cfsa-antigravity 3.0.2 → 3.1.0

package/README.md

@@ -35,7 +35,8 @@ npx cfsa-antigravity init --agent claude,factory
 
 Runtimes are auto-detected from the template. Currently shipped:
 
-- **Antigravity** (`.agent/`) -- Antigravity, Cursor, Codex, Gemini CLI
+- **Antigravity** (`.agent/`) -- Antigravity, Cursor, Gemini CLI
+- **Codex** (`.codex/`) -- Standalone Codex runtime
 - **Claude Code** (`.claude/`) -- Standalone Claude Code runtime
 - **Factory Droid** (`.factory/`) -- Standalone Factory Droid runtime
 
@@ -57,7 +58,11 @@ Every install now scaffolds a shared `.memory/` root at the project level. It is
 └── migrate/     # legacy memory import helpers
 ```
 
-The installer ships the shared memory runtime into `.memory/`, including the project-local MCP server under `.memory/mcp-server/`. Tool-specific MCP client config is intentionally **not** managed by the kit — users wire their own `.mcp.json` / editor settings for the tools they actually use. The daemon writes runtime state into `.memory/runtime/`, and the semantic index writes retrieval artifacts into `.memory/schema/semantic-index.json` plus `.memory/schema/semantic-manifest.json`.
+The installer ships the shared memory runtime into `.memory/`, including the project-local MCP server under `.memory/mcp-server/`. Tool-specific MCP client config is intentionally **not** managed by the kit — users wire their own `.mcp.json` / editor settings for the tools they actually use. The daemon writes workspace-local runtime state into `.memory/runtime/`, and clients resolve that state before proxying requests so one workspace does not silently talk to another workspace's daemon. The semantic index writes retrieval artifacts into `.memory/schema/semantic-index.json` plus `.memory/schema/semantic-manifest.json`.
+
+The practical contract is: point your tool at `.memory/mcp-server/client.mjs`, start the daemon for that workspace, and let the client discover the correct local daemon from `.memory/runtime/cfsa-memory-daemon.json`.
+
+If the daemon health payload reports a different `projectRoot` than the client expects, the client now fails loudly instead of proxying requests to the wrong workspace.
 
 ### MCP client setup and first graph compile
 
@@ -65,6 +70,21 @@ The kit installs the **server/runtime** only. You must configure your tool's MCP
 
 For tools that use a workspace `.mcp.json`, point the tool at the shared server entrypoint:
 
+```json
+{
+  "mcpServers": {
+    "cfsa-memory": {
+      "command": "node",
+      "args": [".memory/mcp-server/client.mjs"]
+    }
+  }
+}
+```
+
+This is the preferred default because the client resolves the correct workspace-local daemon from `.memory/runtime/cfsa-memory-daemon.json`.
+
+If you need a custom host/port, use env overrides:
+
 ```json
 {
   "mcpServers": {
@@ -72,18 +92,15 @@ For tools that use a workspace `.mcp.json`, point the tool at the shared server
       "command": "node",
       "args": [".memory/mcp-server/client.mjs"],
       "env": {
-        "MEMORY_ROOT": ".memory",
         "CFSA_MEMORY_HOST": "127.0.0.1",
-        "CFSA_MEMORY_PORT": "4317",
-        "CFSA_MEMORY_URL": "http://127.0.0.1:4317/mcp",
-        "CFSA_MEMORY_HEALTH_URL": "http://127.0.0.1:4317/health"
+        "CFSA_MEMORY_PORT": "4317"
       }
     }
   }
 }
 ```
 
-For an existing project, after wiring your MCP client, trigger the initial graph/index build by running the memory compile path (`memory_compile` via MCP, or the direct compile script fallback) before opening Obsidian. Verify files like `.memory/schema/spec-graph.json` and `.memory/wiki/hubs/spec-graph.md` exist, then open Obsidian at `.memory/`.
+For an existing project, after wiring your MCP client, start the workspace-local daemon so it writes `.memory/runtime/cfsa-memory-daemon.json`, then trigger the initial graph/index build by running the memory compile path (`memory_compile` via MCP, or the direct compile script fallback) before opening Obsidian. Verify files like `.memory/schema/spec-graph.json` and `.memory/wiki/hubs/spec-graph.md` exist, then open Obsidian at `.memory/`.
 
 This replaces fragmented runtime-local memory as the canonical project memory layer. Runtime-local memory files remain legacy inputs for migration.
 
@@ -94,7 +111,7 @@ Keep the installed runtime directory out of shared `.gitignore` rules when your
 
 Examples:
 1. Antigravity install → keep `.agent/` out of `.gitignore`
-2. Codex install → keep `.agent/` out of `.gitignore`
+2. Codex install → keep `.codex/` out of `.gitignore`
 3. Claude install → keep `.claude/` out of `.gitignore`
 4. Factory install → keep `.factory/` out of `.gitignore`
 5. Use `.git/info/exclude` for local exclusions instead of changing shared ignore rules
@@ -118,13 +135,13 @@ The kit evolves independently of your project. To pull improvements into an exis
 This performs a **semantic merge** — it applies new workflows, skills, and rules from the upstream kit while preserving your project-specific values (tech stack, validation commands, filled placeholders). It will never overwrite your project decisions.
 
 - First sync does a full comparison; subsequent syncs are incremental (commit-scoped)
-- Tracks sync state in the installed agent runtime (`.agent/kit-sync.md`, `.claude/kit-sync.md`, or `.factory/kit-sync.md`) so it knows what changed since last update
+- Tracks sync state in the installed agent runtime (`.agent/kit-sync.md`, `.codex/kit-sync.md`, `.claude/kit-sync.md`, or `.factory/kit-sync.md`) so it knows what changed since last update
 - Flags any structural migrations needed (e.g., ideation format changes)
 
 ## What Init Adds
 
 A fresh `init` now installs:
-- your selected runtime directories (`.agent/`, `.claude/`, `.factory/`)
+- your selected runtime directories (`.agent/`, `.codex/`, `.claude/`, `.factory/`)
 - `docs/`
 - shared `.memory/`
 - the shared memory MCP server/runtime under `.memory/mcp-server/`

package/bin/cli.mjs

@@ -35,7 +35,8 @@ const error = (msg) => { console.error(`${c.red}✗${c.reset} ${msg}`); };
 
 // --- Runtime display names (fallback to directory name for unknown runtimes) ---
 const RUNTIME_DISPLAY = {
-    ".agent":   { name: "Antigravity",   desc: "Antigravity, Cursor, Codex, Gemini CLI" },
+    ".agent":   { name: "Antigravity",   desc: "Antigravity, Cursor, Gemini CLI" },
+    ".codex":   { name: "Codex",         desc: "Standalone Codex runtime" },
     ".claude":  { name: "Claude Code",   desc: "Standalone Claude Code runtime" },
     ".factory": { name: "Factory Droid", desc: "Standalone Factory Droid runtime" },
 };
@@ -206,10 +207,10 @@ ${c.bold}Examples:${c.reset}
   npx cfsa-antigravity init
 
   ${c.dim}# Non-interactive — install specific runtimes${c.reset}
-  npx cfsa-antigravity init --agent claude,factory
+  npx cfsa-antigravity init --agent codex,claude
 
   ${c.dim}# Install a single runtime${c.reset}
-  npx cfsa-antigravity init --agent factory
+  npx cfsa-antigravity init --agent codex
 
   ${c.dim}# Install into a specific directory${c.reset}
   npx cfsa-antigravity init --agent claude --path ./my-project
@@ -326,7 +327,7 @@ function ensureTemplateDir() {
 function resolveAgentNames(agentNames, available) {
     const resolved = [];
     for (const name of agentNames) {
-        // Try exact dir match first (.agent, .claude, .factory)
+        // Try exact dir match first (.agent, .codex, .claude, .factory)
         const dotName = name.startsWith(".") ? name : `.${name}`;
         const match = available.find(r => r.dir === dotName);
         if (match) {
@@ -339,8 +340,8 @@ function resolveAgentNames(agentNames, available) {
             resolved.push(byName);
             continue;
         }
-        // Legacy single-agent names: "antigravity" / "codex" → .agent
-        if (name === "antigravity" || name === "codex") {
+        // Legacy single-agent name: "antigravity" → .agent
+        if (name === "antigravity") {
             const agentRt = available.find(r => r.dir === ".agent");
             if (agentRt && !resolved.find(r => r.dir === ".agent")) {
                 resolved.push(agentRt);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cfsa-antigravity",
-  "version": "3.0.2",
+  "version": "3.1.0",
   "description": "CFSA Pipeline — Constraint-First Specification Architecture for AI agents. Production-grade from line one.",
   "scripts": {
     "changeset": "changeset",

package/template/.agent/PRDS/codex-runtime-support.md

@@ -39,7 +39,7 @@ Make Codex a documented, installable, maintainable runtime on par with the exist
 ### Runtime support
 
 - Codex must be a first-class install target
-- Codex support may reuse the shared `.agent/` runtime instead of introducing a fully separate runtime tree
+- Codex support must ship a standalone `.codex/` runtime tree so Codex can discover workflow skills and runtime assets in its native project directory
 - A dedicated `CODEX.md` guidance file must exist in source and template output
 
 ### CLI support
@@ -70,7 +70,7 @@ Make Codex a documented, installable, maintainable runtime on par with the exist
 
 Prefer a surgical extension of the current runtime model:
 
-1. Reuse the shared `.agent/` runtime for Codex rather than maintaining a redundant fork
+1. Adapt the standalone skill-based runtime shape for Codex under `.codex/`
 2. Add a Codex-specific root guidance file for parity and discoverability
 3. Add an explicit installer/status path for Codex
 4. Update source-of-truth docs first, then CLI/build logic, then published template expectations

package/template/.agent/TASKS/codex-runtime-support.md

@@ -4,8 +4,8 @@
 **Label:** CFSA Antigravity: Codex Runtime Support
 **Description:** Add Codex as a first-class supported agent runtime with installable runtime assets, documentation, and status detection.
 **Type:** Feature
-**Status:** Backlog
+**Status:** Done
 **Priority:** High
 **Created:** 2026-04-10
-**Updated:** 2026-04-10
+**Updated:** 2026-05-03
 **PRD:** [Codex Runtime Support](../PRDS/codex-runtime-support.md)

package/template/.agent/instructions/workflow.md

@@ -6,7 +6,7 @@ Before taking any action on a task:
 - Read the agent config file at project root (`AGENTS.md` for Antigravity, `GEMINI.md` for Gemini CLI, or equivalent for your agent)
 - Read relevant `.agent/instructions/` files for the task type
 - Check [Engineering Standards](../../.memory/wiki/specs/ENGINEERING-STANDARDS.md) for quality bar — if this file doesn't exist yet, the pipeline hasn't reached /create-prd; run /ideate then /create-prd first
-- **Session Resumption**: If `.agent/progress/index.md` exists, read `.agent/skills/session-continuity/protocols/01-session-resumption.md` and follow the **Session Resumption Protocol** to load cross-session context and identify the resumption point
+- **Session Resumption**: If `.memory/pipeline/progress/index.md` exists, read `.agent/skills/session-continuity/protocols/01-session-resumption.md` and follow the **Session Resumption Protocol** to load cross-session context and identify the resumption point
 
 ## 2. Check Skills
 - Scan `.agent/skills/` for applicable skills
@@ -38,7 +38,7 @@ Do NOT mark a task complete until all validations pass.
 After completing a workflow or substantial task:
 
 - **Pattern Extraction**: Read `.agent/skills/session-continuity/protocols/04-pattern-extraction.md` and follow the **Pattern Extraction Protocol**. Reflect on what worked, what didn't, and log reusable patterns to `.memory/wiki/patterns.md`. Skip only if the task was trivial (routine, nothing new learned).
-- **Session Close**: Read `.agent/skills/session-continuity/protocols/05-session-close.md` and follow the **Session Close Protocol**. Write a session log to `.agent/progress/sessions/` so the next session can resume cleanly.
+- **Session Close**: Read `.agent/skills/session-continuity/protocols/05-session-close.md` and follow the **Session Close Protocol**. Write a session log to `.memory/pipeline/progress/sessions/` so the next session can resume cleanly.
 - **Unified Memory First**: Treat `.memory/` as the canonical project memory root. When shared memory is needed, prefer the `cfsa-memory` MCP bridge over runtime-local silos so all runtimes see the same memory.
 
 > These steps are **not optional**. They are what differentiate a pipeline that gets
@@ -47,7 +47,7 @@ After completing a workflow or substantial task:
 ## 6. Recommend Next Step (MANDATORY)
 
 Before reporting completion via `notify_user`:
-- Check the pipeline progress state (`.agent/progress/spec-pipeline.md` or equivalent)
+- Check the pipeline progress state (`.memory/pipeline/progress/spec-pipeline.md` or equivalent)
 - Propose the next valid pipeline command to the user
 - If multiple valid next steps exist, list them with brief context
 - Never end a conversation without telling the user what to do next

package/template/.agent/kit-sync.md

@@ -1,6 +1,6 @@
 # Kit Sync State
 
 upstream: https://github.com/RepairYourTech/cfsa-antigravity
-last_synced_commit: 63c31d9113ccb3f828aeb5c8a4902483cbbc2e8a
-last_synced_at: 2026-04-15T09:10:27Z
-kit_version: 3.0.2
+last_synced_commit: 41065b8165f7ea05b56a48f029eabcca52aa3049
+last_synced_at: 2026-05-03T19:45:21Z
+kit_version: 3.1.0

package/template/.agent/rules/completion-checklist.md

@@ -31,7 +31,7 @@ A unit of work is only DONE when:
 
 1. **The Code**: Implementation meets the contract and acceptance criteria.
 2. **The Tests**: All tests pass (validation step is green).
-3. **The Tracking**: Progress markdown files in `.agent/progress/` are updated.
+3. **The Tracking**: Progress markdown files in `.memory/pipeline/progress/` are updated.
    - Acceptance criteria marked `[x]`
    - Slice/Task marked `[x]`
    - Phase progress fractions updated (e.g., `3/10` → `4/10`)
@@ -42,10 +42,10 @@ A unit of work is only DONE when:
    - `decisions.md` — Any non-trivial decisions logged per Protocol 06
    - `blockers.md` — Any blockers hit logged with status and impact
    - See rule: `memory-capture` for triggers and format
-6. **The Session Log**: A session close log exists in `.agent/progress/sessions/`.
+6. **The Session Log**: A session close log exists in `.memory/pipeline/progress/sessions/`.
    - Follow `.agent/skills/session-continuity/protocols/05-session-close.md` — write what was accomplished, deferred, and where the next session should start
 7. **The Next Step**: The user is told what comes next in the pipeline.
-   - Read the pipeline progress file (`.agent/progress/spec-pipeline.md` or equivalent)
+   - Read the pipeline progress file (`.memory/pipeline/progress/spec-pipeline.md` or equivalent)
    - Propose the next valid pipeline command based on current state
    - If multiple options exist, present them as a numbered list with brief context
    - If the pipeline stage is complete, say so explicitly

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

@@ -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 `.memory/pipeline/progress/slices/phase-NN-slice-NN.md` under `## Dispatch Log`.

package/template/.agent/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 `.memory/pipeline/progress/`.
   Subsumes self-improving-agent — handles both implementation tracking AND
   experiential learning in one skill. Workflows invoke specific protocols by name.
 triggers:
@@ -24,7 +24,7 @@ Without this skill, agents lose all context between sessions. Work restarts from
 scratch, implementations drift without spec accountability, and hard-won patterns
 evaporate. This skill fixes that with five protocols that workflows invoke by name.
 
-Runtime progress remains local to `.agent/progress/`, but canonical cross-runtime memory now lives in `.memory/` and should be read/written through the shared memory files or the `cfsa-memory` MCP bridge.
+Progress state is shared at `.memory/pipeline/progress/`. Cross-runtime memory lives in `.memory/wiki/` and should be read/written through the shared memory files or the `cfsa-memory` MCP bridge.
 
 ### What This Skill Does
 
@@ -52,10 +52,10 @@ 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 `.memory/pipeline/progress/`:
 
 ```
-.agent/progress/
+.memory/pipeline/progress/
 ├── index.md                      # Master checklist — phases + overall %
 ├── spec-pipeline.md              # Spec completion tracker (IA/BE/FE per shard)
 ├── phases/
@@ -93,7 +93,7 @@ for complex ones.
 
 ### Steps
 
-1. **Check if `.agent/progress/index.md` exists**
+1. **Check if `.memory/pipeline/progress/index.md` exists**
    - If no: this is a fresh project with no tracked progress. Skip resumption.
    - If yes: continue.
 
@@ -462,7 +462,7 @@ have IA specs, BE specs, and FE specs completed.
 
 1. **Read the IA index** — `.memory/wiki/specs/ia/index.md` — to get the list of shards.
 
-2. **Create `.agent/progress/spec-pipeline.md`**:
+2. **Create `.memory/pipeline/progress/spec-pipeline.md`**:
    ```markdown
    # Spec Pipeline Progress
 

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

@@ -10,7 +10,7 @@
 
 ## Steps
 
-1. **Check if `.agent/progress/index.md` exists**
+1. **Check if `.memory/pipeline/progress/index.md` exists**
    - If no: this is a fresh project with no tracked progress. Skip resumption.
    - If yes: continue.
 

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

@@ -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 `.memory/pipeline/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 `.memory/pipeline/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 `.memory/pipeline/progress/slices/phase-NN-slice-NN.md`** for each slice with ≥3 criteria:
    ```markdown
    # Phase {{P}} / Slice {{S}}: {{NAME}}
 

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

@@ -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 `.memory/pipeline/progress/` directory, NEVER guess the path):
+   - If slice has its own file: update `.memory/pipeline/progress/slices/phase-NN-slice-NN.md`
+   - If inline: update `.memory/pipeline/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 `.memory/pipeline/progress/index.md`** — recalculate overall progress:
    ```markdown
    **Overall**: 12/20 slices (60%)
    ```

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

@@ -13,7 +13,7 @@ have IA specs, BE specs, and FE specs completed.
 
 1. **Read the IA index** — `.memory/wiki/specs/ia/index.md` — to get the list of shards.
 
-2. **Create `.agent/progress/spec-pipeline.md`**:
+2. **Create `.memory/pipeline/progress/spec-pipeline.md`**:
    ```markdown
    # Spec Pipeline Progress
 

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

@@ -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 `.memory/pipeline/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 `.memory/pipeline/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/.agent/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 (`.memory/pipeline/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")
 

package/template/.agent/workflows/create-prd-architecture.md

@@ -150,8 +150,8 @@ Before reporting completion or proceeding to next shard:
 
 1. **Update checkpoint** — Write final state to `.memory/wiki/specs/architecture/prd-working/workflow-state.md`: mark all architecture sections complete.
 2. **Memory check** — Apply rule `memory-capture`. Write patterns, decisions, or blockers to `.memory/wiki/`. Architecture decisions have highest downstream impact — every confirmed decision should have a `DEC-NNN` entry.
-3. **Progress update** — Update `.agent/progress/` tracking files if they exist.
-4. **Session log** — Write session entry to `.agent/progress/sessions/`.
+3. **Progress update** — Update `.memory/pipeline/progress/` tracking files if they exist.
+4. **Session log** — Write session entry to `.memory/pipeline/progress/sessions/`.
 
 ---
 

package/template/.agent/workflows/create-prd-design-system.md

@@ -161,8 +161,8 @@ Before reporting completion or proceeding to next shard:
 
 1. **Update checkpoint** — Write final state to `.memory/wiki/specs/architecture/prd-working/workflow-state.md`: mark all 7 decisions complete, set `current_step: completion`.
 2. **Memory check** — Apply rule `memory-capture`. Write patterns, decisions, or blockers to `.memory/wiki/`. All 7 design system decisions should have `DEC-NNN` entries. If nothing to write, confirm: "No new patterns/decisions/blockers."
-3. **Progress update** — Update `.agent/progress/` tracking files if they exist.
-4. **Session log** — Write session entry to `.agent/progress/sessions/`.
+3. **Progress update** — Update `.memory/pipeline/progress/` tracking files if they exist.
+4. **Session log** — Write session entry to `.memory/pipeline/progress/sessions/`.
 
 ---
 

package/template/.agent/workflows/create-prd-security.md

@@ -143,8 +143,8 @@ Before reporting completion or proceeding to next shard:
 
 1. **Update checkpoint** — Write final state to `.memory/wiki/specs/architecture/prd-working/workflow-state.md`: mark all security sections complete.
 2. **Memory check** — Apply rule `memory-capture`. Write patterns, decisions, or blockers to `.memory/wiki/`. Security model decisions are high-impact — every confirmed decision should have `DEC-NNN` entry.
-3. **Progress update** — Update `.agent/progress/` tracking files if they exist.
-4. **Session log** — Write session entry to `.agent/progress/sessions/`.
+3. **Progress update** — Update `.memory/pipeline/progress/` tracking files if they exist.
+4. **Session log** — Write session entry to `.memory/pipeline/progress/sessions/`.
 
 ---
 

package/template/.agent/workflows/create-prd-stack.md

@@ -135,8 +135,8 @@ Read `.agent/workflows/bootstrap-agents.md` and call it with `PIPELINE_STAGE=cre
 Before reporting completion or proceeding to next shard:
 
 1. **Memory check** — Apply rule `memory-capture`. Write any patterns, decisions, or blockers from this shard to `.memory/wiki/`. Tech stack decisions are high-impact — every confirmed decision should have a `DEC-NNN` entry. If nothing to write, confirm: "No new patterns/decisions/blockers."
-2. **Progress update** — Update `.agent/progress/` tracking files if they exist.
-3. **Session log** — Write session entry to `.agent/progress/sessions/`.
+2. **Progress update** — Update `.memory/pipeline/progress/` files if they exist.
+3. **Session log** — Write session to `.memory/pipeline/progress/sessions/`.
 
 ---
 

package/template/.agent/workflows/create-prd.md

@@ -145,6 +145,6 @@ Use `notify_user` to present both documents with self-check results.
 Before reporting completion to the user:
 
 1. **Memory check** — Apply rule `memory-capture`. Write any patterns, decisions, or blockers from this workflow to `.memory/wiki/`. If nothing to write, confirm: "No new patterns/decisions/blockers."
-2. **Progress update** — Update `.agent/progress/` tracking files if they exist.
-3. **Session log** — Write session entry to `.agent/progress/sessions/`.
+2. **Progress update** — Update `.memory/pipeline/progress/` tracking files if they exist.
+3. **Session log** — Write session entry to `.memory/pipeline/progress/sessions/`.
 

package/template/.agent/workflows/decompose-architecture-validate.md

@@ -100,4 +100,4 @@ Use `notify_user` to present: IA directory, BE index, FE index, master index, sp
 
 ### Next step
 
-**STOP** — do NOT proceed to any other workflow. The only valid next step is `/write-architecture-spec` starting with the lowest-numbered shard per `.agent/progress/spec-pipeline.md`.
+**STOP** — do NOT proceed to any other workflow. The only valid next step is `/write-architecture-spec` starting with the lowest-numbered shard per `.memory/pipeline/progress/spec-pipeline.md`.

package/template/.agent/workflows/decompose-architecture.md

@@ -97,6 +97,6 @@ Present the proposed domain decomposition to the user for validation.
 Before reporting completion to the user:
 
 1. **Memory check** — Apply rule `memory-capture`. Write any patterns, decisions, or blockers from this workflow to `.memory/wiki/`. If nothing to write, confirm: "No new patterns/decisions/blockers."
-2. **Progress update** — Update `.agent/progress/` tracking files if they exist.
-3. **Session log** — Write session entry to `.agent/progress/sessions/`.
+2. **Progress update** — Update `.memory/pipeline/progress/` tracking files if they exist.
+3. **Session log** — Write session entry to `.memory/pipeline/progress/sessions/`.
 

package/template/.agent/workflows/ideate.md

@@ -132,6 +132,6 @@ Explores constraints, success metrics, and competitive positioning. Runs leaf-no
 Before reporting completion to the user:
 
 1. **Memory check** — Apply rule `memory-capture`. Write any patterns, decisions, or blockers from this workflow to `.memory/wiki/`. If nothing to write, confirm: "No new patterns/decisions/blockers."
-2. **Progress update** — Update `.agent/progress/` tracking files if they exist.
-3. **Session log** — Write session entry to `.agent/progress/sessions/`.
+2. **Progress update** — Update `.memory/pipeline/progress/` tracking files if they exist.
+3. **Session log** — Write session entry to `.memory/pipeline/progress/sessions/`.
 

package/template/.agent/workflows/implement-slice-setup.md

@@ -113,7 +113,7 @@ Read `.agent/skills/parallel-agents/SKILL.md` and `.agent/skills/parallel-featur
 
 Read `.agent/skills/parallel-agents/SKILL.md` and follow its TDD-Order Dispatch methodology for execution order and file isolation.
 
-Log each dispatch phase to `.agent/progress/slices/phase-NN-slice-NN.md` `## Dispatch Log`.
+Log each dispatch phase to `.memory/pipeline/progress/slices/phase-NN-slice-NN.md` `## Dispatch Log`.
 
 ---
 

package/template/.agent/workflows/implement-slice-tdd.md

@@ -166,9 +166,9 @@ Read `.agent/skills/prd-templates/references/tdd-testing-policy.md` and run the
 You may not call `notify_user` until you have edited all four progress file targets (7a–7d).
 
 Verify your edits by reading:
-- `.agent/progress/slices/phase-NN-slice-NN.md` — Status: complete, [x] criteria
-- `.agent/progress/phases/phase-NN.md` — incremented progress fraction
-- `.agent/progress/index.md` — updated overall percentage
+- `.memory/pipeline/progress/slices/phase-NN-slice-NN.md` — Status: complete, [x] criteria
+- `.memory/pipeline/progress/phases/phase-NN.md` — incremented progress fraction
+- `.memory/pipeline/progress/index.md` — updated overall percentage
 
 Your `notify_user` payload **MUST** include:
 1. Raw output from the three reads above

package/template/.agent/workflows/implement-slice.md

@@ -56,5 +56,5 @@ Executes the TDD cycle (RED: write failing tests → GREEN: implement → REFACT
 Before reporting completion to the user:
 
 1. **Memory check** — Apply rule `memory-capture`. Write any patterns, decisions, or blockers from this workflow to `.memory/wiki/`. If nothing to write, confirm: "No new patterns/decisions/blockers."
-2. **Progress update** — Update `.agent/progress/` tracking files if they exist.
-3. **Session log** — Write session entry to `.agent/progress/sessions/`.
+2. **Progress update** — Update `.memory/pipeline/progress/` tracking files if they exist.
+3. **Session log** — Write session entry to `.memory/pipeline/progress/sessions/`.

package/template/.agent/workflows/plan-phase-preflight.md

@@ -25,10 +25,10 @@ Pre-flight checks before slice planning: phase sequencing, skill loading, comple
 
 ## 0. Phase sequencing gate
 
-Read `.agent/progress/index.md` to identify the current phase number N.
+Read `.memory/pipeline/progress/index.md` to identify the current phase number N.
 
 - **If N = 1** → this is the first phase. Skip this gate.
-- **If N > 1** → read `.agent/progress/phases/phase-[N-1].md` and verify its status is `complete` with a passing `/validate-phase`. **Hard stop** if the previous phase is not complete: "Phase [N-1] must be complete with a passing `/validate-phase` before planning Phase [N]. Run `/validate-phase` for Phase [N-1] first."
+- **If N > 1** → read `.memory/pipeline/progress/phases/phase-[N-1].md` and verify its status is `complete` with a passing `/validate-phase`. **Hard stop** if the previous phase is not complete: "Phase [N-1] must be complete with a passing `/validate-phase` before planning Phase [N]. Run `/validate-phase` for Phase [N-1] first."
 
   **Architecture map freshness check (N > 1 only)** — warning, not a hard stop.
 

package/template/.agent/workflows/plan-phase-write.md

@@ -139,7 +139,7 @@ Read `.memory/wiki/specs/phases/phase-N-draft.md` (which was built progressively
 
 ## 6. Generate progress files
 
-Read `.agent/skills/session-continuity/protocols/02-progress-generation.md` and follow the **Progress Generation Protocol** to create tracking files for this phase in `.agent/progress/`.
+Read `.agent/skills/session-continuity/protocols/02-progress-generation.md` and follow the **Progress Generation Protocol** to create tracking files for this phase in `.memory/pipeline/progress/`.
 
 ## 6.5. Bootstrap Completeness Gate
 
@@ -157,4 +157,4 @@ Read the surface stack map from `.agent/instructions/tech-stack.md`. Verify all
 2. Verify the compile succeeded before presenting completion.
 3. Use `notify_user` to request review of the phase plan and generated progress files, including graph refresh confirmation.
 
-**STOP** — do NOT proceed until the user explicitly approves the phase plan. The only valid next step after approval is `/implement-slice` for the first slice. Read `.agent/progress/` to identify which slice to start with.
+**STOP** — do NOT proceed until the user explicitly approves the phase plan. The only valid next step after approval is `/implement-slice` for the first slice. Read `.memory/pipeline/progress/` to identify which slice to start with.

package/template/.agent/workflows/plan-phase.md

@@ -49,6 +49,6 @@ Run `.agent/workflows/plan-phase-write.md`.
 Before reporting completion to the user:
 
 1. **Memory check** — Apply rule `memory-capture`. Write any patterns, decisions, or blockers from this workflow to `.memory/wiki/`. If nothing to write, confirm: "No new patterns/decisions/blockers."
-2. **Progress update** — Update `.agent/progress/` tracking files if they exist.
-3. **Session log** — Write session entry to `.agent/progress/sessions/`.
+2. **Progress update** — Update `.memory/pipeline/progress/` tracking files if they exist.
+3. **Session log** — Write session entry to `.memory/pipeline/progress/sessions/`.
 

package/template/.agent/workflows/setup-workspace.md

@@ -22,7 +22,7 @@ Operational setup of the project workspace, CI/CD pipeline, hosting platform, an
 
 ## 0. Pre-flight
 
-1. Read `.agent/skills/session-continuity/SKILL.md` and follow its session-open protocol. Check `.agent/progress/sessions/` for any previous session working on `setup-workspace`. If found → read the session close log to determine which shards completed and resume from the next incomplete shard.
+1. Read `.agent/skills/session-continuity/SKILL.md` and follow its session-open protocol. Check `.memory/pipeline/progress/sessions/` for any previous session working on `setup-workspace`. If found → read the session close log to determine which shards completed and resume from the next incomplete shard.
 2. Read the approved phase plan from `.memory/wiki/specs/phases/phase-N.md`
 3. Read `.memory/wiki/specs/*-architecture-design.md` for the architecture pattern
 
@@ -70,7 +70,7 @@ After all 4 shards complete, run `/verify-infrastructure` with trigger `workspac
 
 ## 2.5. Completion Gate (MANDATORY)
 
-1. Update `.agent/progress/` — mark workspace setup as complete
+1. Update `.memory/pipeline/progress/` — mark workspace setup as complete
 2. Scan this conversation for memory-capture triggers (see rule: `memory-capture`):
    - Patterns observed → write to `.memory/wiki/patterns.md`
    - Non-trivial decisions made → write to `.memory/wiki/decisions.md`

package/template/.agent/workflows/update-architecture-map.md

@@ -68,7 +68,7 @@ Ensure the document is human-readable, well-structured, and focuses on high-leve
 ## 6. Phase completion gate
 
 Read `.memory/wiki/specs/*-architecture-design.md` → **Phasing** section to determine the total number of planned phases.
-Read `.agent/progress/index.md` to determine the current phase number N and how many phases have `status: complete`.
+Read `.memory/pipeline/progress/index.md` to determine the current phase number N and how many phases have `status: complete`.
 
 ### If completed phases < total phases
 

package/template/.agent/workflows/validate-phase-quality.md

@@ -20,7 +20,7 @@ pipeline:
 Run all code quality checks for a completed implementation phase.
 
 **Prerequisite**: All slices in the phase must be complete.
-1. Read `.agent/progress/phases/phase-N.md`
+1. Read `.memory/pipeline/progress/phases/phase-N.md`
 2. Verify every slice shows `complete` status
 3. If any slice is not complete → **STOP**: "Phase N has incomplete slices: [list]. Complete them via `/implement-slice` before running validation."
 

package/template/.agent/workflows/validate-phase-readiness.md

@@ -135,7 +135,7 @@ If `.memory/wiki/specs/feature-ledger.md` exists:
 1. Read the ledger and the current phase plan
 2. For each **Must Have** feature assigned to this phase:
    - Verify the `Implemented` column is marked complete
-   - Verify the slice(s) that implement it are marked complete in `.agent/progress/phases/phase-N.md`
+   - Verify the slice(s) that implement it are marked complete in `.memory/pipeline/progress/phases/phase-N.md`
 3. If any Must Have feature assigned to this phase is not implemented → **STOP**: "Phase N has unimplemented Must Have features: [list]. Complete them via `/implement-slice` before marking the phase as validated."
 
 ## 8.8. Boundary stub audit
@@ -158,7 +158,7 @@ Follow the **Validation Report Structure** in `.agent/skills/prd-templates/refer
 
 ## 9.5. Completion Gate (MANDATORY)
 
-1. Update `.agent/progress/` — mark phase as validated
+1. Update `.memory/pipeline/progress/` — mark phase as validated
 2. Scan this conversation for memory-capture triggers (see rule: `memory-capture`):
    - Patterns observed → write to `.memory/wiki/patterns.md`
    - Non-trivial decisions made → write to `.memory/wiki/decisions.md`