implementations. This gate catches completions that are technically correct but substantively empty.
+
+### When to Run
+
+- After all PRD tasks are marked complete (during `/ship` Phase 4-5)
+- Before closing any bead
+- When `--full` verification is requested
+
+### Stub Patterns to Detect
+
+Scan all files modified in the current task/bead for these phantom indicators:
+
+```bash
+# Run against modified code files only (exclude .md, .json, .yml to avoid false positives)
+git diff --name-only origin/main | grep -E '\.(ts|tsx|js|jsx|py|rs|go|swift|kt|java)$' | xargs grep -nE \
+  'return null|return undefined|return \{\}|return \[\]|onClick=\{?\(\) => \{\}\}?|TODO|FIXME|placeholder|stub|not.?implemented|throw new Error\(.Not implemented' \
+  2>/dev/null
+```
+
+| Pattern                                                  | What It Indicates         | Severity |
+| -------------------------------------------------------- | ------------------------- | -------- |
+| `return null` / `return undefined`                       | Empty implementation      | HIGH     |
+| `return {}` / `return []`                                | Hollow data               | HIGH     |
+| `onClick={() => {}}`                                     | No-op handler             | HIGH     |
+| `<div>Component</div>` / `<div>{/* TODO */}</div>`       | Placeholder UI            | HIGH     |
+| `TODO` / `FIXME` / `HACK`                                | Acknowledged incomplete   | MEDIUM   |
+| `placeholder` / `stub` / `not implemented`               | Self-documenting stubs    | HIGH     |
+| `throw new Error("Not implemented")`                     | Explicit stub             | HIGH     |
+| `fetch('/api/...')` without `await` or error handling    | Disconnected call         | MEDIUM   |
+| `Response.json({ok: true})` or static hardcoded response | Fake API response         | HIGH     |
+| `console.log` as only function body                      | Debug-only implementation | MEDIUM   |
+
+### Three-Level Artifact Verification
+
+For each file listed in PRD `Affected Files`:
+
+| Level              | Check                  | How                                                                                          |
+| ------------------ | ---------------------- | -------------------------------------------------------------------------------------------- |
+| **1: Exists**      | File is present        | `ls path/to/file.ts`                                                                         |
+| **2: Substantive** | Not a stub/placeholder | `grep -v "TODO\|FIXME\|return null\|placeholder" path/to/file.ts` — verify real logic exists |
+| **3: Wired**       | Connected and used     | `grep -r "import.*ExportName" src/` — verify other files import/use it                       |
+
+### Key Link Verification
+
+Check that components are actually connected (not just existing side-by-side):
+
+| Connection Type | Check Command                                                  |
+| --------------- | -------------------------------------------------------------- |
+| Component → API | `grep -E "fetch.*api/\|axios\|useSWR\|useQuery" Component.tsx` |
+| API → Database  | `grep -E "prisma\.\|db\.\|sql\|query" route.ts`                |
+| Form → Handler  | `grep "onSubmit\|handleSubmit" Component.tsx`                  |
+| State → Render  | `grep "{stateVar}" Component.tsx`                              |
+| Route → Page    | Check router config references the page component              |
+
+### Phantom Score
+
+After running all checks, report a phantom score:
+
+```
+Phantom Completion Check:
+- Files scanned: [N]
+- Stubs found: [N] (HIGH: [n], MEDIUM: [n])
+- Artifact levels: [N] exist, [M] substantive, [K] wired
+- Key links verified: [N]/[M]
+- Score: [CLEAN | SUSPECT | PHANTOM]
+```
+
+| Score       | Criteria                                       | Action                            |
+| ----------- | ---------------------------------------------- | --------------------------------- |
+| **CLEAN**   | 0 HIGH stubs, all artifacts Level 3            | Proceed                           |
+| **SUSPECT** | 1-2 MEDIUM stubs OR 1 artifact not Level 3     | Report, ask user                  |
+| **PHANTOM** | Any HIGH stubs OR >2 artifacts not substantive | **BLOCK** — fix before completion |
+
 ## Why This Matters
 
 From 24 failure memories:

package/dist/template/.opencode/skill/verification-gates/SKILL.md

@@ -0,0 +1,63 @@
+---
+name: verification-gates
+description: >
+  Use when running pre-merge or pre-PR verification checks. Detects project type and runs appropriate build, test, lint, and typecheck commands.
+version: 1.0.0
+tags: [verification, testing, lint, typecheck, ci]
+---
+
+# Verification Gates
+
+Detect project type and run the appropriate verification commands before merging or creating PRs.
+
+## When to Use
+
+- In `/pr` before creating a pull request
+- In `/review-codebase` during automated checks phase
+- In `/ship` during final verification
+- Any command that needs to verify code quality before completion
+
+## When NOT to Use
+
+- For incremental checks during development (just run the specific tool)
+- When only one check type is needed (e.g., lint-only)
+
+## Project Type Detection
+
+| Project Type    | Detect Via                    | Build            | Test            | Lint                          | Typecheck                             |
+| --------------- | ----------------------------- | ---------------- | --------------- | ----------------------------- | ------------------------------------- |
+| Node/TypeScript | `package.json`                | `npm run build`  | `npm test`      | `npm run lint`                | `npm run typecheck` or `tsc --noEmit` |
+| Rust            | `Cargo.toml`                  | `cargo build`    | `cargo test`    | `cargo clippy -- -D warnings` | (included in build)                   |
+| Python          | `pyproject.toml` / `setup.py` | —                | `pytest`        | `ruff check .`                | `mypy .`                              |
+| Go              | `go.mod`                      | `go build ./...` | `go test ./...` | `golangci-lint run`           | (included in build)                   |
+
+## Protocol
+
+### Step 1: Detect project type
+
+Check for indicator files in the project root. Multiple types may coexist (e.g., Node + Python monorepo).
+
+### Step 2: Run checks in parallel where possible
+
+```bash
+# Run typecheck and lint in parallel
+npm run typecheck &
+npm run lint &
+wait
+
+# Then run tests (may depend on build)
+npm test
+```
+
+### Step 3: Report results
+
+For each check, report:
+
+- **Pass/Fail** status
+- **Error count** (if failed)
+- **Key error messages** (first 5)
+
+### Step 4: Gate decision
+
+- **All pass:** Proceed with the command
+- **Any fail:** Stop and report. Let the user decide whether to proceed or fix.