cfsa-antigravity 2.19.2 → 2.19.4

package/template/.claude/skills/database-schema-design/SKILL.md

@@ -21,7 +21,7 @@ Design scalable, well-structured database schemas with proper relationships, con
 
 ## Paradigm-Specific References
 
-After reading the methodology below, read the reference matching your surface's Databases column in the surface stack map (`.agent/instructions/tech-stack.md`):
+After reading the methodology below, read the reference matching your surface's Databases column in the surface stack map (`.claude/instructions/tech-stack.md`):
 
 | Paradigm | Reference | Example Stores |
 |----------|-----------|----------------|
@@ -147,7 +147,7 @@ Present and confirm the table with the user before proceeding to Sub-step B.
 
 ### Sub-step B — Registry-First Skill Search
 
-Before presenting any store options, read `.agent/skills/find-skills/SKILL.md` and run `npx skills find [query type or store name]` for each query type that appeared in the table.
+Before presenting any store options, read `.claude/skills/find-skills/SKILL.md` and run `npx skills find [query type or store name]` for each query type that appeared in the table.
 
 If the registry returns a skill, install it first. The bundled skill library is a fallback only.
 
@@ -198,7 +198,7 @@ For each cross-store entity, answer the following in order:
 
 ### Skill Instruction
 
-Read all database skills listed in the Databases column of the surface stack map (`.agent/instructions/tech-stack.md`) for advice on each store's transaction semantics and consistency guarantees before completing this step.
+Read all database skills listed in the Databases column of the surface stack map (`.claude/instructions/tech-stack.md`) for advice on each store's transaction semantics and consistency guarantees before completing this step.
 
 ### Output
 

package/template/.claude/skills/error-handling-patterns/SKILL.md

@@ -20,7 +20,7 @@ Build resilient applications with robust error handling strategies that graceful
 
 ## Stack-Specific References
 
-After reading the methodology below, read the reference matching your surface's Languages column in the surface stack map (`.agent/instructions/tech-stack.md`):
+After reading the methodology below, read the reference matching your surface's Languages column in the surface stack map (`.claude/instructions/tech-stack.md`):
 
 | Language | Reference |
 |----------|-----------|

package/template/.claude/skills/find-skills/SKILL.md

@@ -21,7 +21,7 @@ Use this skill when the user:
 
 ## When Called as a Workflow Fallback
 
-Workflows that load stack-specific skills may invoke this skill as a fallback when a required skill is not installed in `.agent/skills/` and has no matching entry in `.agent/skill-library/MANIFEST.md`. In this case:
+Workflows that load stack-specific skills may invoke this skill as a fallback when a required skill is not installed in `.claude/skills/` and has no matching entry in `.claude/skill-library/MANIFEST.md`. In this case:
 
 1. Use the `npx skills find [skill-name]` command to search the open agent skills ecosystem for a matching skill
 2. Present the top results to the user with install commands

package/template/.claude/skills/idea-extraction/SKILL.md

@@ -38,16 +38,16 @@ This skill writes directly to the `docs/plans/ideation/` folder using a **fracta
 **Key rules:**
 
 1. **Always folders.** Every domain, sub-domain, and even single-surface projects use folders — no flat files. One universal pattern, no exceptions.
-2. **Indexes at every level.** Template: `.agent/skills/prd-templates/references/fractal-node-index-template.md`
-3. **CX files at every level.** Template: `.agent/skills/prd-templates/references/fractal-cx-template.md`
-4. **Feature files are leaf nodes.** Template: `.agent/skills/prd-templates/references/fractal-feature-template.md`
+2. **Indexes at every level.** Template: `.claude/skills/prd-templates/references/fractal-node-index-template.md`
+3. **CX files at every level.** Template: `.claude/skills/prd-templates/references/fractal-cx-template.md`
+4. **Feature files are leaf nodes.** Template: `.claude/skills/prd-templates/references/fractal-feature-template.md`
 5. **Depth is reactive.** The structure grows during exploration — never pre-scaffolded beyond what's discovered.
 6. **Soft limit at 4 levels.** If creating a level 5+ node, pause and ask the user: "This is getting unusually deep — should I promote a parent to reduce nesting, or is this depth justified?"
 
 ### Super-Index
 
-The top-level `ideation-index.md` uses a different template: `.agent/skills/prd-templates/references/ideation-index-template.md`
-The top-level `ideation-cx.md` uses: `.agent/skills/prd-templates/references/ideation-crosscut-template.md`
+The top-level `ideation-index.md` uses a different template: `.claude/skills/prd-templates/references/ideation-index-template.md`
+The top-level `ideation-cx.md` uses: `.claude/skills/prd-templates/references/ideation-crosscut-template.md`
 
 ### Numbering Convention
 

package/template/.claude/skills/migration-management/SKILL.md

@@ -21,7 +21,7 @@ Implement robust database migration systems with version control, rollback capab
 
 ## Paradigm-Specific References
 
-After reading the methodology below, read the reference matching your surface's Databases column in the surface stack map (`.agent/instructions/tech-stack.md`):
+After reading the methodology below, read the reference matching your surface's Databases column in the surface stack map (`.claude/instructions/tech-stack.md`):
 
 | Paradigm | Reference | Example Stores |
 |----------|-----------|----------------|

package/template/.claude/skills/parallel-agents/SKILL.md

@@ -154,7 +154,7 @@ Enter parallel mode when the slice's tasks contain surface tags (`BE`, `FE`, `QA
 ### Dispatch Instructions
 
 1. **Untagged tasks first** — Contract/schema work runs sequentially by orchestrator (Phase 0) before any tagged dispatch.
-2. **QA-RED** — QA agent writes comprehensive failing tests for ALL acceptance criteria. Tests MUST fail. Read `.agent/skills/session-continuity/protocols/09-parallel-claim.md`. Every contract field and error type covered.
+2. **QA-RED** — QA agent writes comprehensive failing tests for ALL acceptance criteria. Tests MUST fail. Read `.claude/skills/session-continuity/protocols/09-parallel-claim.md`. Every contract field and error type covered.
 3. **BE + FE parallel** — Code against tests and contracts simultaneously. Annotate spec-gap decisions with `// DECISION: [what and why]`.
 4. **QA-GREEN** — Re-verify all tests pass, anti-cheat check, add integration tests.
 5. **Iterative loop rule** — If QA-GREEN fails → re-dispatch BE/FE → QA-GREEN again → repeat until all pass.
@@ -162,4 +162,4 @@ Enter parallel mode when the slice's tasks contain surface tags (`BE`, `FE`, `QA
 
 ### Progress Logging
 
-Log each dispatch phase to `.agent/progress/slices/phase-NN-slice-NN.md` under `## Dispatch Log`.
+Log each dispatch phase to `.claude/progress/slices/phase-NN-slice-NN.md` under `## Dispatch Log`.

package/template/.claude/skills/prd-templates/references/bootstrap-verification-protocol.md

@@ -8,7 +8,7 @@
 
 ### 1. Fire
 
-Read `.agent/workflows/bootstrap-agents.md` and execute with the provided key(s).
+Read `.claude/skills/workflows/workflow-bootstrap-agents.md` and execute with the provided key(s).
 
 ### 2. Verify
 
@@ -16,12 +16,12 @@ After bootstrap returns, verify that the target was actually filled:
 
 | Key Type | Where to Verify | How to Verify |
 |----------|----------------|---------------|
-| Language/Framework/DB/ORM | Surface stack map in `.agent/instructions/tech-stack.md` | The cell for the provided key's surface row is no longer empty |
+| Language/Framework/DB/ORM | Surface stack map in `.claude/instructions/tech-stack.md` | The cell for the provided key's surface row is no longer empty |
 | CI/CD, Hosting, Auth, Security | Cross-cutting section of surface stack map | The cell is no longer empty |
-| Design direction | `.agent/skills/brand-guidelines/SKILL.md` | `{{DESIGN_DIRECTION}}` no longer appears as literal text |
-| Project structure | `.agent/instructions/structure.md` | `{{PROJECT_STRUCTURE}}` no longer appears as literal text |
-| Dev tooling | `.agent/instructions/commands.md` | Template values are replaced with real commands |
-| New dependency skill | `.agent/skills/[skill-name]/SKILL.md` | The skill directory exists and `SKILL.md` is readable |
+| Design direction | `.claude/skills/brand-guidelines/SKILL.md` | `{{DESIGN_DIRECTION}}` no longer appears as literal text |
+| Project structure | `.claude/instructions/structure.md` | `{{PROJECT_STRUCTURE}}` no longer appears as literal text |
+| Dev tooling | `.claude/instructions/commands.md` | Template values are replaced with real commands |
+| New dependency skill | `.claude/skills/[skill-name]/SKILL.md` | The skill directory exists and `SKILL.md` is readable |
 
 ### 3. Hard Gate
 

package/template/.claude/skills/prd-templates/references/decision-confirmation-protocol.md

@@ -37,7 +37,7 @@ After confirmation, write the decision to the target file + section.
 
 ### 5. Verify Write
 
-Follow the write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`):
+Follow the write verification protocol (`.claude/skills/prd-templates/references/write-verification-protocol.md`):
 - Read back the target file
 - Verify the section header exists and content matches what was confirmed
 - If missing or mismatched → write failed, retry

package/template/.claude/skills/prd-templates/references/decision-propagation.md

@@ -6,11 +6,11 @@ Templates, formats, and scan procedures for `/propagate-decision` workflows.
 
 | Decision Type | Source Document | Downstream Scope |
 |--------------|-----------------|-------------------|
-| **structure** | `.agent/instructions/structure.md` | All IA shards, BE specs, FE specs |
-| **tech-stack** | `.agent/instructions/tech-stack.md` + architecture doc | All IA shards, BE specs, FE specs |
+| **structure** | `.claude/instructions/structure.md` | All IA shards, BE specs, FE specs |
+| **tech-stack** | `.claude/instructions/tech-stack.md` + architecture doc | All IA shards, BE specs, FE specs |
 | **auth-model** | Architecture doc (auth/security section) | All BE specs with middleware, all FE specs with auth flows |
 | **data-placement** | `docs/plans/data-placement-strategy.md` | All IA shards with data models, all BE specs with storage |
-| **patterns** | `.agent/instructions/patterns.md` | All IA shards, BE specs with implementation patterns, FE specs with component patterns |
+| **patterns** | `.claude/instructions/patterns.md` | All IA shards, BE specs with implementation patterns, FE specs with component patterns |
 | **error-architecture** | Architecture doc `## Error Architecture` (5 sub-sections) | All BE specs, all FE specs |
 
 ## Selection Menu Format

package/template/.claude/skills/prd-templates/references/engagement-tier-protocol.md

@@ -55,4 +55,4 @@ Not all decisions follow the engagement tier. Some are always user-facing regard
 | **Structural** | No — tier-aware | File naming, directory organization |
 | **Implementation** | No — agent decides | Import ordering, variable naming |
 
-See `.agent/rules/decision-classification.md` for the full classification.
+See `.claude/rules/decision-classification.md` for the full classification.

package/template/.claude/skills/prd-templates/references/evolution-layer-guidance.md

@@ -7,8 +7,8 @@ Reference for `/evolve-feature-classify` Step 4 and `/evolve-feature-cascade` St
 ### Ideation Layer (`docs/plans/ideation/`)
 
 1. **Placement**: Read `ideation-index.md` Structure Map. Identify the domain folder. Create new domain if needed.
-2. **Classification Gate**: Apply Node Classification Gate from `.agent/skills/idea-extraction/SKILL.md` — leaf feature or sub-domain folder.
-3. **Write**: Use `.agent/skills/prd-templates/references/fractal-feature-template.md`. Include:
+2. **Classification Gate**: Apply Node Classification Gate from `.claude/skills/idea-extraction/SKILL.md` — leaf feature or sub-domain folder.
+3. **Write**: Use `.claude/skills/prd-templates/references/fractal-feature-template.md`. Include:
    - Feature description (what and why)
    - Affected personas
    - Success criteria

package/template/.claude/skills/prd-templates/references/folder-seeding-protocol.md

@@ -33,11 +33,11 @@ For multi-product projects, additionally create `surfaces/` with sub-folders per
 
 Read these templates when creating files:
 
-- `.agent/skills/prd-templates/references/ideation-index-template.md` (super-index)
-- `.agent/skills/prd-templates/references/ideation-crosscut-template.md` (global CX)
-- `.agent/skills/prd-templates/references/fractal-node-index-template.md` (node index)
-- `.agent/skills/prd-templates/references/fractal-cx-template.md` (node CX)
-- `.agent/skills/prd-templates/references/fractal-feature-template.md` (feature file)
+- `.claude/skills/prd-templates/references/ideation-index-template.md` (super-index)
+- `.claude/skills/prd-templates/references/ideation-crosscut-template.md` (global CX)
+- `.claude/skills/prd-templates/references/fractal-node-index-template.md` (node index)
+- `.claude/skills/prd-templates/references/fractal-cx-template.md` (node CX)
+- `.claude/skills/prd-templates/references/fractal-feature-template.md` (feature file)
 
 ## Domain Seeding Rules
 

package/template/.claude/skills/prd-templates/references/input-classification.md

@@ -12,7 +12,7 @@ Classify user-provided input to determine which mode the `idea-extraction` skill
 
 ## Mode References
 
-Each mode's full process is defined in `.agent/skills/idea-extraction/SKILL.md`:
+Each mode's full process is defined in `.claude/skills/idea-extraction/SKILL.md`:
 
 - **Extraction Mode** → `## Input-Adaptive Modes → Extraction Mode — Rich Input`
 - **Expansion Mode** → `## Input-Adaptive Modes → Expansion Mode — Thin Input`

package/template/.claude/skills/prd-templates/references/map-guard-protocol.md

@@ -8,7 +8,7 @@
 
 ### 1. Read the Map
 
-Read the surface stack map from `.agent/instructions/tech-stack.md`.
+Read the surface stack map from `.claude/instructions/tech-stack.md`.
 
 ### 2. Check Required Cells
 
@@ -38,7 +38,7 @@ If the empty cells are auto-recoverable:
 
 1. **Read `docs/plans/architecture-draft.md`** — extract confirmed tech stack decisions (languages, frameworks, databases, ORMs, hosting, auth, CI/CD)
 2. **Build the bootstrap key set** from confirmed decisions
-3. **Execute `/bootstrap-agents`** with those keys — read `.agent/workflows/bootstrap-agents.md` and run BOTH shards (fill + provision)
+3. **Execute `/bootstrap-agents`** with those keys — read `.claude/skills/workflows/workflow-bootstrap-agents.md` and run BOTH shards (fill + provision)
 4. **Re-read the surface stack map** after bootstrap completes
 5. **Re-check the required cells** — if now filled → proceed. If still empty → escalate to hard stop (Step 5)
 

package/template/.claude/skills/prd-templates/references/persona-completeness-gate.md

@@ -17,4 +17,4 @@ Every persona must have all 6 fields populated before proceeding past persona ex
 
 If any field is absent for any persona → probe the user before proceeding.
 
-Reference: `.agent/skills/pipeline-rubrics/references/ideation-rubric.md` Dimension 2.
+Reference: `.claude/skills/pipeline-rubrics/references/ideation-rubric.md` Dimension 2.

package/template/.claude/skills/prd-templates/references/placeholder-workflow-mapping.md

@@ -2,7 +2,7 @@
 
 Maps surface stack map columns and cross-cutting categories to the workflows that consume them.
 
-> **How workflows use the map**: See `.agent/instructions/tech-stack.md` for the surface stack map format and resolution rules. Workflows determine their surface context (from shard directory or slice surface tag), then look up the corresponding row and column.
+> **How workflows use the map**: See `.claude/instructions/tech-stack.md` for the surface stack map format and resolution rules. Workflows determine their surface context (from shard directory or slice surface tag), then look up the corresponding row and column.
 
 ## Per-Surface Columns
 

package/template/.claude/skills/prd-templates/references/shard-boundary-analysis.md

@@ -73,7 +73,7 @@ Proposed split:
 Split rationale: [why these groups are independent]
 ```
 
-**After any split**: Update `docs/plans/ia/decomposition-plan.md` with the revised table, re-run the Must Have coverage gate, **then run `/remediate-shard-split` to update all downstream cross-references. Do NOT proceed until zero stale parent references remain.** See `.agent/skills/prd-templates/references/shard-split-remediation.md` for scan patterns and matching heuristics.
+**After any split**: Update `docs/plans/ia/decomposition-plan.md` with the revised table, re-run the Must Have coverage gate, **then run `/remediate-shard-split` to update all downstream cross-references. Do NOT proceed until zero stale parent references remain.** See `.claude/skills/prd-templates/references/shard-split-remediation.md` for scan patterns and matching heuristics.
 
 **Companion spec tracking**: When writing BE or FE specs for split shards, populate the `## Split Group` section in each spec file (see `be-spec-template.md` / `fe-spec-template.md`). This enables downstream discovery of sibling specs during implementation.
 

package/template/.claude/skills/prd-templates/references/skill-loading-protocol.md

@@ -6,16 +6,16 @@ Standard procedure for loading skills from the surface stack map before beginnin
 
 1. **Determine the surface**: Identify which surface this work belongs to from the directory path or phase plan (e.g., `docs/plans/be/web/` → surface `web`; flat `docs/plans/be/` → surface `shared`).
 
-2. **Read the surface stack map**: Open `.agent/instructions/tech-stack.md` and locate this surface's row.
+2. **Read the surface stack map**: Open `.claude/instructions/tech-stack.md` and locate this surface's row.
 
 3. **For each skill category** relevant to your workflow (Languages, Databases, BE Frameworks, FE Frameworks, FE Design, ORMs, Auth, Unit Tests, E2E Tests, State Mgmt, Accessibility, CI/CD, Hosting, Security):
    - Read the skill name(s) listed in that cell
-   - For each skill directory name, read `.agent/skills/[skill]/SKILL.md`
+   - For each skill directory name, read `.claude/skills/[skill]/SKILL.md`
    - Follow its conventions (language, testing, framework, design, etc.)
 
 4. **Cross-cutting skills**: Some categories (Auth, Security, CI/CD, Hosting, Accessibility) are in the cross-cutting section — not per-surface. Read those from the cross-cutting rows.
 
-5. **Missing skill fallback**: If any skill in the bundle is not installed in `.agent/skills/` and is not in `.agent/skill-library/MANIFEST.md`, read `.agent/skills/find-skills/SKILL.md` and follow its discovery methodology to search for a community equivalent before proceeding without it.
+5. **Missing skill fallback**: If any skill in the bundle is not installed in `.claude/skills/` and is not in `.claude/skill-library/MANIFEST.md`, read `.claude/skills/find-skills/SKILL.md` and follow its discovery methodology to search for a community equivalent before proceeding without it.
 
 ## Which Categories to Load Per Workflow
 

package/template/.claude/skills/prd-templates/references/spec-coverage-sweep.md

@@ -33,7 +33,7 @@ For each slice in the phase plan (`docs/plans/phases/phase-N.md`):
 
 If any flow, field, error code, auth rule, IA acceptance criterion, or accessibility requirement has no corresponding test:
 
-> ❌ STOP — Do not mark this phase as complete. List the uncovered items. Either write the missing tests and re-run the Test Cmd from `.agent/instructions/commands.md`, or if the item was genuinely deferred (valid boundary stub + tracking issue), document the deferral explicitly in the phase validation report.
+> ❌ STOP — Do not mark this phase as complete. List the uncovered items. Either write the missing tests and re-run the Test Cmd from `.claude/instructions/commands.md`, or if the item was genuinely deferred (valid boundary stub + tracking issue), document the deferral explicitly in the phase validation report.
 
 ## Pass Criteria
 

package/template/.claude/skills/prd-templates/references/workflow-checkpoint-protocol.md

@@ -13,7 +13,7 @@ The checkpoint is a markdown file with YAML-style key-value pairs. Agents must p
 ```markdown
 # Workflow Checkpoint
 
-active_shard: .agent/workflows/create-prd-stack.md
+active_shard: .claude/skills/workflows/workflow-create-prd-stack.md
 current_step: per-axis-flow
 current_item: Frontend Framework (STK-04)
 items_completed: [Hosting (STK-01), Database (STK-02), Auth (STK-03)]

package/template/.claude/skills/resolve-ambiguity/SKILL.md

@@ -38,10 +38,10 @@ Check sources in this order. **Stop as soon as you find authoritative informatio
 
 Look for project-specific context that may already answer the question:
 - `AGENTS.md` or `GEMINI.md` — Agent instructions, tech stack, validation commands
-- `.agent/instructions/tech-stack.md` — Technology decisions
-- `.agent/instructions/patterns.md` — Code conventions
-- `.agent/instructions/structure.md` — Directory layout
-- `.agent/instructions/commands.md` — Dev, test, lint, build
+- `.claude/instructions/tech-stack.md` — Technology decisions
+- `.claude/instructions/patterns.md` — Code conventions
+- `.claude/instructions/structure.md` — Directory layout
+- `.claude/instructions/commands.md` — Dev, test, lint, build
 
 If these files contain `{{PLACEHOLDER}}` values, the information hasn't been decided yet — move to the next tier.
 

package/template/.claude/skills/session-continuity/SKILL.md

@@ -2,7 +2,7 @@
 name: session-continuity
 description: >
   Cross-session progress tracking, pattern extraction, and session resumption.
-  Gives agents memory across sessions using markdown files in `.agent/progress/`.
+  Gives agents memory across sessions using markdown files in `.claude/progress/`.
   Subsumes self-improving-agent — handles both implementation tracking AND
   experiential learning in one skill. Workflows invoke specific protocols by name.
 triggers:
@@ -43,17 +43,17 @@ Workflows  = WHAT to do (ordered steps — invoke protocols by name)
 This Skill = HOW to do it (protocols — detailed step-by-step)
 ```
 
-Workflows say: "Read `.agent/skills/session-continuity/protocols/NN-protocol-name.md` and follow the **X Protocol**."
+Workflows say: "Read `.claude/skills/session-continuity/protocols/NN-protocol-name.md` and follow the **X Protocol**."
 This skill defines each protocol with exact steps, file formats, and rules.
 
 ---
 
 ## Directory Structure
 
-All progress state lives in `.agent/progress/`:
+All progress state lives in `.claude/progress/`:
 
 ```
-.agent/progress/
+.claude/progress/
 ├── index.md                      # Master checklist — phases + overall %
 ├── spec-pipeline.md              # Spec completion tracker (IA/BE/FE per shard)
 ├── phases/
@@ -91,7 +91,7 @@ for complex ones.
 
 ### Steps
 
-1. **Check if `.agent/progress/index.md` exists**
+1. **Check if `.claude/progress/index.md` exists**
    - If no: this is a fresh project with no tracked progress. Skip resumption.
    - If yes: continue.
 
@@ -460,7 +460,7 @@ have IA specs, BE specs, and FE specs completed.
 
 1. **Read the IA index** — `docs/plans/ia/index.md` — to get the list of shards.
 
-2. **Create `.agent/progress/spec-pipeline.md`**:
+2. **Create `.claude/progress/spec-pipeline.md`**:
    ```markdown
    # Spec Pipeline Progress
 

package/template/.claude/skills/session-continuity/protocols/01-session-resumption.md

@@ -1,4 +1,4 @@
-> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.agent/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
+> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.claude/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
 
 # Protocol 1: Session Resumption
 
@@ -10,7 +10,7 @@
 
 ## Steps
 
-1. **Check if `.agent/progress/index.md` exists**
+1. **Check if `.claude/progress/index.md` exists**
    - If no: this is a fresh project with no tracked progress. Skip resumption.
    - If yes: continue.
 

package/template/.claude/skills/session-continuity/protocols/02-progress-generation.md

@@ -1,4 +1,4 @@
-> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.agent/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
+> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.claude/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
 
 # Protocol 2: Progress Generation
 
@@ -12,7 +12,7 @@
 
 1. **Read the phase plan** that was just created (the output of `/plan-phase`).
 
-2. **Create or update `.agent/progress/index.md`**:
+2. **Create or update `.claude/progress/index.md`**:
    ```markdown
    # Implementation Progress
 
@@ -27,7 +27,7 @@
    | Phase 1: {{NAME}} | not-started | 0/{{N}} | [→](phases/phase-01.md) |
    ```
 
-3. **Create `.agent/progress/phases/phase-NN.md`**:
+3. **Create `.claude/progress/phases/phase-NN.md`**:
    ```markdown
    # Phase {{N}}: {{NAME}}
 
@@ -55,7 +55,7 @@
    - `files:` blocks are NOT written during generation — only during claim (Protocol 9)
    - Subtasks under tagged tasks inherit the parent's surface ownership
 
-4. **Create `.agent/progress/slices/phase-NN-slice-NN.md`** for each slice with ≥3 criteria:
+4. **Create `.claude/progress/slices/phase-NN-slice-NN.md`** for each slice with ≥3 criteria:
    ```markdown
    # Phase {{P}} / Slice {{S}}: {{NAME}}
 
@@ -80,6 +80,6 @@
    ```
 
 5. **Initialize memory files** (only if they don't already exist):
-   - `.agent/progress/memory/patterns.md` — empty with header
-   - `.agent/progress/memory/blockers.md` — empty with header
-   - `.agent/progress/memory/decisions.md` — empty with header
+   - `.claude/memory/patterns.md` — empty with header
+   - `.claude/memory/blockers.md` — empty with header
+   - `.claude/memory/decisions.md` — empty with header

package/template/.claude/skills/session-continuity/protocols/03-progress-update.md

@@ -1,4 +1,4 @@
-> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.agent/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
+> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.claude/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
 
 # Protocol 3: Progress Update
 
@@ -10,9 +10,9 @@
 
 ## Steps
 
-1. **Mark tasks and acceptance criteria `[x]`** in the slice's tracking location (use the exact files in the `.agent/progress/` directory, NEVER guess the path):
-   - If slice has its own file: update `.agent/progress/slices/phase-NN-slice-NN.md`
-   - If inline: update `.agent/progress/phases/phase-NN.md`
+1. **Mark tasks and acceptance criteria `[x]`** in the slice's tracking location (use the exact files in the `.claude/progress/` directory, NEVER guess the path):
+   - If slice has its own file: update `.claude/progress/slices/phase-NN-slice-NN.md`
+   - If inline: update `.claude/progress/phases/phase-NN.md`
 
 2. **Release any claimed tasks** — if the completed task had `[!]`:
    - Change status from `[/]` to `[x]`
@@ -42,7 +42,7 @@
    **Progress**: 4/7 slices
    ```
 
-5. **Update `.agent/progress/index.md`** — recalculate overall progress:
+5. **Update `.claude/progress/index.md`** — recalculate overall progress:
    ```markdown
    **Overall**: 12/20 slices (60%)
    ```

package/template/.claude/skills/session-continuity/protocols/04-pattern-extraction.md

@@ -1,4 +1,4 @@
-> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.agent/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
+> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.claude/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
 
 # Protocol 4: Pattern Extraction
 

package/template/.claude/skills/session-continuity/protocols/05-session-close.md

@@ -1,4 +1,4 @@
-> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.agent/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
+> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.claude/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
 
 # Protocol 5: Session Close
 

package/template/.claude/skills/session-continuity/protocols/06-decision-analysis.md

@@ -1,4 +1,4 @@
-> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.agent/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
+> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.claude/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
 
 # Protocol 6: Decision Effect Analysis
 

package/template/.claude/skills/session-continuity/protocols/07-spec-pipeline-generation.md

@@ -1,4 +1,4 @@
-> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.agent/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
+> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.claude/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
 
 # Protocol 7: Spec Pipeline Generation
 
@@ -13,7 +13,7 @@ have IA specs, BE specs, and FE specs completed.
 
 1. **Read the IA index** — `docs/plans/ia/index.md` — to get the list of shards.
 
-2. **Create `.agent/progress/spec-pipeline.md`**:
+2. **Create `.claude/progress/spec-pipeline.md`**:
    ```markdown
    # Spec Pipeline Progress
 

package/template/.claude/skills/session-continuity/protocols/08-spec-pipeline-update.md

@@ -1,4 +1,4 @@
-> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.agent/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
+> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.claude/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
 
 # Protocol 8: Spec Pipeline Update
 
@@ -14,7 +14,7 @@
 1. **Identify the shard and layer** — which shard just got its spec completed,
    and which layer (IA, BE, or FE)?
 
-2. **Update `.agent/progress/spec-pipeline.md`** — before updating any cell, perform these validation checks:
+2. **Update `.claude/progress/spec-pipeline.md`** — before updating any cell, perform these validation checks:
 
    (a) Read the `File` column for the shard from the tracker to get the expected file path.
    (b) Confirm the file exists at that path. If not → **skip the update** and report: `"Cannot mark [shard] [layer] as complete — file not found at [path]"`
@@ -44,7 +44,7 @@
 
 6. **Read-back verification** — immediately after updating the tracker:
 
-   (a) Read `.agent/progress/spec-pipeline.md` back.
+   (a) Read `.claude/progress/spec-pipeline.md` back.
    (b) Locate the row for the shard that was just updated.
    (c) Verify the column that was just marked shows `complete` (not `not-started`, not unchanged, not any other value).
    (d) If the cell does NOT show `complete`:

package/template/.claude/skills/session-continuity/protocols/09-parallel-claim.md

@@ -1,4 +1,4 @@
-> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.agent/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
+> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.claude/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
 
 # Protocol 9: Parallel Claim
 

package/template/.claude/skills/session-continuity/protocols/10-placeholder-verification-gate.md

@@ -4,7 +4,7 @@
 
 Specification and implementation workflows must verify the surface stack map is populated **before** any skill reads. This prevents spec authoring from running with empty map cells, which would produce patterns incompatible with the chosen tech stack.
 
-> **Note**: As of v3, workflows no longer use `{{PLACEHOLDER}}` values for skill paths. Instead, they read skill names from the surface stack map in `.agent/instructions/tech-stack.md`. This gate verifies map completeness.
+> **Note**: As of v3, workflows no longer use `{{PLACEHOLDER}}` values for skill paths. Instead, they read skill names from the surface stack map in `.claude/instructions/tech-stack.md`. This gate verifies map completeness.
 
 ## How to Apply
 
@@ -14,7 +14,7 @@ Add a **Step 0 — Map guard** to any specification or implementation workflow t
 
 ### 1. Read the surface stack map
 
-Read `.agent/instructions/tech-stack.md` and parse both tables:
+Read `.claude/instructions/tech-stack.md` and parse both tables:
 - **Per-Surface Skills** — One row per surface
 - **Cross-Cutting Skills** — Project-wide categories
 
@@ -80,4 +80,4 @@ This fallback **only** applies to workflows invoked within the `/create-prd` orc
 
 ## Commands verification
 
-Additionally verify that `.agent/instructions/commands.md` has non-template values. If the commands section still contains `{{COMMAND_SECTIONS}}`, run `/bootstrap-agents` to fill it.
+Additionally verify that `.claude/instructions/commands.md` has non-template values. If the commands section still contains `{{COMMAND_SECTIONS}}`, run `/bootstrap-agents` to fill it.

package/template/.claude/skills/session-continuity/protocols/11-parallel-synthesis.md

@@ -4,7 +4,7 @@ Run after all parallel agents have completed and QA-GREEN has passed.
 
 ## Pre-Synthesis Plan
 
-Before beginning any synthesis work, write a `## Synthesis Plan` section to the slice file (`.agent/progress/slices/phase-NN-slice-NN.md`) listing:
+Before beginning any synthesis work, write a `## Synthesis Plan` section to the slice file (`.claude/progress/slices/phase-NN-slice-NN.md`) listing:
 - All `// BOUNDARY:` stubs found across agent outputs (file path + stub description)
 - All cross-surface integrations to wire (e.g., "BE auth middleware → FE token refresh handler")
 
@@ -17,5 +17,5 @@ This gives you a checklist to resume from if the session is interrupted during s
    - Update shared contracts if needed
    - Install any new dependencies
    - Wire cross-surface integrations
-3. **Run full validation** — run the Validation Cmd from `.agent/instructions/commands.md` after synthesis
+3. **Run full validation** — run the Validation Cmd from `.claude/instructions/commands.md` after synthesis
 4. **Create synthesis report** per the `parallel-agents` skill (Synthesize step)

package/template/.claude/skills/session-continuity/protocols/ambiguity-gates.md

@@ -1,4 +1,4 @@
-> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.agent/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
+> **Framework context required**: This is a protocol excerpt. Before following these steps, read `.claude/skills/session-continuity/SKILL.md` for the complete framework — including the Adaptive Granularity Rule, Level Hierarchy Reference, Frozen Files concept, and Parallel Claim protocol. Protocol files are reference documents for specific steps, not standalone instructions.
 
 # Ambiguity Gates (Micro + Macro)
 

package/template/.claude/skills/setup/setup-provision-skills.md

@@ -14,7 +14,7 @@ parameters:
 
 ## Overview
 
-This skill provisions Claude Code skills from `.claude/skill-library/` (shared via symlink to `.agent/skill-library/`) based on `.claude/instructions/tech-stack.md`.
+This skill provisions Claude Code skills from `.claude/skill-library/` (shared via symlink to `.claude/skill-library/`) based on `.claude/instructions/tech-stack.md`.
 
 Equivalent to Antigravity's `bootstrap-agents-provision.md` shard.