skillpacks 0.1.0

package/packs/code-debug/claude/trace/SKILL.md

@@ -0,0 +1,110 @@
+---
+name: trace
+description: Follow a request end-to-end through the stack from route to database
+type: review
+version: v0.1
+argument-hint: <route, endpoint, or feature to trace, e.g. "/api/products" or "user login flow">
+---
+
+# Trace
+
+Follow a request or feature flow end-to-end through the application stack, mapping every layer from the entry point to the database and back.
+
+## Process
+
+1. **Identify the entry point** from `$ARGUMENTS`:
+   - API route or page route → find the route handler or page component.
+   - Feature name → identify the primary user action and its entry point.
+   - tRPC procedure → find the router definition.
+   - If unclear, ask the user for specifics.
+
+2. **Read `CLAUDE.md`** for project conventions and architecture.
+
+3. **Trace forward through the stack:**
+
+   **Layer 1 — Entry Point:**
+   - Route handler, page component, or API endpoint.
+   - What middleware runs before it (auth, rate limiting, etc.).
+   - What parameters/inputs it receives.
+
+   **Layer 2 — Business Logic:**
+   - Service functions, tRPC procedures, or server actions called.
+   - Validation and transformation logic.
+   - Authorization checks.
+
+   **Layer 3 — Data Access:**
+   - Database queries (Drizzle, Prisma, raw SQL).
+   - External API calls.
+   - Cache reads/writes.
+   - What tables/collections are touched.
+
+   **Layer 4 — Response:**
+   - How the response is constructed.
+   - What data is returned to the client.
+   - Error handling at each layer.
+
+4. **Map the data flow:**
+   - What types are used at each boundary.
+   - Where data is transformed or mapped.
+   - Where validation happens.
+   - Where errors are caught and how they propagate.
+
+5. **Identify concerns:**
+   - N+1 queries or redundant data fetches.
+   - Missing error handling at layer boundaries.
+   - Auth/authz gaps.
+   - Type mismatches between layers.
+   - Performance bottlenecks (large queries, missing indexes, unnecessary joins).
+
+## Output
+
+### Trace: [route/feature name]
+
+```
+[Entry] → [Middleware] → [Handler] → [Service] → [DB Query] → [Response]
+file.ts:10   auth.ts:5    route.ts:20  svc.ts:45   db.ts:30     route.ts:25
+```
+
+### Layer-by-Layer
+
+#### 1. Entry Point
+- **File**: `app/api/route.ts:10`
+- **Method**: GET/POST
+- **Middleware**: auth, rate-limit
+- **Input**: params, body, query
+
+#### 2. Business Logic
+- **File**: `services/foo.ts:45`
+- **Called by**: route handler
+- **Validates**: [what]
+- **Calls**: [what functions/services]
+
+#### 3. Data Access
+- **File**: `db/queries/foo.ts:30`
+- **Table(s)**: `products`, `categories`
+- **Query type**: SELECT with JOIN
+- **Indexes used**: [if identifiable]
+
+#### 4. Response
+- **Shape**: `{ data: Product[], count: number }`
+- **Error cases**: 401, 404, 500
+
+### Data Flow
+```
+Input (params) → validated → service call → DB query → transform → response
+```
+
+### Concerns Found
+- [Any issues identified during the trace]
+
+## Constraints
+- Follow the actual code path — do not guess or assume based on naming conventions.
+- Read each file in the chain; do not skip layers.
+- Keep the output focused on the specific route/feature — do not map the entire application.
+- If a layer uses dynamic dispatch or plugin patterns that make the path ambiguous, note the ambiguity.
+- Do not modify any code — this is a read-only analysis.
+
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/code-debug/claude/trace/archive/v0.0/SKILL.md

@@ -0,0 +1,138 @@
+---
+name: trace
+description: Follow a request end-to-end through the stack from route to database
+type: review
+version: v0.0
+argument-hint: <route, endpoint, or feature to trace, e.g. "/api/products" or "user login flow">
+---
+
+# Trace
+
+Follow a request or feature flow end-to-end through the application stack, mapping every layer from the entry point to the database and back.
+
+## Process
+
+1. **Identify the entry point** from `$ARGUMENTS`:
+   - API route or page route → find the route handler or page component.
+   - Feature name → identify the primary user action and its entry point.
+   - tRPC procedure → find the router definition.
+   - If unclear, ask the user for specifics.
+
+2. **Read `CLAUDE.md`** for project conventions and architecture.
+
+3. **Trace forward through the stack:**
+
+   **Layer 1 — Entry Point:**
+   - Route handler, page component, or API endpoint.
+   - What middleware runs before it (auth, rate limiting, etc.).
+   - What parameters/inputs it receives.
+
+   **Layer 2 — Business Logic:**
+   - Service functions, tRPC procedures, or server actions called.
+   - Validation and transformation logic.
+   - Authorization checks.
+
+   **Layer 3 — Data Access:**
+   - Database queries (Drizzle, Prisma, raw SQL).
+   - External API calls.
+   - Cache reads/writes.
+   - What tables/collections are touched.
+
+   **Layer 4 — Response:**
+   - How the response is constructed.
+   - What data is returned to the client.
+   - Error handling at each layer.
+
+4. **Map the data flow:**
+   - What types are used at each boundary.
+   - Where data is transformed or mapped.
+   - Where validation happens.
+   - Where errors are caught and how they propagate.
+
+5. **Identify concerns:**
+   - N+1 queries or redundant data fetches.
+   - Missing error handling at layer boundaries.
+   - Auth/authz gaps.
+   - Type mismatches between layers.
+   - Performance bottlenecks (large queries, missing indexes, unnecessary joins).
+
+## Output Format
+
+### Trace: [route/feature name]
+
+```
+[Entry] → [Middleware] → [Handler] → [Service] → [DB Query] → [Response]
+file.ts:10   auth.ts:5    route.ts:20  svc.ts:45   db.ts:30     route.ts:25
+```
+
+### Layer-by-Layer
+
+#### 1. Entry Point
+- **File**: `app/api/route.ts:10`
+- **Method**: GET/POST
+- **Middleware**: auth, rate-limit
+- **Input**: params, body, query
+
+#### 2. Business Logic
+- **File**: `services/foo.ts:45`
+- **Called by**: route handler
+- **Validates**: [what]
+- **Calls**: [what functions/services]
+
+#### 3. Data Access
+- **File**: `db/queries/foo.ts:30`
+- **Table(s)**: `products`, `categories`
+- **Query type**: SELECT with JOIN
+- **Indexes used**: [if identifiable]
+
+#### 4. Response
+- **Shape**: `{ data: Product[], count: number }`
+- **Error cases**: 401, 404, 500
+
+### Data Flow
+```
+Input (params) → validated → service call → DB query → transform → response
+```
+
+### Concerns Found
+- [Any issues identified during the trace]
+
+## Constraints
+- Follow the actual code path — do not guess or assume based on naming conventions.
+- Read each file in the chain; do not skip layers.
+- Keep the output focused on the specific route/feature — do not map the entire application.
+- If a layer uses dynamic dispatch or plugin patterns that make the path ambiguous, note the ambiguity.
+- Do not modify any code — this is a read-only analysis.
+
+
+## Alignment Page
+
+When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page at `alignment/trace-{topic}.html`. Use a normalized topic slug derived from the app, feature, research subject, report subject, or output filename.
+
+**Full content requirement.** The alignment page must contain the complete content of every proposed markdown deliverable -- every section, every finding, every detail, every list item. It is a thorough interactive review document, not a summary. Render the full deliverable content in clean, readable HTML with appropriate hierarchy, styling, and navigation. If the skill writes multiple scoped deliverables in one run, build one alignment page that contains all deliverables with anchor-linked navigation. Durable tracker artifacts, such as `research/assumption-tracker.md`, remain canonical markdown outputs but must also be fully rendered into the alignment page before approval.
+
+**Dark-mode styling.** Use a dark color scheme by default. Base CSS variables: `--bg: #0d1117; --surface: #161b22; --border: #30363d; --text: #c9d1d9; --text-muted: #8b949e; --accent: #58a6ff; --green: #3fb950; --red: #f85149; --orange: #d29922; --purple: #bc8cff;`. Apply `background: var(--bg); color: var(--text);` on body. Use `--surface` for cards, nav, and table headers. Use `--border` for all borders. Use `--purple` for question blocks and gate headings. Use `--accent` for links and section headings. Keep headings `color: #fff` or `var(--accent)` for hierarchy. Question block backgrounds should use `#1c2333`.
+
+**Alignment gates.** Treat gates as explicit review sections inside the HTML page. A gate blocks finalization until its required inline questions are answered and compiled into YAML. Include every gate that applies to the skill output, and include these gate types whenever relevant: evidence coverage, assumptions/confidence, scope/non-goals, candidate/verdict decisions, artifact destination, proposed file changes, coverage checkpoint, and post-approval route.
+
+**Report-only research gates.** For report-only or pre-approval research skills, the alignment page must explicitly contain evidence coverage, assumptions/confidence, recommended path, proposed file changes, and approval gates before any canonical research, spec, or task file is created or updated.
+
+
+**Required inline questions.** Each gate must contain at least one required inline question placed directly under the content it governs, inside a visually distinct question block. Each question must use radio-button inputs and include two standing options after the skill-generated choices: "Other / None of the above" backed by a multi-line text box for free-form input, and "Need clarification" backed by an optional notes box where the user can explain what is unclear. When any radio option other than "Other" or "Need clarification" is selected, show an optional "Additional notes" text box beneath it so the user can qualify their choice. Generate questions based on what genuinely needs user input -- do not add filler questions. Do not create a separate bottom "Decisions & Clarifications" section.
+
+**Gate YAML contract.** At the bottom of the page, include a "Compile Answers" button that aggregates answers from all inline gate questions throughout the page, including free-text notes. The button remains disabled until every required question has a selection, shows a count of remaining unanswered questions, and scrolls to the first unanswered question if clicked early. When every question is answered, generate a structured YAML block with one item per gate answer using this stable shape: `section`, `gate_type`, `status` (`answered`, `other`, or `needs-clarification`), `answer`, optional `notes`, and optional `target_artifact` or `target_path` when the gate controls file output. After successful compilation, automatically attempt to copy the YAML to the clipboard with the Clipboard API, display copy status, and display the YAML in a read-only textarea with an explicit "Copy YAML" button. The copy button must retry clipboard copy when supported and fall back to selecting the textarea contents when clipboard access is unavailable or blocked.
+
+**Pre-approval stop.** Before user approval, the next action is review of the HTML alignment page, not downstream routing. Ask the user to review the page and provide the compiled YAML answers. Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language until after compiled YAML has been provided and the approved artifacts have been written or updated.
+
+**Diff highlighting on updates.** When the agent updates an existing alignment page after receiving compiled answers, highlight what changed since the previous version. The agent chooses inline annotation or side-by-side layout per situation.
+
+**Archiving.** Before replacing an existing alignment page, archive it to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/trace-{topic}.html`.
+
+**Browser open.** Attempt to open the resulting HTML page in the browser and report whether the open succeeded or was blocked. A blocked browser-open attempt does not make the skill fail when the files were written correctly.
+
+## Default Shipping Contract
+
+- **Default next-step routing:** when reporting completion, include either `Recommended next skill: <command>` or the two-line pair `**Next work:** <specific task or "none">` and `**Recommended next command:** <one command or route>` so the next operator has a concrete handoff.
+- If this skill creates or modifies tracked repository files, finish by committing and pushing all intended changes to the repository primary branch (`main` when present, otherwise `master`) before stopping, even if the user did not explicitly ask for commit/push.
+- Do not leave tracked changes or unpushed commits behind. If unrelated tracked work is already present, either include it in sensible commits too or stop and explain the blocker.
+- This contract does not override stricter safety rules about secrets, destructive history changes, release publication/tag confirmation, or production deploy confirmation.

package/packs/code-debug/codex/debug/CHANGELOG.md

@@ -0,0 +1,9 @@
+# Changelog
+
+## v0.0
+
+- Archived previous skill contract.
+
+## v0.1 - 2026-05-25
+
+- Added research-quality alignment requirements covering claim/evidence/inference separation, no-context-loss HTML translation, evidence matrices, confidence/assumption registers, source coverage, and research completeness gates.

package/packs/code-debug/codex/debug/SKILL.md

@@ -0,0 +1,46 @@
+---
+name: debug
+description: Investigate a problem, log it to the debug changelog, cross-check past issues, and suggest a non-duplicate fix.
+type: debugging
+version: v0.1
+---
+
+# Debug
+
+Invoke as `$debug`.
+
+Investigate a reported problem, maintain a persistent debug changelog (`docs/debug-changelog.md`), and propose a fix that avoids repeating past solutions.
+
+## Process
+
+1. Parse the error message, stack trace, or bug description.
+2. Capture environment context: current branch, recent commits, uncommitted changes.
+3. Ensure `docs/debug-changelog.md` exists (create `docs/` directory and file if missing).
+4. Read the full debug changelog and search for prior entries matching the current symptom.
+5. If a match is found, report what was tried before and whether the recurrence is systemic.
+6. Trace the execution path from the symptom to the root cause, reading only files in the chain.
+7. Check recent git history for changes that may have introduced the issue.
+8. Propose a minimal fix, cross-checking the changelog to avoid repeating a previously failed approach.
+9. Apply the fix, write or update tests, and run them to verify.
+10. Prepend a structured entry to `docs/debug-changelog.md` with: date, symptom, category, severity, root cause, fix, test results, related entries, and systemic flag.
+
+## Output
+
+- **Problem**: Symptom, new or recurring
+- **Root Cause**: file:line, what's wrong, when introduced
+- **Fix Applied**: approach, files modified, test results
+- **Changelog Updated**: entry added, any cross-references
+- **Prevention**: what check would have caught this earlier; systemic follow-up if applicable
+
+## Constraints
+
+- Always read the full debug changelog before proposing a fix.
+- Do not refactor unrelated code.
+- Never duplicate a previously failed fix without justification.
+- If the root cause can't be determined, report what was ruled out.
+- Always run tests after applying the fix.
+
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/code-debug/codex/debug/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Debug"
+  short_description: "Investigate problem with changelog cross-check"
+  default_prompt: "Use $debug to investigate this problem, cross-check past issues, and suggest a fix."
+
+policy:
+  allow_implicit_invocation: true

package/packs/code-debug/codex/debug/archive/v0.0/SKILL.md

@@ -0,0 +1,74 @@
+---
+name: debug
+description: Investigate a problem, log it to the debug changelog, cross-check past issues, and suggest a non-duplicate fix.
+type: debugging
+version: v0.0
+---
+
+# Debug
+
+Invoke as `$debug`.
+
+Investigate a reported problem, maintain a persistent debug changelog (`docs/debug-changelog.md`), and propose a fix that avoids repeating past solutions.
+
+## Workflow
+
+1. Parse the error message, stack trace, or bug description.
+2. Capture environment context: current branch, recent commits, uncommitted changes.
+3. Ensure `docs/debug-changelog.md` exists (create `docs/` directory and file if missing).
+4. Read the full debug changelog and search for prior entries matching the current symptom.
+5. If a match is found, report what was tried before and whether the recurrence is systemic.
+6. Trace the execution path from the symptom to the root cause, reading only files in the chain.
+7. Check recent git history for changes that may have introduced the issue.
+8. Propose a minimal fix, cross-checking the changelog to avoid repeating a previously failed approach.
+9. Apply the fix, write or update tests, and run them to verify.
+10. Prepend a structured entry to `docs/debug-changelog.md` with: date, symptom, category, severity, root cause, fix, test results, related entries, and systemic flag.
+
+## Output Format
+
+- **Problem**: Symptom, new or recurring
+- **Root Cause**: file:line, what's wrong, when introduced
+- **Fix Applied**: approach, files modified, test results
+- **Changelog Updated**: entry added, any cross-references
+- **Prevention**: what check would have caught this earlier; systemic follow-up if applicable
+
+## Constraints
+
+- Always read the full debug changelog before proposing a fix.
+- Do not refactor unrelated code.
+- Never duplicate a previously failed fix without justification.
+- If the root cause can't be determined, report what was ruled out.
+- Always run tests after applying the fix.
+
+
+## Alignment Page
+
+When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page at `alignment/debug-{topic}.html`. Use a normalized topic slug derived from the app, feature, research subject, report subject, or output filename.
+
+**Full content requirement.** The alignment page must contain the complete content of every proposed markdown deliverable -- every section, every finding, every detail, every list item. It is a thorough interactive review document, not a summary. Render the full deliverable content in clean, readable HTML with appropriate hierarchy, styling, and navigation. If the skill writes multiple scoped deliverables in one run, build one alignment page that contains all deliverables with anchor-linked navigation. Durable tracker artifacts, such as `research/assumption-tracker.md`, remain canonical markdown outputs but must also be fully rendered into the alignment page before approval.
+
+**Dark-mode styling.** Use a dark color scheme by default. Base CSS variables: `--bg: #0d1117; --surface: #161b22; --border: #30363d; --text: #c9d1d9; --text-muted: #8b949e; --accent: #58a6ff; --green: #3fb950; --red: #f85149; --orange: #d29922; --purple: #bc8cff;`. Apply `background: var(--bg); color: var(--text);` on body. Use `--surface` for cards, nav, and table headers. Use `--border` for all borders. Use `--purple` for question blocks and gate headings. Use `--accent` for links and section headings. Keep headings `color: #fff` or `var(--accent)` for hierarchy. Question block backgrounds should use `#1c2333`.
+
+**Alignment gates.** Treat gates as explicit review sections inside the HTML page. A gate blocks finalization until its required inline questions are answered and compiled into YAML. Include every gate that applies to the skill output, and include these gate types whenever relevant: evidence coverage, assumptions/confidence, scope/non-goals, candidate/verdict decisions, artifact destination, proposed file changes, coverage checkpoint, and post-approval route.
+
+**Report-only research gates.** For report-only or pre-approval research skills, the alignment page must explicitly contain evidence coverage, assumptions/confidence, recommended path, proposed file changes, and approval gates before any canonical research, spec, or task file is created or updated.
+
+
+**Required inline questions.** Each gate must contain at least one required inline question placed directly under the content it governs, inside a visually distinct question block. Each question must use radio-button inputs and include two standing options after the skill-generated choices: "Other / None of the above" backed by a multi-line text box for free-form input, and "Need clarification" backed by an optional notes box where the user can explain what is unclear. When any radio option other than "Other" or "Need clarification" is selected, show an optional "Additional notes" text box beneath it so the user can qualify their choice. Generate questions based on what genuinely needs user input -- do not add filler questions. Do not create a separate bottom "Decisions & Clarifications" section.
+
+**Gate YAML contract.** At the bottom of the page, include a "Compile Answers" button that aggregates answers from all inline gate questions throughout the page, including free-text notes. The button remains disabled until every required question has a selection, shows a count of remaining unanswered questions, and scrolls to the first unanswered question if clicked early. When every question is answered, generate a structured YAML block with one item per gate answer using this stable shape: `section`, `gate_type`, `status` (`answered`, `other`, or `needs-clarification`), `answer`, optional `notes`, and optional `target_artifact` or `target_path` when the gate controls file output. After successful compilation, automatically attempt to copy the YAML to the clipboard with the Clipboard API, display copy status, and display the YAML in a read-only textarea with an explicit "Copy YAML" button. The copy button must retry clipboard copy when supported and fall back to selecting the textarea contents when clipboard access is unavailable or blocked.
+
+**Pre-approval stop.** Before user approval, the next action is review of the HTML alignment page, not downstream routing. Ask the user to review the page and provide the compiled YAML answers. Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language until after compiled YAML has been provided and the approved artifacts have been written or updated.
+
+**Diff highlighting on updates.** When the agent updates an existing alignment page after receiving compiled answers, highlight what changed since the previous version. The agent chooses inline annotation or side-by-side layout per situation.
+
+**Archiving.** Before replacing an existing alignment page, archive it to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/debug-{topic}.html`.
+
+**Browser open.** Attempt to open the resulting HTML page in the browser and report whether the open succeeded or was blocked. A blocked browser-open attempt does not make the skill fail when the files were written correctly.
+
+## Default Shipping Contract
+
+- **Default next-step routing:** when reporting completion, include either `Recommended next skill: <command>` or the two-line pair `**Next work:** <specific task or "none">` and `**Recommended next command:** <one command or route>` so the next operator has a concrete handoff.
+- If this skill creates or modifies tracked repository files, finish by committing and pushing all intended changes to the repository primary branch (`main` when present, otherwise `master`) before stopping, even if the user did not explicitly ask for commit/push.
+- Do not leave tracked changes or unpushed commits behind. If unrelated tracked work is already present, either include it in sensible commits too or stop and explain the blocker.
+- This contract does not override stricter safety rules about secrets, destructive history changes, release publication/tag confirmation, or production deploy confirmation.

package/packs/code-debug/codex/investigate/CHANGELOG.md

@@ -0,0 +1,9 @@
+# Changelog
+
+## v0.0
+
+- Archived previous skill contract.
+
+## v0.1 - 2026-05-25
+
+- Added research-quality alignment requirements covering claim/evidence/inference separation, no-context-loss HTML translation, evidence matrices, confidence/assumption registers, source coverage, and research completeness gates.

package/packs/code-debug/codex/investigate/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: investigate
+description: Validate user claims against codebase and git history, trace to root cause, and propose a fix
+type: debugging
+version: v0.1
+---
+
+# Investigate
+
+Invoke as `$investigate`.
+
+Use this skill when the user reports a bug, error, unexpected behavior, or provides observations/hypotheses about what they think is wrong. Validates claims against the codebase and git history before tracing to root cause.
+
+## Process
+
+1. Parse the error message, stack trace, bug description, or user observations/claims.
+2. **Select investigation strategy** from flags or auto-detection:
+   - `--ui`: Visual/layout bugs — start from component tree, styles, animations, transitions, spacing, theming, skeleton/loading states, positioning. Signal words: skeleton, animation, spacing, popover, transition, theme, truncated, glitch, dead space, detached, pop-in, flickering, layout, z-index, overflow.
+   - `--data`: Data/state bugs — start from data pipeline, state management, timers, counters, sync logic. Signal words: countdown, percentage, usage, sync, stale, timer, refresh, reset, missing data, wrong number, out of sync, not updating, mismatch.
+   - General (default): Errors, crashes, behavioral bugs, and anything ambiguous — start from symptom/stack trace.
+   - If input has signals from both UI and data, prefer data strategy — wrong data commonly manifests as a visual symptom.
+3. If the user provides claims or hypotheses, validate each one against the codebase and git history (`git log`, `git diff`, `git blame`). Classify each as confirmed, partially correct, or not supported by evidence. Report findings before proceeding.
+4. Trace using the selected strategy:
+   - **UI**: component tree → styles → layout → animation/transition → render lifecycle. Check CSS conflicts, missing keys, layout thrashing, transition timing.
+   - **Data**: data source → transform → store → subscription → render. Check stale closures, missing dependency arrays, incorrect comparisons, cache invalidation, timer drift.
+   - **General**: execution path from symptom to source — null/undefined, wrong types, missing env vars, stale imports, race conditions, schema mismatches.
+   - If the initial strategy hits a dead end, pivot to the other — a UI bug may have a data root cause, and vice versa.
+5. Check recent git history for changes that may have introduced the issue.
+6. Identify the root cause with file and line reference.
+7. Apply a minimal fix and write or update tests.
+8. Run tests to verify the fix and check for regressions.
+
+## Output
+
+- **Strategy Used**: UI / Data / General (auto-detected or flag-forced), whether a pivot occurred
+- **User Claims Validated**: For each claim — verdict (confirmed/partially correct/not supported) and evidence. Skip if input was a plain error message.
+- **Root Cause**: file:line, what's wrong, when introduced, relationship to user's theory
+- **Fix Applied**: files modified, test results
+- **Prevention**: what check would have caught this earlier
+
+## Constraints
+
+- Do not refactor unrelated code.
+- Validate user claims before assuming they're correct — observations are a starting point, not ground truth.
+- If the root cause can't be determined, report what was ruled out.
+- Always run tests after applying the fix.
+
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/code-debug/codex/investigate/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Investigate"
+  short_description: "Trace bug to root cause"
+  default_prompt: "Use $investigate to investigate this bug and find the root cause."
+
+policy:
+  allow_implicit_invocation: true

package/packs/code-debug/codex/investigate/archive/v0.0/SKILL.md

@@ -0,0 +1,81 @@
+---
+name: investigate
+description: Validate user claims against codebase and git history, trace to root cause, and propose a fix
+type: debugging
+version: v0.0
+---
+
+# Investigate
+
+Invoke as `$investigate`.
+
+Use this skill when the user reports a bug, error, unexpected behavior, or provides observations/hypotheses about what they think is wrong. Validates claims against the codebase and git history before tracing to root cause.
+
+## Workflow
+
+1. Parse the error message, stack trace, bug description, or user observations/claims.
+2. **Select investigation strategy** from flags or auto-detection:
+   - `--ui`: Visual/layout bugs — start from component tree, styles, animations, transitions, spacing, theming, skeleton/loading states, positioning. Signal words: skeleton, animation, spacing, popover, transition, theme, truncated, glitch, dead space, detached, pop-in, flickering, layout, z-index, overflow.
+   - `--data`: Data/state bugs — start from data pipeline, state management, timers, counters, sync logic. Signal words: countdown, percentage, usage, sync, stale, timer, refresh, reset, missing data, wrong number, out of sync, not updating, mismatch.
+   - General (default): Errors, crashes, behavioral bugs, and anything ambiguous — start from symptom/stack trace.
+   - If input has signals from both UI and data, prefer data strategy — wrong data commonly manifests as a visual symptom.
+3. If the user provides claims or hypotheses, validate each one against the codebase and git history (`git log`, `git diff`, `git blame`). Classify each as confirmed, partially correct, or not supported by evidence. Report findings before proceeding.
+4. Trace using the selected strategy:
+   - **UI**: component tree → styles → layout → animation/transition → render lifecycle. Check CSS conflicts, missing keys, layout thrashing, transition timing.
+   - **Data**: data source → transform → store → subscription → render. Check stale closures, missing dependency arrays, incorrect comparisons, cache invalidation, timer drift.
+   - **General**: execution path from symptom to source — null/undefined, wrong types, missing env vars, stale imports, race conditions, schema mismatches.
+   - If the initial strategy hits a dead end, pivot to the other — a UI bug may have a data root cause, and vice versa.
+5. Check recent git history for changes that may have introduced the issue.
+6. Identify the root cause with file and line reference.
+7. Apply a minimal fix and write or update tests.
+8. Run tests to verify the fix and check for regressions.
+
+## Output Format
+
+- **Strategy Used**: UI / Data / General (auto-detected or flag-forced), whether a pivot occurred
+- **User Claims Validated**: For each claim — verdict (confirmed/partially correct/not supported) and evidence. Skip if input was a plain error message.
+- **Root Cause**: file:line, what's wrong, when introduced, relationship to user's theory
+- **Fix Applied**: files modified, test results
+- **Prevention**: what check would have caught this earlier
+
+## Constraints
+
+- Do not refactor unrelated code.
+- Validate user claims before assuming they're correct — observations are a starting point, not ground truth.
+- If the root cause can't be determined, report what was ruled out.
+- Always run tests after applying the fix.
+
+
+## Alignment Page
+
+When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page at `alignment/investigate-{topic}.html`. Use a normalized topic slug derived from the app, feature, research subject, report subject, or output filename.
+
+**Full content requirement.** The alignment page must contain the complete content of every proposed markdown deliverable -- every section, every finding, every detail, every list item. It is a thorough interactive review document, not a summary. Render the full deliverable content in clean, readable HTML with appropriate hierarchy, styling, and navigation. If the skill writes multiple scoped deliverables in one run, build one alignment page that contains all deliverables with anchor-linked navigation. Durable tracker artifacts, such as `research/assumption-tracker.md`, remain canonical markdown outputs but must also be fully rendered into the alignment page before approval.
+
+**Dark-mode styling.** Use a dark color scheme by default. Base CSS variables: `--bg: #0d1117; --surface: #161b22; --border: #30363d; --text: #c9d1d9; --text-muted: #8b949e; --accent: #58a6ff; --green: #3fb950; --red: #f85149; --orange: #d29922; --purple: #bc8cff;`. Apply `background: var(--bg); color: var(--text);` on body. Use `--surface` for cards, nav, and table headers. Use `--border` for all borders. Use `--purple` for question blocks and gate headings. Use `--accent` for links and section headings. Keep headings `color: #fff` or `var(--accent)` for hierarchy. Question block backgrounds should use `#1c2333`.
+
+**Alignment gates.** Treat gates as explicit review sections inside the HTML page. A gate blocks finalization until its required inline questions are answered and compiled into YAML. Include every gate that applies to the skill output, and include these gate types whenever relevant: evidence coverage, assumptions/confidence, scope/non-goals, candidate/verdict decisions, artifact destination, proposed file changes, coverage checkpoint, and post-approval route.
+
+**Report-only research gates.** For report-only or pre-approval research skills, the alignment page must explicitly contain evidence coverage, assumptions/confidence, recommended path, proposed file changes, and approval gates before any canonical research, spec, or task file is created or updated.
+
+
+**Required inline questions.** Each gate must contain at least one required inline question placed directly under the content it governs, inside a visually distinct question block. Each question must use radio-button inputs and include two standing options after the skill-generated choices: "Other / None of the above" backed by a multi-line text box for free-form input, and "Need clarification" backed by an optional notes box where the user can explain what is unclear. When any radio option other than "Other" or "Need clarification" is selected, show an optional "Additional notes" text box beneath it so the user can qualify their choice. Generate questions based on what genuinely needs user input -- do not add filler questions. Do not create a separate bottom "Decisions & Clarifications" section.
+
+**Gate YAML contract.** At the bottom of the page, include a "Compile Answers" button that aggregates answers from all inline gate questions throughout the page, including free-text notes. The button remains disabled until every required question has a selection, shows a count of remaining unanswered questions, and scrolls to the first unanswered question if clicked early. When every question is answered, generate a structured YAML block with one item per gate answer using this stable shape: `section`, `gate_type`, `status` (`answered`, `other`, or `needs-clarification`), `answer`, optional `notes`, and optional `target_artifact` or `target_path` when the gate controls file output. After successful compilation, automatically attempt to copy the YAML to the clipboard with the Clipboard API, display copy status, and display the YAML in a read-only textarea with an explicit "Copy YAML" button. The copy button must retry clipboard copy when supported and fall back to selecting the textarea contents when clipboard access is unavailable or blocked.
+
+**Pre-approval stop.** Before user approval, the next action is review of the HTML alignment page, not downstream routing. Ask the user to review the page and provide the compiled YAML answers. Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language until after compiled YAML has been provided and the approved artifacts have been written or updated.
+
+**Diff highlighting on updates.** When the agent updates an existing alignment page after receiving compiled answers, highlight what changed since the previous version. The agent chooses inline annotation or side-by-side layout per situation.
+
+**Archiving.** Before replacing an existing alignment page, archive it to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/investigate-{topic}.html`.
+
+**Browser open.** Attempt to open the resulting HTML page in the browser and report whether the open succeeded or was blocked. A blocked browser-open attempt does not make the skill fail when the files were written correctly.
+
+## Default Shipping Contract
+
+- **Default next-step routing:** when reporting completion, include either `Recommended next skill: <command>` or the two-line pair `**Next work:** <specific task or "none">` and `**Recommended next command:** <one command or route>` so the next operator has a concrete handoff.
+- If the investigation applied a fix, validated it, committed it, pushed it, and confirmed the tree is clean with no unpushed commits, end with exactly `**Next work:** none` and `**Recommended next command:** none`.
+- Do not recommend `$ship-end` after a clean, already-pushed investigation unless there are pending docs, uncommitted changes, unpushed commits, deploy follow-up, unresolved wrap-up work, or a project task source explicitly points to `$ship-end`.
+- If this skill creates or modifies tracked repository files, finish by committing and pushing all intended changes to the repository primary branch (`main` when present, otherwise `master`) before stopping, even if the user did not explicitly ask for commit/push.
+- Do not leave tracked changes or unpushed commits behind. If unrelated tracked work is already present, either include it in sensible commits too or stop and explain the blocker.
+- This contract does not override stricter safety rules about secrets, destructive history changes, release publication/tag confirmation, or production deploy confirmation.

package/packs/code-debug/codex/trace/CHANGELOG.md

@@ -0,0 +1,9 @@
+# Changelog
+
+## v0.0
+
+- Archived previous skill contract.
+
+## v0.1 - 2026-05-25
+
+- Added research-quality alignment requirements covering claim/evidence/inference separation, no-context-loss HTML translation, evidence matrices, confidence/assumption registers, source coverage, and research completeness gates.

package/packs/code-debug/codex/trace/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: trace
+description: Follow a request end-to-end through the stack from route to database
+type: review
+version: v0.1
+---
+
+# Trace
+
+Invoke as `$trace`.
+
+Use this skill when the user wants to understand how a specific route, endpoint, or feature flows through the application stack.
+
+## Process
+
+1. Identify the entry point from the user's description.
+2. Read CLAUDE.md for architecture context.
+3. Trace forward through each layer: entry point → middleware → business logic → data access → response.
+4. Map the data flow and types at each boundary.
+5. Identify concerns: N+1 queries, auth gaps, type mismatches, performance issues.
+
+## Output
+
+- **Visual trace**: entry → middleware → handler → service → DB → response with file:line refs
+- **Layer-by-layer detail**: file, inputs, outputs, what it does
+- **Data flow**: how data transforms through the stack
+- **Concerns found**: issues identified during the trace
+
+## Constraints
+
+- Follow actual code paths — do not guess from naming.
+- Read each file in the chain.
+- Do not modify any code — read-only analysis.
+
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/code-debug/codex/trace/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Trace"
+  short_description: "Map request flow through the stack"
+  default_prompt: "Use $trace to trace the specified route or feature through the stack."
+
+policy:
+  allow_implicit_invocation: true