forgetrail 0.5.4 → 0.5.5

package/CONTINUATION_PROMPT.md

@@ -11,7 +11,7 @@ I'm continuing work on [APP NAME]. You are following ForgeTrail, a structured ph
 
 1. Call ForgeTrail MCP **`getResumeSessionInstructions`** and follow it.
 2. Read **`appledger/profiles/forgetrail.yaml`** and the latest session record. If the phase is **plan**, read **`docs/PHASE_1_BRIEF.md`**. Otherwise read **`CONTEXT_PROMPT.md`** (if a later phase is current but CONTEXT is missing and the brief exists, **merge the brief into CONTEXT** first per the CONTEXT_PROMPT template).
-3. Use **`getPhaseGuidance`** for the current phase. Do **not** update **`workflow_tracking.json`**. If that file exists and is not a pointer, run **`appledger migrate preview`** and then apply.
+3. Use **`getPhaseGuidance`** for the current phase. If a legacy `.forgetrail/workflow_tracking.json` exists and is not a pointer, run **`appledger migrate preview`** and then apply.
 
 ### Local `_forgetrail/` folder
 
@@ -19,7 +19,7 @@ I'm continuing work on [APP NAME]. You are following ForgeTrail, a structured ph
 
 **Before doing anything else:**
 
-1. Read **`appledger/profiles/forgetrail.yaml`** and the latest session record to see where we left off. Do not treat **`.forgetrail/workflow_tracking.json`** as the live record.
+1. Read **`appledger/profiles/forgetrail.yaml`** and the latest session record to see where we left off.
 2. Read `_forgetrail/WORKFLOW.md` for the full phase map, playbooks, and patterns.
 3. Read `_forgetrail/TRACKING_SCHEMA.md` for where project state lives. The legacy JSON shape in that file is for migration only.
 4. Read `CONTEXT_PROMPT.md` for the current architecture and project state — or **`docs/PHASE_1_BRIEF.md`** if still in Phase 1; if Phase 2+ and CONTEXT is empty but the brief exists, merge brief → CONTEXT first.
@@ -27,7 +27,7 @@ I'm continuing work on [APP NAME]. You are following ForgeTrail, a structured ph
 **Rules for this session:**
 
 - When you believe a phase's exit criteria are met, tell me explicitly: "I think we've completed [Phase X]. The exit criteria are met because [reasons]. Ready to move to [Phase Y]?" Wait for my confirmation.
-- After completing work, update **`appledger/`**: move satisfied criteria only when evidence exists, add decision records (with rationale), log lessons or questions, and update the session record. Do not write **`workflow_tracking.json`**.
+- After completing work, update **`appledger/`**: move satisfied criteria only when evidence exists, add decision records (with rationale), log lessons or questions, and update the session record.
 - Keep `CONTEXT_PROMPT.md` updated as the source of truth for project architecture.
 - If something isn't working after 5 turns, propose a fundamentally different approach rather than continuing to patch.
 

package/INITIAL_PROMPT.md

@@ -9,12 +9,12 @@ You are helping me build a full-stack web application. I use ForgeTrail, a struc
 
 ### MCP-first (recommended — no `_forgetrail/` copy in this repo)
 
-If **ForgeTrail is connected as an MCP server**, do **not** require a local `_forgetrail/` folder. Methodology, templates, and audits stay in the MCP server (open-source ForgeTrail install). Persist project state in **`appledger/`**. Do **not** create **`.forgetrail/workflow_tracking.json`**. Optional Cursor rules may live in this repo.
+If **ForgeTrail is connected as an MCP server**, do **not** require a local `_forgetrail/` folder. Methodology, templates, and audits stay in the MCP server (open-source ForgeTrail install). Persist project state in **`appledger/`**. Optional Cursor rules may live in this repo.
 
 **Before doing anything else:**
 
 0. If **`docs/GENESIS.md`** exists, call **`ingestPlanArtifact`** with its contents and review the draft brief before scaffolding. If the user only has an idea, offer **`getGenesisSpecPrompt`** (they save as `docs/GENESIS.md`) or point them at **TRY_FORGETRAIL.md** when MCP is not the entry path.
-1. Call the ForgeTrail MCP tool **`getNewProjectKickoff`** (set **`includeCursorRule`** to **false** if not using Cursor). When `appledger` is installed, run **`appledger init`** as that bundle describes. Do **not** write **`workflow_tracking.json`**. Write the Cursor rule when included. Keep the **first reply to the user** short per the bundle’s post-bootstrap section (no MCP tool list or raw JSON dump). **Alternatively:** call **`getNewProjectBootstrap`**, **`getInitialWorkflowTracking`**, **`getPostBootstrapUserMessage`**, and **`getForgeTrailCursorPhaseRule`** separately. `getInitialWorkflowTracking` does not return a JSON file to save.
+1. Call the ForgeTrail MCP tool **`getNewProjectKickoff`** (set **`includeCursorRule`** to **false** if not using Cursor). When `appledger` is installed, run **`appledger init`** as that bundle describes. Write the Cursor rule when included. Keep the **first reply to the user** short per the bundle’s post-bootstrap section (no MCP tool list or raw JSON dump). **Alternatively:** call **`getNewProjectBootstrap`**, **`getInitialWorkflowTracking`**, **`getPostBootstrapUserMessage`**, and **`getForgeTrailCursorPhaseRule`** separately. `getInitialWorkflowTracking` does not return a JSON file to save.
 2. In Phase 1, call **`getGreenfieldIntakePrompt`** alongside **`getChecklist`** (`before-session-1`) so exports (PDF / DOCX / PPTX, etc.), tenancy (e.g. consultants × clients), hybrid vs full spec, compliance tier, and hero flow are captured early in **`PHASE_1_BRIEF.md`** and as decision records (skip questions already answered in Genesis).
 3. Use **`getProgressiveDocSchedule`**, **`getPhaseGuidance`**, **`getChecklist`**, **`getTemplate`** (include **`PHASE_1_BRIEF`** in Phase 1; use `mode: "shell"` or `full` as needed), **`getTrackingSchema`**, **`runAudit`**, **`searchLessons`**, and **`getAntiPatterns`** as that bootstrap describes.
 4. We're starting with Phase 1 (Architecture + Planning).
@@ -27,7 +27,7 @@ If **ForgeTrail is connected as an MCP server**, do **not** require a local `_fo
 
 **Optional — web search (live data):** If the app needs **up-to-date web search**, the user can sign up for **[Tavily](https://tavily.com/)** and/or the **[Brave Search API](https://api-dashboard.search.brave.com/)** (free or entry-level credits — see vendor pricing), add the key to **`.env`**, and ask you to wire **server-side** calls only. **`FORGETRAIL_LITE.md` §4.4** has the full note; log the provider choice as a decision record.
 
-**Phase 1 — project archetype:** classify the project as **`product`** (default — full 7-phase lifecycle), **`internal-tool`** (Phase 6 optional; Phase 7 drops payments/business-plan/marketing criteria), or **`one-shot`** (gift / event / demo — phases 5–7 collapse into one polish-and-ship gate). Infer from my description and confirm rather than interrogate. Record it in **`PHASE_1_BRIEF.md`**, as a decision record, and as **`archetype`** on **`appledger/profiles/forgetrail.yaml`**. Prune the non-applicable criteria on that profile and log the pruning as a decision. Do not write `workflow_tracking.json`. See **WORKFLOW.md §1d**. When the project **ends**, run the **wrap protocol** (WORKFLOW.md §1e): harvest lesson and decision records, propagate the generalizable ones, and set **`project_status`** to **`wrapped`** on the profile.
+**Phase 1 — project archetype:** classify the project as **`product`** (default — full 7-phase lifecycle), **`internal-tool`** (Phase 6 optional; Phase 7 drops payments/business-plan/marketing criteria), or **`one-shot`** (gift / event / demo — phases 5–7 collapse into one polish-and-ship gate). Infer from my description and confirm rather than interrogate. Record it in **`PHASE_1_BRIEF.md`**, as a decision record, and as **`archetype`** on **`appledger/profiles/forgetrail.yaml`**. Prune the non-applicable criteria on that profile and log the pruning as a decision. See **WORKFLOW.md §1d**. When the project **ends**, run the **wrap protocol** (WORKFLOW.md §1e): harvest lesson and decision records, propagate the generalizable ones, and set **`project_status`** to **`wrapped`** on the profile.
 
 **Phase 1 — state persistence (web apps):** before locking PocketBase + auth, ask me *"Does any state need to outlive this browser — accounts, cross-device sync, shared data — or is per-user state fine in `localStorage`?"* If **local-only**: drop PocketBase + auth, target `adapter-static`, no deploy-time secrets. If **persistent**: full Default-A stack. Record the answer in **`PHASE_1_BRIEF.md` §4 (`State persistence:`)** and as a decision record. See **`FORGETRAIL_LITE.md` §7** (A-local vs A-persistent).
 
@@ -55,7 +55,7 @@ Skip the **“copy-paste paths”** section below unless we are using a **local*
 
 1. Read `_forgetrail/WORKFLOW.md` to understand the full phase map, playbooks, and patterns.
 2. Read `_forgetrail/TRACKING_SCHEMA.md` for where project state lives. The legacy JSON shape in that file is for migration only.
-3. Read **`appledger/profiles/forgetrail.yaml`** and the latest session record. Do **not** create **`.forgetrail/workflow_tracking.json`**.
+3. Read **`appledger/profiles/forgetrail.yaml`** and the latest session record.
 4. If using **Cursor**, copy **`_forgetrail/content/cursor-rules/forgetrail-phase-status.mdc`** to **`.cursor/rules/forgetrail-phase-status.mdc`** (create folders if needed) so agents surface phase / next actions from `appledger/profiles/forgetrail.yaml`.
 5. We're starting with Phase 1 (Architecture + Planning).
 
@@ -63,7 +63,7 @@ Skip the **“copy-paste paths”** section below unless we are using a **local*
 
 - At the start of each session, read `appledger/profiles/forgetrail.yaml`, the latest session record, and `CONTEXT_PROMPT.md` (if it exists).
 - When you believe a phase's exit criteria are met, tell me explicitly: "I think we've completed [Phase X]. The exit criteria are met because [reasons]. Ready to move to [Phase Y]?" Wait for my confirmation.
-- After completing work, update **`appledger/`**: move satisfied criteria only when evidence exists, add decision records (with rationale), log lessons or questions, and update the session record. Do not write **`workflow_tracking.json`**.
+- After completing work, update **`appledger/`**: move satisfied criteria only when evidence exists, add decision records (with rationale), log lessons or questions, and update the session record.
 - During Phase 1, create and lock **`docs/PHASE_1_BRIEF.md`**; mirror major decisions as decision records.
 - When we create `CONTEXT_PROMPT.md` (Phase 2), **merge `PHASE_1_BRIEF.md` into it** first (see template), then keep it updated as the source of truth.
 - If something isn't working after 5 turns, propose a fundamentally different approach rather than continuing to patch.
@@ -174,12 +174,12 @@ Phase 1 (Architecture + Planning):
 - Recommend what to skip for v1.
 - Wait for my confirmation on every architectural decision.
 - Create **`docs/PHASE_1_BRIEF.md`** from the ForgeTrail template (`_forgetrail/docs/` or MCP **`getTemplate("PHASE_1_BRIEF")`**). Fill and **lock** it before we exit Phase 1.
-- Record major commitments as **decision records in `appledger/`** so the next session does not depend on chat history. Do not write **`workflow_tracking.json`**.
+- Record major commitments as **decision records in `appledger/`** so the next session does not depend on chat history.
 
 Phase 2 (Scaffolding + Core Build):
 
 - Only after I've confirmed the architecture and the brief is locked.
-- Read **`PHASE_1_BRIEF.md`**, **`appledger/profiles/forgetrail.yaml`**, and the latest session record first. Do not treat **`workflow_tracking.json`** as the live record.
+- Read **`PHASE_1_BRIEF.md`**, **`appledger/profiles/forgetrail.yaml`**, and the latest session record first.
 - Build the **entire app skeleton in one pass**: project init, dependencies, services, routes, components — **do not defer the runnable spine or hero flow**.
 - Include an import script if there's existing data.
 - Wire up the hero flow end to end.

package/WORKFLOW.md

@@ -4,7 +4,7 @@
 
 A persistent development system for building software with AI agents. A structured 7-phase workflow for solo developers building non-trivial full-stack apps with coding agents. Derived from 7 sessions and ~78,000 lines of real-world app development.
 
-**System of record:** Phase, decisions, lessons, and sessions live in `appledger/` (`profiles/forgetrail.yaml` and records). Do not create or update `.forgetrail/workflow_tracking.json`. If that file already exists and is not a pointer, run `appledger migrate preview` and then apply. Do not keep a second decision log. `.forgetrail/` is hooks and host integration.
+**System of record:** Phase, decisions, lessons, and sessions live in `appledger/` (`profiles/forgetrail.yaml` and records). If a legacy `.forgetrail/workflow_tracking.json` exists and is not a pointer, run `appledger migrate preview` and then apply. Do not keep a second decision log. `.forgetrail/` is hooks and host integration.
 
 ---
 
@@ -104,7 +104,7 @@ These phases emerged from the actual build sequence across all sessions. They're
 
 **Principle:** **Phase 2** still means the **full app spine** in one pass — project init, dependencies, data path, routes, components, import/migration if needed, **hero flow end-to-end**. That spine should not be deferred.
 
-**ForgeTrail workspace:** Protocol, rules, and hooks live in **`.forgetrail/`** at the repo root — **`.forgetrail/IDEAS.md`**, platform rules (`AGENTS.md`, `CLAUDE.md`, optional `FORGETRAIL_LITE.md`). Project state lives in **`appledger/`**. Do not create `.forgetrail/workflow_tracking.json`. Product docs (`docs/PHASE_1_BRIEF.md`, `CONTEXT_PROMPT.md`, `README.md`, `TODO.md`, **`docs/FORGETRAIL_PROGRESS.md`**) stay outside `.forgetrail/`. Optionally gitignore `.forgetrail/` for a cleaner public repo or MCP-only boots (no vendored Lite). Commit `appledger/` with the app. See **`FORGETRAIL_LITE.md` §1.5** and **`NEW_PROJECT_BOOTSTRAP.md`**.
+**ForgeTrail workspace:** Protocol, rules, and hooks live in **`.forgetrail/`** at the repo root — **`.forgetrail/IDEAS.md`**, platform rules (`AGENTS.md`, `CLAUDE.md`, optional `FORGETRAIL_LITE.md`). Project state lives in **`appledger/`**. Product docs (`docs/PHASE_1_BRIEF.md`, `CONTEXT_PROMPT.md`, `README.md`, `TODO.md`, **`docs/FORGETRAIL_PROGRESS.md`**) stay outside `.forgetrail/`. Optionally gitignore `.forgetrail/` for a cleaner public repo or MCP-only boots (no vendored Lite). Commit `appledger/` with the app. See **`FORGETRAIL_LITE.md` §1.5** and **`NEW_PROJECT_BOOTSTRAP.md`**.
 
 **Non-technical operators:** Phase 2 should add **setup/run/status** launchers (**`ONE_CLICK_DEV_SETUP.md`**) and **test-*** launchers per dependency (**`SYSTEM_HEALTH_CHECKS.md`**). Avoid hardcoded PocketBase versions (**§4.2.2**). Local Ollama: Granite 4.1 / Gemma 3 defaults, not thinking models unless required (**§4.8**).
 
@@ -160,7 +160,7 @@ Run **both** ForgeTrail's `runAudit("black-hat")` and gstack's `/cso` — they'r
 
 ### Key rule
 
-After every gstack sprint that completes meaningful work, **update `appledger/`** (criteria that have evidence, decision records, lessons, and the session record). Do not write `.forgetrail/workflow_tracking.json`. gstack does persist some sprint-level artifacts — design docs from `/office-hours` live in `~/.gstack/projects/`, retro snapshots in `.context/retros/`, review gate overrides per branch, and skill usage analytics. But gstack has **no lifecycle state** (what phase are we in?), **no decision rationale log** (why did we choose PocketBase over Supabase?), **no lesson capture** (what burned us and how did we fix it?), and **no architecture context document** (what does the file tree look like, what patterns do we use?). ForgeTrail's `appledger/` + `CONTEXT_PROMPT.md` fill exactly this gap — they are the system of record that lets the next session pick up where this one left off without replaying context from chat history.
+After every gstack sprint that completes meaningful work, **update `appledger/`** (criteria that have evidence, decision records, lessons, and the session record). gstack does persist some sprint-level artifacts — design docs from `/office-hours` live in `~/.gstack/projects/`, retro snapshots in `.context/retros/`, review gate overrides per branch, and skill usage analytics. But gstack has **no lifecycle state** (what phase are we in?), **no decision rationale log** (why did we choose PocketBase over Supabase?), **no lesson capture** (what burned us and how did we fix it?), and **no architecture context document** (what does the file tree look like, what patterns do we use?). ForgeTrail's `appledger/` + `CONTEXT_PROMPT.md` fill exactly this gap — they are the system of record that lets the next session pick up where this one left off without replaying context from chat history.
 
 ---
 
@@ -220,7 +220,7 @@ Hosts differ in spawn syntax — call **`getAgentIntegrationGuide`** (`grok`, `c
 
 ### Key rule
 
-After subagent results return, the **parent must** update `appledger/` (criteria that have evidence, decision records, lessons, and the session record) and relevant progressive docs. Do not write `.forgetrail/workflow_tracking.json`. Subagents fix or explore in isolation but **do not** replace ForgeTrail as the system of record for lifecycle state, decision rationale, or lesson capture.
+After subagent results return, the **parent must** update `appledger/` (criteria that have evidence, decision records, lessons, and the session record) and relevant progressive docs. Subagents fix or explore in isolation but **do not** replace ForgeTrail as the system of record for lifecycle state, decision rationale, or lesson capture.
 
 ---
 
@@ -256,7 +256,7 @@ The ledger collects lessons and decisions all project long — but nothing consu
 
 1. **Sweep the ledger.** Read every lesson and decision record plus `CONTEXT_PROMPT.md`'s lesson and pattern sections. For each, ask: *is this generalizable beyond this app?* Framework traps, CLI behavior changes, and integration surprises usually are; app-specific content decisions usually are not.
 2. **Run the propagation prompt** (`prompts/propagate-to-forgetrail.md`) with the harvest list as input — see its **Harvest mode** section, designed for exactly this sweep. Small projects without a product journal or full doc set use `appledger/` as the primary discovery source.
-3. **Close the ledger.** Set `project_status` to `wrapped` on `appledger/profiles/forgetrail.yaml`, add a final session record summarizing end state and where things live (deploy URL, handoff notes), and make a final commit. Optionally tag the repo (`v1.0`, `shipped`). Do not write `.forgetrail/workflow_tracking.json`.
+3. **Close the ledger.** Set `project_status` to `wrapped` on `appledger/profiles/forgetrail.yaml`, add a final session record summarizing end state and where things live (deploy URL, handoff notes), and make a final commit. Optionally tag the repo (`v1.0`, `shipped`).
 4. **Log the propagation** in ForgeTrail's `update-log.md` as usual. A wrap with zero propagable lessons is legitimate — note "wrapped, nothing to propagate" in the final session record and skip steps 2 and 4.
 
 **Why this is a protocol and not a suggestion:** the compounding loop (README) only compounds if lessons actually flow back. One flagship project propagating regularly plus a dozen small projects propagating never is a leak — the small projects are often where the freshest scaffolding and framework gotchas surface, because they exercise the newest tool versions.
@@ -270,7 +270,7 @@ Catalyst Forge siblings (and Cloudflare as a default DNS/hosting suggestion) are
 - **ForgeTrail** = lifecycle + project memory.
 - **Companions** = one bounded job (publish Markdown, named ports, editorial review, quality score, labels, backup, voice journal).
 
-They are **never required**. Decline is success. Do not dump the shelf at kickoff. Suggest when a trigger is true; persist the outcome on the appledger session as `data.companion_outcomes`. Do not write `workflow_tracking.json`.
+They are **never required**. Decline is success. Do not dump the shelf at kickoff. Suggest when a trigger is true; persist the outcome on the appledger session as `data.companion_outcomes`.
 
 **Subjects:** When an applicable subject exists — an application, a tool server, a skill package, an agent configuration, or a model variant — record a disposition with `appledger subjects`. A family with no subject is `not_applicable`, not a missing label. Do not generate or rewrite a label. A published xFacts label remains an offer when the product goes public or changes hands, and only if the user asks.
 
@@ -303,8 +303,8 @@ ForgeTrail includes deterministic host hooks (`.forgetrail/hooks/` with `.cursor
 
 - **Shell guards:** Runs pre-commit verification (`pnpm run verify`), prevents package manager divergence (e.g. `npm`/`yarn` when `pnpm-lock.yaml` is present), gates `git push` on explicit user approval, and flags destructive operations (`git reset --hard`, `rm -rf`).
 - **Edit guards:** Requires user confirmation before mutating environment secrets (`.env*`) or canonical/completed specs (`specs/completed/**`).
-- **Session start injection:** Points the session at `appledger/` (profile phase and the latest session). It does not treat `.forgetrail/workflow_tracking.json` as the live phase.
-- **Tracking validation:** A pointer to `appledger/` is accepted. A writable `workflow_tracking.json` is a conflict and is not the system of record.
+- **Session start injection:** Points the session at `appledger/` (profile phase and the latest session). It reports a legacy `.forgetrail/workflow_tracking.json` as a conflict, not the live phase.
+- **Tracking validation:** A pointer to `appledger/` is accepted. A legacy writable `workflow_tracking.json` is a conflict and is not the system of record.
 
 Where the host supports hooks, tool-level denial and injection take the load off agent context budgets.
 
@@ -342,7 +342,7 @@ Where the host supports hooks, tool-level denial and injection take the load off
 **Artifacts to create:**
 
 - **`PHASE_1_BRIEF.md`** in `docs/` (from `_forgetrail/docs/PHASE_1_BRIEF.md` template or ForgeTrail MCP `getTemplate({ name: "PHASE_1_BRIEF" })`). Fill every section; mark **locked** when accurate.
-- **`appledger/`**: a decision record for each major architectural commitment (with rationale); the session record carries the sign-off summary. Do not create `.forgetrail/workflow_tracking.json`.
+- **`appledger/`**: a decision record for each major architectural commitment (with rationale); the session record carries the sign-off summary.
 
 **Verify before moving on:**
 
@@ -410,7 +410,7 @@ Where the host supports hooks, tool-level denial and injection take the load off
 - No **new** doc files. However:
   - Update **`CONTEXT_PROMPT.md`** with any patterns, env quirks, or workarounds discovered during stabilization.
   - Update **`README.md`** if setup steps changed (new env vars, revised install, required services).
-  - Record a lesson in **`appledger/`** for every surprise (env, path, auth, integration) so the same mistake is never repeated. Do not write `.forgetrail/workflow_tracking.json`.
+  - Record a lesson in **`appledger/`** for every surprise (env, path, auth, integration) so the same mistake is never repeated.
 
 **Verify before moving on:**
 
@@ -869,7 +869,7 @@ Print this and work through it sequentially for each new project.
 - [ ] Use "paste the error" for debugging
 - [ ] Update CONTEXT_PROMPT.md before ending (especially decisions and their WHY)
 - [ ] Mark completed TODOs, add new ones
-- [ ] Update the appledger session, decisions, and lessons. Do not write workflow_tracking.json
+- [ ] Update the appledger session, decisions, and lessons.
 
 ---
 
@@ -902,7 +902,7 @@ Full templates for each document live in `_forgetrail/docs/` (or ForgeTrail MCP
 
 ### Document Lifecycle
 
-**Phase 1 (Architecture):** Complete and lock **`PHASE_1_BRIEF.md`**; mirror commitments as decision records in **`appledger/`**. Do not write `.forgetrail/workflow_tracking.json`.
+**Phase 1 (Architecture):** Complete and lock **`PHASE_1_BRIEF.md`**; mirror commitments as decision records in **`appledger/`**.
 
 **Phase 2 (Scaffold):** Full **app spine** in one pass. **Docs:** Merge brief → **`CONTEXT_PROMPT.md`**, then **`TODO.md`**, **`README.md`**, **`.forgetrail/IDEAS.md`** only (§1a). Minimal extra prose at first beyond the merge.
 

package/content/AGENT_INTEGRATION_claude.md

@@ -17,7 +17,7 @@ Claude-based coding agents integrate with ForgeTrail through MCP, extended plann
 
 **New project:**
 ```
-Call ForgeTrail getNewProjectKickoff, write appledger/, getGreenfieldIntakePrompt, getPhaseGuidance("1"). Do not write workflow_tracking.json.
+Call ForgeTrail getNewProjectKickoff, write appledger/, getGreenfieldIntakePrompt, getPhaseGuidance("1").
 No app code until PHASE_1_BRIEF.md is locked.
 ```
 

package/content/AGENT_INTEGRATION_cursor.md

@@ -23,7 +23,7 @@ Use plan mode for Phase 1 if available. Lock PHASE_1_BRIEF.md before scaffolding
 
 **Resume:**
 ```
-Call getResumeSessionInstructions. Read appledger/profiles/forgetrail.yaml, the latest session record, and CONTEXT_PROMPT.md. Do not update workflow_tracking.json.
+Call getResumeSessionInstructions. Read appledger/profiles/forgetrail.yaml, the latest session record, and CONTEXT_PROMPT.md.
 ```
 
 ## Subagent patterns
@@ -41,7 +41,7 @@ Use `run_in_background` for long subagents when appropriate.
 ## Tracking sync
 
 After subagent or feature work:
-- Update `appledger/` (criteria, decision records, lessons, the session). Do not write `workflow_tracking.json`.
+- Update `appledger/` (criteria, decision records, lessons, the session).
 - Run **`validateTracking`** only when a legacy tracking file is present. A missing file is expected.
 - Update `CONTEXT_PROMPT.md` when architecture or patterns change.
 

package/content/AGENT_INTEGRATION_generic.md

@@ -15,14 +15,14 @@ ForgeTrail owns **what** and **when**. The host agent owns **execution**.
 
 **New project:**
 ```
-Call ForgeTrail getNewProjectKickoff, write appledger/, then getPhaseGuidance("1"). Do not write workflow_tracking.json.
+Call ForgeTrail getNewProjectKickoff, write appledger/, then getPhaseGuidance("1").
 Lock architecture in docs/PHASE_1_BRIEF.md before any app code.
 ```
 
 **Resume:**
 ```
 Call getResumeSessionInstructions. Read appledger/profiles/forgetrail.yaml, the latest session record, and CONTEXT_PROMPT.md.
-Continue from the current phase. Do not update workflow_tracking.json.
+Continue from the current phase.
 ```
 
 ## When the host supports subagents
@@ -35,7 +35,7 @@ Prefer **read-only** subagents for analysis; parent or a single write-capable wo
 
 ## When the host supports plan mode
 
-Use native plan mode for **Phase 1** only. On approval, export to `PHASE_1_BRIEF.md` and decision records in `appledger/`. Do not write `workflow_tracking.json`. See **`getPlanModePatterns`**.
+Use native plan mode for **Phase 1** only. On approval, export to `PHASE_1_BRIEF.md` and decision records in `appledger/`. See **`getPlanModePatterns`**.
 
 ## Persistent discipline
 

package/content/AGENT_INTEGRATION_grok.md

@@ -6,25 +6,25 @@ Grok Build (the agentic TUI/CLI from xAI) has excellent native primitives that m
 
 | Grok Primitive              | ForgeTrail Phase(s)          | How to Use |
 |-----------------------------|----------------------------|------------|
-| `/plan` + enter/exit_plan_mode + plan.md | Phase 1 (Architecture)    | Use native plan mode for all Phase 1 work. On approval, export to `PHASE_1_BRIEF.md` and decision records in `appledger/`. Do not write `workflow_tracking.json`. See `PLAN_MODE_PATTERNS.md`. |
+| `/plan` + enter/exit_plan_mode + plan.md | Phase 1 (Architecture)    | Use native plan mode for all Phase 1 work. On approval, export to `PHASE_1_BRIEF.md` and decision records in `appledger/`. See `PLAN_MODE_PATTERNS.md`. |
 | `spawn_subagent` (explore/plan/general, capability_mode, isolation: worktree, background, resume_from, personas) | All phases, especially 4, 5, 7 | Use for parallel audits (black-hat, UX, code quality), research, stabilize debugging, and exploratory spikes. Call `suggestSubagentDecomposition` first. Prefer read-only for analysis subagents. |
-| `todo_write` + TODO panel   | All phases                 | Mirror open criteria and next actions from `appledger/profiles/forgetrail.yaml`. The ledger is the durable record. Do not write `workflow_tracking.json`. |
+| `todo_write` + TODO panel   | All phases                 | Mirror open criteria and next actions from `appledger/profiles/forgetrail.yaml`. The ledger is the durable record. |
 | Skills (`/create-skill`, SKILL.md) | All sessions             | Install the `forgetrail` skill (see `SKILL.md` in content/skills/forgetrail). It keeps phase discipline, tracking rules, and subagent patterns always active. |
 | Native MCP (search_tool + use_tool) | Methodology delivery    | Register the ForgeTrail MCP server. Tools appear as `forgetrail__*`. Use `getNewProjectKickoff`, `getPhaseGuidance`, `getCompanionSuggestions`, `runAudit`, `searchLessons`, `validateTracking`, etc. |
 | Headless (`grok -p ... --output-format json`) | Automation / CI       | Call kickoff/resume tools and have the agent produce structured phase state. Add exit-criteria validation in pipelines. |
 | `docx` / `pptx` / `xlsx` skills + image/video gen | Phase 1 intake, Phase 6/7 deliverables | Use for exports (PDF/DOCX/PPTX), landing pages, brand assets, and marketing materials called out in greenfield intake. |
-| Sessions + memory + AGENTS.md | Cross-session continuity | `appledger/` plus `CONTEXT_PROMPT.md` are the ForgeTrail equivalents. Update the session record at session end. Do not write `workflow_tracking.json`. |
+| Sessions + memory + AGENTS.md | Cross-session continuity | `appledger/` plus `CONTEXT_PROMPT.md` are the ForgeTrail equivalents. Update the session record at session end. |
 
 ## Recommended Session Openers in Grok
 
 For a new project:
 ```
-Call ForgeTrail getNewProjectKickoff (includeCursorRule false), write appledger/, then start Phase 1 using native /plan mode. Read the generated plan on approval and produce PHASE_1_BRIEF.md plus decision records. Do not write workflow_tracking.json.
+Call ForgeTrail getNewProjectKickoff (includeCursorRule false), write appledger/, then start Phase 1 using native /plan mode. Read the generated plan on approval and produce PHASE_1_BRIEF.md plus decision records.
 ```
 
 For resuming:
 ```
-Call ForgeTrail getResumeSessionInstructions. Read appledger/profiles/forgetrail.yaml, the latest session record, and CONTEXT_PROMPT.md. Continue from the current phase. Do not update workflow_tracking.json.
+Call ForgeTrail getResumeSessionInstructions. Read appledger/profiles/forgetrail.yaml, the latest session record, and CONTEXT_PROMPT.md. Continue from the current phase.
 ```
 
 ## Subagent Patterns (Grok-specific)
@@ -45,7 +45,7 @@ Use `background: true` for long-running subagents and retrieve with `get_command
 ## Ledger sync
 
 After meaningful work (especially subagent results or feature completion):
-- Update `appledger/` (criteria, decision records, lessons, the session). Do not write `workflow_tracking.json`.
+- Update `appledger/` (criteria, decision records, lessons, the session).
 - Use `todo_write` to surface the next 3–5 open items from the profile.
 - Update `CONTEXT_PROMPT.md` when patterns or architecture change.
 

package/content/COMPANION_TOOLS.md

@@ -4,7 +4,7 @@ ForgeTrail owns phases, tracking, and progressive docs. **Companions** do one bo
 
 Public shelf (current versions and install): [catalystforge.com/tools](https://catalystforge.com/tools/).
 
-**Agents:** call **`getCompanionSuggestions`** with a `phase` (`1`–`7`) or a `situation` id when a trigger below is true. `getPhaseGuidance` also appends a short optional-companions footer. Offer one sentence plus the homepage. Do **not** install unless the user asked. Do **not** name this file, MCP tools, or spec paths in the human-facing offer. After a run that matters, persist the outcome on the appledger session as `data.companion_outcomes` and in the matching progressive doc. Do not write `workflow_tracking.json`.
+**Agents:** call **`getCompanionSuggestions`** with a `phase` (`1`–`7`) or a `situation` id when a trigger below is true. `getPhaseGuidance` also appends a short optional-companions footer. Offer one sentence plus the homepage. Do **not** install unless the user asked. Do **not** name this file, MCP tools, or spec paths in the human-facing offer. After a run that matters, persist the outcome on the appledger session as `data.companion_outcomes` and in the matching progressive doc.
 
 **Humans:** skip this file unless you already want a neighbor for a specific job.
 

package/content/FORGETRAIL_LITE.md

@@ -1,6 +1,6 @@
 # ForgeTrail Lite — portable kickoff for any agentic chat
 
-> **ForgeTrail Lite v2.2.1**
+> **ForgeTrail Lite v2.2.2**
 > © Catalyst Forge, LLC — [www.catalystforge.com](https://www.catalystforge.com)
 > Part of the **ForgeTrail** open-source methodology ([Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0) in the upstream ForgeTrail repo).
 >
@@ -8,7 +8,7 @@
 
 A single self-contained file for starting a new project in **any** agent: Cursor, Claude Code, Claude Cowork, OpenAI Codex, Cline, Aider, Continue, Windsurf, etc. **No MCP server, no vendored methodology tree, no external fetches.** Drop this file into the repo (or paste it into chat), and the agent has enough structure to run a real project end to end.
 
-**System of record:** Phase, decisions, lessons, and sessions live in `appledger/` (`profiles/forgetrail.yaml` and records). Do not create or update `.forgetrail/workflow_tracking.json`. §11 is the legacy shape for `appledger migrate` only. If that file already exists and is not a pointer, run `appledger migrate preview` and then apply. Do not keep a second decision log. `.forgetrail/` is the protocol, rules, and hooks.
+**System of record:** Phase, decisions, lessons, and sessions live in `appledger/` (`profiles/forgetrail.yaml` and records). §11 is the legacy shape for `appledger migrate` only. If a legacy `.forgetrail/workflow_tracking.json` exists and is not a pointer, run `appledger migrate preview` and then apply. Do not keep a second decision log. `.forgetrail/` is the protocol, rules, and hooks.
 
 > **Maintainers:** Optional onboarding blocks in **§4.3**, **§4.4**, and **§7.1** are intentionally duplicated in root **`README.md`** and **`WORKFLOW.md`**. When you edit one, sync the others (see **`update-log.md`** — FORGETRAIL_LITE release checklist, item 3).
 
@@ -107,7 +107,7 @@ When a boot surfaces a gap in **ForgeTrail Lite itself** (not a one-off app bug)
 
 ### Who creates what
 
-The **human** only needs to do two things: copy ForgeTrail Lite into **`.forgetrail/`** (or paste this doc into chat), and tell the agent to follow it. **Everything else is created by the agent** as it works through the phases. You should never be asked to hand-write `appledger/`, `.forgetrail/AGENTS.md`, the brief, `CONTEXT_PROMPT.md`, or the Phase 2 baseline files — the agent writes them and shows them to you for review. Do not create `.forgetrail/workflow_tracking.json`.
+The **human** only needs to do two things: copy ForgeTrail Lite into **`.forgetrail/`** (or paste this doc into chat), and tell the agent to follow it. **Everything else is created by the agent** as it works through the phases. You should never be asked to hand-write `appledger/`, `.forgetrail/AGENTS.md`, the brief, `CONTEXT_PROMPT.md`, or the Phase 2 baseline files — the agent writes them and shows them to you for review.
 
 | File / folder | Who creates it | When |
 |---|---|---|
@@ -307,7 +307,7 @@ Record anything non-obvious as a lesson in **`appledger/`** (for example, Playwr
 
 ### 4.2 Ordered first actions
 
-1. **Read** `.forgetrail/FORGETRAIL_LITE.md` top to bottom. Also read `appledger/profiles/forgetrail.yaml`, the latest session record, `.forgetrail/AGENTS.md`, and `CONTEXT_PROMPT.md` if they already exist. Do not read a writable `workflow_tracking.json` as the live phase.
+1. **Read** `.forgetrail/FORGETRAIL_LITE.md` top to bottom. Also read `appledger/profiles/forgetrail.yaml`, the latest session record, `.forgetrail/AGENTS.md`, and `CONTEXT_PROMPT.md` if they already exist.
 2. **Ensure the folder is a git repo.** *(Skip this step if the user opted into no-git mode in §4.1.)* Check with `git rev-parse --is-inside-work-tree`. If it returns false or errors, run `git init -b main` (or `git init` + `git branch -m main` on older git) at the repo root. Never re-init an existing repo. **Apply §1.5 git policy** (default: **commit `.forgetrail/`** for Lite). Write a minimal `.gitignore` containing at least:
    ```
    node_modules/
@@ -320,7 +320,7 @@ Record anything non-obvious as a lesson in **`appledger/`** (for example, Playwr
    2. **`.forgetrail/cursor/rules/forgetrail-updates-log.mdc`** — use the §12.5 snippet verbatim. **Symlink or copy** into `.cursor/rules/` so Cursor reminds agents when to update `FORGETRAIL_LITE_UPDATES.md` (§1.6). Optional: copy the upstream **`FORGETRAIL_LITE_UPDATES.md`** starter into `.forgetrail/` when you expect protocol feedback during the project.
    3. **`.forgetrail/hooks/` and `.cursor/hooks.json`** — install host safety hooks (`content/hooks/`) into `.forgetrail/hooks/` and copy `cursor-hooks.json` to `.cursor/hooks.json`. On Cursor, this runs pre-commit verification, enforces pnpm lock consistency, gates git push at the tool level, and injects live phase context at session start. For Claude Code, add `claude-settings-hooks.json` into `.claude/settings.json`.
    If any of these already exists and its content conflicts with the Lite defaults, **do not overwrite** — flag the conflict to the user and ask how to reconcile. Record the reconciliation as a decision in `appledger/`.
-4. **Create `appledger/`** if it does not exist. Run `pnpm dlx appledger init --name "<application name>"` (or `appledger init` when it is installed globally), then `pnpm dlx appledger check`. Init writes `manifest.yaml`, `profiles/forgetrail.yaml` with the `plan` phase `in_progress`, an application record, and a session record. It does not overwrite existing files. Init leaves the purpose as "Not supplied." Write the one-line purpose into the application record from what the user has already said, then run `check` again. Do **not** create `.forgetrail/workflow_tracking.json`. Criteria stay `pending` until evidence exists. **Without Node:** write the same four files by hand in the shape of the [minimal example ledger](https://github.com/Catalyst-Forge-LLC/appledger/tree/main/examples/minimal/appledger), and run `appledger check` once Node is available. A hand-written ledger is not checked until then.
+4. **Create `appledger/`** if it does not exist. Run `pnpm dlx appledger init --name "<application name>"` (or `appledger init` when it is installed globally), then `pnpm dlx appledger check`. Init writes `manifest.yaml`, `profiles/forgetrail.yaml` with the `plan` phase `in_progress`, an application record, and a session record. It does not overwrite existing files. Init leaves the purpose as "Not supplied." Write the one-line purpose into the application record from what the user has already said, then run `check` again. Criteria stay `pending` until evidence exists. **Without Node:** write the same four files by hand in the shape of the [minimal example ledger](https://github.com/Catalyst-Forge-LLC/appledger/tree/main/examples/minimal/appledger), and run `appledger check` once Node is available. A hand-written ledger is not checked until then.
 5. **If git was initialized in step 2**, make the first commit now so the user has a clean baseline. **What lands in the commit depends on §1.5:** if **committing `.forgetrail/`**, steps 3–4 artifacts are included; if **gitignoring `.forgetrail/`**, only `.gitignore` (and any `.cursor/rules/` copies) — the workspace stays local-only and that is expected, not a mistake. Example: `git add -A && git commit -m "chore: ForgeTrail Lite bootstrap"`. Skip this step if the repo already had history — do not squash or amend what's there. Skip entirely if the user is in no-git mode (§4.1).
 6. **Ask the §5 intake questions.** Do not write any project code yet. For the first user-facing reply, follow §9 (plain product language, one clear "reply with," no methodology jargon).
 7. **Create `docs/`** (if missing) and **draft `docs/PHASE_1_BRIEF.md`** from the §6 template using the user's answers. Show it to the user, iterate, then **lock it**: mark the brief criteria met in `appledger/profiles/forgetrail.yaml` only when the user has approved them, and record major commitments as decision records.
@@ -461,7 +461,7 @@ Output requirements
 
 ### 4.6 ForgeTrail phase progress (human-readable)
 
-**Source of truth:** **`appledger/profiles/forgetrail.yaml`** and the latest session record (agents update every session). Do not write `workflow_tracking.json`.
+**Source of truth:** **`appledger/profiles/forgetrail.yaml`** and the latest session record (agents update every session).
 
 **For humans who are not in Cursor:**
 
@@ -839,7 +839,7 @@ Full ForgeTrail expands this under **`docs/TECHNICAL_REFERENCE.md`** (*URL impor
    - **Letters** (A/B/C) = pick-one / "which first?" — avoids collision with numbered steps.
 6. **No interactive CLIs** in scripted commands. Pass non-interactive flags. Examples: `npm create vite@latest -- --template ...`, `gh repo create --confirm`. For SvelteKit in Lite, **prefer the manual scaffold** (§4.2 step 10 A.1) over `sv create` — by the time Phase 2 runs, the repo root is never empty and `sv create .` will hit an un-skippable **`Directory not empty. Continue?`** prompt and hang. If you do use `sv create` as a shortcut, target a **new empty subfolder** (`sv create app`), never `.`. A hanging prompt in an agent terminal is a dead session.
 7. **Five-turn rule.** If a bug or design problem has not converged in ~5 turns, **stop patching** and propose a different approach (different library, different data model, different scope cut). Announce the pivot explicitly.
-8. **Update the ledger after substantive work.** Move criteria that have evidence, and update the session record. A stale `appledger/` after a busy session is a bug. Do not write `workflow_tracking.json`.
+8. **Update the ledger after substantive work.** Move criteria that have evidence, and update the session record. A stale `appledger/` after a busy session is a bug.
 9. **Git commits — clean messages and natural stopping points.** See **§8.9** for guidelines. Commit with phase-prefixed or descriptive messages (`git commit -m "phase-2: wire hero flow"` or `git commit -F path/to/msg.txt`). Always verify that types and checks pass cleanly before committing. Never leave uncommitted broken states across session boundaries.
 
 10. **Install/bootstrap scripts must branch on `process.platform` before shelling out to archive, network, or text tools.** Treat `tar`, `unzip`, `curl`, `sed`, `awk`, `openssl`, and similar as **platform-dependent on Windows** — never a drop-in from a Unix-only recipe. On `win32`, prefer PowerShell (`Expand-Archive`, `Invoke-WebRequest`) or call `C:\Windows\System32\tar.exe` by absolute path to bypass PATH shadowing; keep `tar` / `unzip` / `curl` for macOS/Linux branches. Layer fallbacks and end with a clear error that points the user at manual steps (e.g. “Extract All”) if automation cannot run. Full failure modes: §13 (Engineering).
@@ -862,7 +862,7 @@ Ensure that automated checks pass (`pnpm run verify` or project test suite) befo
 
 ## 9. First user-facing reply after bootstrap
 
-After you create `.forgetrail/AGENTS.md`, `appledger/`, and the git baseline, your **first message to the human** should be **short, plain-English, and ask only the opening round** of §5. Do not create `.forgetrail/workflow_tracking.json`. Do **not** dump the full intake checklist. Do **not** list MCP tools, internal file paths, ForgeTrail terms ("hero workflow," "architecture," "spine," "exit criteria," "brief," "phase"), or file inventories. Target **~80 words or fewer** — this is a conversation starter, not a form.
+After you create `.forgetrail/AGENTS.md`, `appledger/`, and the git baseline, your **first message to the human** should be **short, plain-English, and ask only the opening round** of §5. Do **not** dump the full intake checklist. Do **not** list MCP tools, internal file paths, ForgeTrail terms ("hero workflow," "architecture," "spine," "exit criteria," "brief," "phase"), or file inventories. Target **~80 words or fewer** — this is a conversation starter, not a form.
 
 **The anchor round is always Round 1:** three small, numbered questions — project name, what it is, who it's for. Nothing else. Stagger the rest of §5 across follow-up messages once they answer.
 
@@ -1003,7 +1003,7 @@ Save this as `.forgetrail/AGENTS.md` so agents that auto-load it (Codex, Cursor,
 
 ```markdown
 <!--
-  Agent protocol based on ForgeTrail Lite v2.2.1.
+  Agent protocol based on ForgeTrail Lite v2.2.2.
   © Catalyst Forge, LLC — www.catalystforge.com
   Licensed under Apache License 2.0 (upstream ForgeTrail repo).
 -->
@@ -1034,7 +1034,7 @@ This repository uses **ForgeTrail Lite** as its project kickoff and operating pr
 Initial `git init`, `pnpm init` / scaffolder, `pnpm install`, and the initial commit are all done by the agent per `.forgetrail/FORGETRAIL_LITE.md` §4. Do not ask the user to run setup commands by hand. If `git`, **Node.js**, **npm**, or **pnpm** are missing, follow §4.1 preflight (concrete install path; no-git mode for git only — never silently skip).
 
 ## Session start
-1. Read `appledger/profiles/forgetrail.yaml` and `CONTEXT_PROMPT.md` (if present). Do not treat `.forgetrail/workflow_tracking.json` as the live phase.
+1. Read `appledger/profiles/forgetrail.yaml` and `CONTEXT_PROMPT.md` (if present).
 2. Check the current profile phase and the latest session record.
 3. Verify `.git/` and `package.json` exist if the phase calls for them; if missing, re-read `.forgetrail/FORGETRAIL_LITE.md` §4 (preflight + ordered actions) and catch up before proceeding. If a decision records that source control is deferred, respect no-git mode and remind the user git is still pending.
 4. If the previous session left exit criteria unmet, resume there — do not jump ahead.
@@ -1056,7 +1056,7 @@ These are the failures ForgeTrail sees most often. The agent should re-read this
 - **Skipping the Phase 1 brief.** Rewrites compound. If the user says "just start coding," offer to write a 10-line brief in 2 minutes first — it still pays off.
 - **Half-built spine.** Scaffolding a UI with mock data, or wiring a DB with no UI, and calling it Phase 2. The spine is end-to-end or it is not a spine.
 - **Silent stack swap.** Choosing a framework, DB, or language the user did not confirm. Always name the stack and get a "yes" before Phase 2.
-- **Ledger rot.** Creating `appledger/` once and never updating it. Update the session record at the end of every substantive turn. Do not recreate `.forgetrail/workflow_tracking.json`.
+- **Ledger rot.** Creating `appledger/` once and never updating it. Update the session record at the end of every substantive turn.
 - **Turning the first reply into a methodology dump.** Users want a product answer, not a tour of decision records and exit criteria.
 
 **Engineering**
@@ -1119,7 +1119,6 @@ During Phase 2, create these once the spine is running. Keep them short and hone
   # CLAUDE.md
   # IDEAS.md
   # .cursor/rules/forgetrail-updates-log.mdc
-  # Do not symlink or recreate .forgetrail/workflow_tracking.json.
   # Project state is appledger/ and is committed with the app.
 
   # Deps
@@ -1179,4 +1178,4 @@ ForgeTrail Lite covers the shape of a project. The full **ForgeTrail MCP server*
 
 ---
 
-**ForgeTrail Lite v2.2.1** · © Catalyst Forge, LLC · [www.catalystforge.com](https://www.catalystforge.com) · [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)
+**ForgeTrail Lite v2.2.2** · © Catalyst Forge, LLC · [www.catalystforge.com](https://www.catalystforge.com) · [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)

package/content/FORGETRAIL_PROGRESS.md

@@ -1,6 +1,6 @@
 # ForgeTrail progress
 
-_Human-readable snapshot for non-technical operators. **Source of truth:** `appledger/profiles/forgetrail.yaml` and the latest session record. The agent updates those. Do not write `.forgetrail/workflow_tracking.json`. This page is a snapshot, not the record._
+_Human-readable snapshot for non-technical operators. **Source of truth:** `appledger/profiles/forgetrail.yaml` and the latest session record. The agent updates those. This page is a snapshot, not the record._
 
 ## Current phase
 

package/content/GENESIS_SPEC_PROMPT.md

@@ -14,7 +14,7 @@ Use this **before** Phase 1, in **any** LLM chat — ChatGPT, Claude, Grok, a lo
 
 1. Save it in the project repo as **`docs/GENESIS.md`** (canonical path).
 2. Follow the human recipe in **`TRY_FORGETRAIL.md`** (ForgeTrail repo root), or feed the spec into ForgeTrail Phase 1:
-   - **Automatic draft:** call **`ingestPlanArtifact`** with the full `GENESIS.md` text as `planContent`. It maps headings like *Problem statement*, *Goals and non-goals*, *Required background on the data/file format*, *Core domain concepts*, *Edge cases*, *Milestones*, and *Open questions* into `docs/PHASE_1_BRIEF.md` sections, and extracts any `D1.`/`D2.`-style decisions into decision records for `appledger/`. Do not write `workflow_tracking.json`. Sections without a clean home (e.g. **Acceptance criteria** — the brief has no dedicated section for it) land in a "Plan sections not auto-mapped" footer — fold that into **§12 Handoff checklist** or its own appendix by hand.
+   - **Automatic draft:** call **`ingestPlanArtifact`** with the full `GENESIS.md` text as `planContent`. It maps headings like *Problem statement*, *Goals and non-goals*, *Required background on the data/file format*, *Core domain concepts*, *Edge cases*, *Milestones*, and *Open questions* into `docs/PHASE_1_BRIEF.md` sections, and extracts any `D1.`/`D2.`-style decisions into decision records for `appledger/`. Sections without a clean home (e.g. **Acceptance criteria** — the brief has no dedicated section for it) land in a "Plan sections not auto-mapped" footer — fold that into **§12 Handoff checklist** or its own appendix by hand.
    - **Manual walkthrough:** read `docs/GENESIS.md` together with the agent as context, then run **`getGreenfieldIntakePrompt`** + `getChecklist(before-session-1)` to confirm delivery details the spec might not cover (tenancy, compliance, live search, content-generation pattern).
 3. Either way, **lock `docs/PHASE_1_BRIEF.md`** before Phase 2 scaffolding, per the normal Phase 1 exit criteria.
 

package/content/GENESIS_STUB.md

@@ -13,6 +13,6 @@ Replace this file with your **what, not how** build spec.
 
 See **TRY_FORGETRAIL.md** in the ForgeTrail repo for the full recipe. Short version:
 
-> Follow `.forgetrail/FORGETRAIL_LITE.md` as the project protocol. Treat `docs/GENESIS.md` as the product spec (what, not how). If `appledger` is installed, run `appledger init`. Otherwise create `appledger/` (manifest, profile, application record, session record). Draft `docs/PHASE_1_BRIEF.md` from the Genesis file, asking me only about gaps. Do not create `workflow_tracking.json`. Do not scaffold application code until I explicitly approve the Phase 1 brief.
+> Follow `.forgetrail/FORGETRAIL_LITE.md` as the project protocol. Treat `docs/GENESIS.md` as the product spec (what, not how). If `appledger` is installed, run `appledger init`. Otherwise create `appledger/` (manifest, profile, application record, session record). Draft `docs/PHASE_1_BRIEF.md` from the Genesis file, asking me only about gaps. Do not scaffold application code until I explicitly approve the Phase 1 brief.
 
 Keep this file at **`docs/GENESIS.md`** (this path). Do not move it to the repo root.

package/content/GREENFIELD_INTAKE.md

@@ -4,7 +4,7 @@ Use alongside **`getChecklist`** section `before-session-1`. That checklist cove
 
 **Already have a written spec (e.g. `docs/GENESIS.md`)?** Feed it into **`ingestPlanArtifact`** first, then use this document only to fill gaps (delivery, tenancy, compliance, live search) it may not cover. If the user has only an idea, **`getGenesisSpecPrompt`** (or human recipe **`TRY_FORGETRAIL.md`**) produces a portable spec via an external LLM chat before you run through these questions.
 
-**Agent:** Walk through these with the user (or infer from context and confirm). Record answers in **`docs/PHASE_1_BRIEF.md`** (§1–3, §6–8 as needed) and as **decision records in `appledger/`**. Do not write `workflow_tracking.json`.
+**Agent:** Walk through these with the user (or infer from context and confirm). Record answers in **`docs/PHASE_1_BRIEF.md`** (§1–3, §6–8 as needed) and as **decision records in `appledger/`**.
 
 ---
 
@@ -19,7 +19,7 @@ Use alongside **`getChecklist`** section `before-session-1`. That checklist cove
 
 - **Is this a product, an internal tool, or a one-shot?** (product: others will use it, possibly pay; internal-tool: real recurring users, no market; one-shot: gift, event page, demo: one occasion, then done). Often obvious from the problem statement; confirm rather than interrogate.
 - The archetype **prunes the lifecycle**: internal tools make Phase 6 optional and drop payments/business-plan criteria from Phase 7; one-shots collapse phases 5–7 into a single polish-and-ship gate. See **WORKFLOW.md §1d**.
-- Record it in **`PHASE_1_BRIEF.md`**, as a decision record, and as **`archetype`** on **`appledger/profiles/forgetrail.yaml`**. Prune non-applicable criteria on that profile. Do not write `workflow_tracking.json`.
+- Record it in **`PHASE_1_BRIEF.md`**, as a decision record, and as **`archetype`** on **`appledger/profiles/forgetrail.yaml`**. Prune non-applicable criteria on that profile.
 
 ## 1. Outputs and formats
 

package/content/KICKOFF_WITHOUT_MCP.md

@@ -7,7 +7,7 @@ Some Cursor sessions **do not expose MCP tools** to the agent (or only a subset)
 **If you must replicate the kickoff bundle from this repo** (same sources as `buildNewProjectKickoff` in `mcp-server/src/index.ts`), read and apply in order:
 
 1. `content/NEW_PROJECT_BOOTSTRAP.md` — methodology and next steps  
-2. If `appledger` is installed, run **`appledger init`** in the customer repo (pass **`--name`** when the name is known). Otherwise create the manifest, `profiles/forgetrail.yaml`, an application record, and a session record by hand. Do **not** copy root `workflow_tracking.json`. `getInitialWorkflowTracking` does not return a file to write.  
+2. If `appledger` is installed, run **`appledger init`** in the customer repo (pass **`--name`** when the name is known). Otherwise create the manifest, `profiles/forgetrail.yaml`, an application record, and a session record by hand.  
 3. `content/POST_BOOTSTRAP_USER_MESSAGE.md` — how the first user-facing reply should read  
 4. `content/cursor-rules/forgetrail-phase-status.mdc` — write to `.cursor/rules/forgetrail-phase-status.mdc` in the customer repo (Cursor only)  
 5. `content/cursor-rules/forgetrail-lessons-gate.mdc` and `forgetrail-lessons-mcp.mdc` — write to `.cursor/rules/` (lessons + anti-patterns gate before large work)  

package/content/NEW_PROJECT_BOOTSTRAP.md

@@ -1,6 +1,6 @@
 # ForgeTrail — New project bootstrap (MCP-first)
 
-Use this when **ForgeTrail is available via the MCP server** (recommended). The customer repo should **not** contain a copied `_forgetrail/` methodology tree — templates, audits, phase playbooks, and lessons are retrieved through MCP tools from the open-source ForgeTrail install. Project state lives in **`appledger/`**. Do **not** create **`.forgetrail/workflow_tracking.json`**. `.forgetrail/` is hooks and host rules.
+Use this when **ForgeTrail is available via the MCP server** (recommended). The customer repo should **not** contain a copied `_forgetrail/` methodology tree — templates, audits, phase playbooks, and lessons are retrieved through MCP tools from the open-source ForgeTrail install. Project state lives in **`appledger/`**. `.forgetrail/` is hooks and host rules.
 
 ---
 
@@ -8,7 +8,7 @@ Use this when **ForgeTrail is available via the MCP server** (recommended). The
 
 1. Follow the **7-phase lifecycle** (Plan → Build → Stabilize → Iterate → Refine → Align → Harden).
 2. **Pause at phase transitions** for explicit user approval before advancing.
-3. **Persist ForgeTrail state in `appledger/`** — manifest, `profiles/forgetrail.yaml`, and records. Do **not** write **`.forgetrail/workflow_tracking.json`**. Add **`.forgetrail/AGENTS.md`**, **`.forgetrail/CLAUDE.md`**, and **`.forgetrail/cursor/rules/`** (symlink `.mdc` files into **`.cursor/rules/`**) for host rules. Product docs (**`docs/`**, **`CONTEXT_PROMPT.md`**, **`README.md`**, **`TODO.md`**) stay at repo root. **Optionally gitignore `.forgetrail/`** if you want a cleaner public history or use MCP-only without a vendored Lite file (see **`FORGETRAIL_LITE.md` §1.5**). Commit **`appledger/`**. For **Cursor**, add **`.cursor/rules/forgetrail-phase-status.mdc`** from **`getNewProjectKickoff`** (bundled) or **`getForgeTrailCursorPhaseRule`** — it reads **`appledger/profiles/forgetrail.yaml`**. Also add **`forgetrail-lessons-gate.mdc`** and **`forgetrail-lessons-mcp.mdc`** from the same bundle or **`getForgeTrailCursorLessonsRules`** so agents call **`getAntiPatterns`** + **`searchLessons`** before substantial feature work.
+3. **Persist ForgeTrail state in `appledger/`** — manifest, `profiles/forgetrail.yaml`, and records. Add **`.forgetrail/AGENTS.md`**, **`.forgetrail/CLAUDE.md`**, and **`.forgetrail/cursor/rules/`** (symlink `.mdc` files into **`.cursor/rules/`**) for host rules. Product docs (**`docs/`**, **`CONTEXT_PROMPT.md`**, **`README.md`**, **`TODO.md`**) stay at repo root. **Optionally gitignore `.forgetrail/`** if you want a cleaner public history or use MCP-only without a vendored Lite file (see **`FORGETRAIL_LITE.md` §1.5**). Commit **`appledger/`**. For **Cursor**, add **`.cursor/rules/forgetrail-phase-status.mdc`** from **`getNewProjectKickoff`** (bundled) or **`getForgeTrailCursorPhaseRule`** — it reads **`appledger/profiles/forgetrail.yaml`**. Also add **`forgetrail-lessons-gate.mdc`** and **`forgetrail-lessons-mcp.mdc`** from the same bundle or **`getForgeTrailCursorLessonsRules`** so agents call **`getAntiPatterns`** + **`searchLessons`** before substantial feature work.
 4. **Pull methodology on demand** via ForgeTrail MCP tools (below). Do not ask the user to paste entire ForgeTrail files.
 5. **User-facing replies:** After bootstrap files exist, **`getPostBootstrapUserMessage`** defines the **first** reply—plain language only: what you did, what happens next, and a **concrete “reply with”** (problem, audience, hero workflow, constraints, v1 scope). **No** MCP/tool names, methodology jargon, ForgeTrail footers, file inventories, or “reference only” tracking dumps unless the user asks for internals.
 6. **Lists and choices:** When offering several next steps or options, follow **`USER_REPLY_FORMAT.md`** (ForgeTrail): **numbers** for ordered pipelines, **bullets** for parallel items, **letters** for pick-one / “which first—A/B/C?”—never hide multiple paths in one long sentence.
@@ -21,7 +21,7 @@ On a **new project folder**, commands like `git status`, `git log`, or `git rev-
 
 **You** initialize git after bootstrap files exist (unless the user chose **no-git mode** — see **`FORGETRAIL_LITE.md` §4.1**):
 
-1. Write kickoff artifacts first: **`appledger/`**, guardrails, optional Cursor rules. Do not write **`workflow_tracking.json`**.
+1. Write kickoff artifacts first: **`appledger/`**, guardrails, optional Cursor rules.
 2. Check with `git rev-parse --is-inside-work-tree`. If it returns false or errors, run **`git init -b main`** at the repo root (or `git init` + `git branch -m main` on older Git). **Never** re-init an existing repo.
 3. Write a **minimal** `.gitignore` now — at least `node_modules/`, `.env`, `.DS_Store`. Add `.forgetrail/` **only** if you chose the gitignore branch in **`FORGETRAIL_LITE.md` §1.5** (default MCP greenfield: **commit `.forgetrail/`**).
 4. Make a **first commit** when steps 1–3 are done so the user has a clean baseline (plain `-m` or `-F`). Skip if the repo already had history; skip entirely in no-git mode.
@@ -34,7 +34,7 @@ Do **not** treat an early missing-repo git error as blocking. Prefer **`git rev-
 
 - **Phase 1:** Create and lock **`docs/PHASE_1_BRIEF.md`** (`getTemplate({ name: "PHASE_1_BRIEF" })`). Log major commitments as **decision records in `appledger/`**. If the host supports **native plan mode**, use **`getPlanModePatterns`** and WORKFLOW §1c — plan first, export to the brief on approval (no app code during planning).
 - **App/code:** Phase 2 still means the **full runnable spine** in one pass: init, deps, data path, routes, components, hero flow **end-to-end**. Do **not** defer that spine.
-- **Project archetype (Phase 1):** classify the project as **`product`** (default), **`internal-tool`**, or **`one-shot`** (gift / event / demo) — often inferable from the problem statement; confirm rather than interrogate. Record it in **`PHASE_1_BRIEF.md`**, as a decision record, and as **`archetype`** on **`appledger/profiles/forgetrail.yaml`**. Prune non-applicable criteria on that profile (internal tools: Phase 6 optional, no payments/business-plan rows; one-shots: phases 5–7 collapse into one polish-and-ship gate). Log the pruning as a decision. Do not write `workflow_tracking.json`. See **WORKFLOW §1d** and **`GREENFIELD_INTAKE.md`** §0.
+- **Project archetype (Phase 1):** classify the project as **`product`** (default), **`internal-tool`**, or **`one-shot`** (gift / event / demo) — often inferable from the problem statement; confirm rather than interrogate. Record it in **`PHASE_1_BRIEF.md`**, as a decision record, and as **`archetype`** on **`appledger/profiles/forgetrail.yaml`**. Prune non-applicable criteria on that profile (internal tools: Phase 6 optional, no payments/business-plan rows; one-shots: phases 5–7 collapse into one polish-and-ship gate). Log the pruning as a decision. See **WORKFLOW §1d** and **`GREENFIELD_INTAKE.md`** §0.
 - **Web-app sub-question (Phase 1, when app type = web app):** before locking PocketBase + auth, ask *"Does any state need to outlive the browser — accounts, cross-device sync, shared data — or is every user's state private and fine in `localStorage`?"* If local-only → **drop PocketBase and auth**, `adapter-static` becomes viable, no deploy-time secrets; persist via `localStorage` / `IndexedDB`. If persistent → the full Default-A stack applies. Record the choice as a decision record and in **`PHASE_1_BRIEF.md` §4 (`State persistence:` row)**. See **`FORGETRAIL_LITE.md` §7** (A-local vs A-persistent) and **`GREENFIELD_INTAKE.md`** §7.
 - **Initial data (optional):** The user may create **JSON files** for seed, fixtures, or imports by using **any** LLM chat (including **local Ollama**) with the copy-paste prompt in **`FORGETRAIL_LITE.md` §4.3** (structured JSON only; save to `data/` or `fixtures/`). The agent **validates** shape before import; the user can repeat for multiple datasets. Not a replacement for the Phase 1 brief — only for bulk structured content.
 - **Web search (optional):** If v1 needs **live internet search**, the user can sign up for **[Tavily](https://tavily.com/)** and/or the **[Brave Search API](https://api-dashboard.search.brave.com/)** (free or entry-level credits per vendor terms), add keys to **`.env`**, and the agent wires **server-side** clients. See **`FORGETRAIL_LITE.md` §4.4** and **`GREENFIELD_INTAKE.md`** §6.
@@ -57,7 +57,7 @@ Call **`getProgressiveDocSchedule`** for the canonical phase → doc matrix (WOR
    - If **`docs/GENESIS.md`** already exists (Try path / human brought a what-not-how spec), call **`ingestPlanArtifact`** with that file’s contents as `planContent`, review the draft brief, then continue intake for gaps only (`getGreenfieldIntakePrompt`). Do **not** re-run a full blank Genesis prompt unless the user asks.
    - If the user only has an **idea** (no file yet), especially one that wraps an existing app’s data/file format, offer **`getGenesisSpecPrompt`**: they paste it into an **external** LLM chat, save the result as **`docs/GENESIS.md`**, then you ingest as above. Humans without MCP can follow repo-root **`TRY_FORGETRAIL.md`** instead.
    - Skip this step if the user wants straight Lite/MCP intake questions with no Genesis file.
-1. Call **`getNewProjectKickoff`** (`includeCursorRule: false` if not using **Cursor**). It bundles this document, **`appledger/`** initialization, post-bootstrap user-message guidance, and optionally the Cursor rules (phase status + lessons gate + lessons MCP detail)—**or** call **`getNewProjectBootstrap`**, **`getInitialWorkflowTracking`**, **`getPostBootstrapUserMessage`**, **`getForgeTrailCursorPhaseRule`**, and **`getForgeTrailCursorLessonsRules`** separately if you need only one piece. **`getInitialWorkflowTracking` does not return a JSON file.** Write **`appledger/`**. Do not write **`workflow_tracking.json`**. The **next message to the user** follows **`getPostBootstrapUserMessage`** (product-facing, no methodology leak).
+1. Call **`getNewProjectKickoff`** (`includeCursorRule: false` if not using **Cursor**). It bundles this document, **`appledger/`** initialization, post-bootstrap user-message guidance, and optionally the Cursor rules (phase status + lessons gate + lessons MCP detail)—**or** call **`getNewProjectBootstrap`**, **`getInitialWorkflowTracking`**, **`getPostBootstrapUserMessage`**, **`getForgeTrailCursorPhaseRule`**, and **`getForgeTrailCursorLessonsRules`** separately if you need only one piece. **`getInitialWorkflowTracking` does not return a JSON file.** Write **`appledger/`**. The **next message to the user** follows **`getPostBootstrapUserMessage`** (product-facing, no methodology leak).
 2. **Initialize git if needed** (see **Greenfield git** above): after bootstrap files exist, `git init -b main` when `git rev-parse --is-inside-work-tree` fails; minimal `.gitignore`; optional first commit. Do not ask the user to run `git init`.
 3. Call **`getProgressiveDocSchedule`** and keep it in mind for every phase transition.
 4. Call **`getChecklist`** with section `before-session-1` — complete those items with the user (problem statement, stack, assets, hero flow).
@@ -106,7 +106,7 @@ Call **`getProgressiveDocSchedule`** for the canonical phase → doc matrix (WOR
 
 **Immediately (greenfield):**
 
-- **`appledger/`** — if the `appledger` command is installed, run **`appledger init`** and pass **`--name`** when the name is known. Init writes the manifest, profile, application record, and session record, and does not overwrite them. If the command is not installed, write those four files by hand. Do **not** write **`workflow_tracking.json`**. Commit **`appledger/`**.
+- **`appledger/`** — if the `appledger` command is installed, run **`appledger init`** and pass **`--name`** when the name is known. Init writes the manifest, profile, application record, and session record, and does not overwrite them. If the command is not installed, write those four files by hand. Commit **`appledger/`**.
 - **`docs/GENESIS.md`** (optional but preferred on the Try path) — what-not-how product spec from **`getGenesisSpecPrompt`** / **`TRY_FORGETRAIL.md`**. If present at kickoff, ingest with **`ingestPlanArtifact`** before locking the brief.
 - **Git repo** — if `git rev-parse --is-inside-work-tree` fails, **`git init -b main`** after bootstrap files exist (see **Greenfield git**). A failed early `git status` on an empty folder is **not** an error. Add minimal **`.gitignore`** and an optional first commit before Phase 1 intake.
 - **Cursor users:** `.cursor/rules/forgetrail-phase-status.mdc` — from **`getForgeTrailCursorPhaseRule`**. **`forgetrail-lessons-gate.mdc`** + **`forgetrail-lessons-mcp.mdc`** — from **`getForgeTrailCursorLessonsRules`** or **`getNewProjectKickoff`** (lessons workflow before substantial changes).
@@ -140,9 +140,9 @@ Call **`getProgressiveDocSchedule`** for the canonical phase → doc matrix (WOR
 
 - At **each session start**, read **`appledger/profiles/forgetrail.yaml`**, the latest session record, and `CONTEXT_PROMPT.md` (if present). Use **`getPhaseGuidance`** for the current phase.
 - When exit criteria for a phase appear satisfied, **state that explicitly** and **wait for user confirmation** before treating the next phase as active; change `current_phase_instance` only after approval.
-- After substantive work, update **`appledger/`** (criteria, decision records, lessons, the session). Do not write **`workflow_tracking.json`**. If that file exists and is not a pointer, **`validateTracking`** reports the conflict.
+- After substantive work, update **`appledger/`** (criteria, decision records, lessons, the session). If a legacy `.forgetrail/workflow_tracking.json` exists and is not a pointer, **`validateTracking`** reports the conflict.
 - If a problem does not converge after **~5 turns**, propose a **different approach**, not more patches.
-- **When the project ends** (shipped, delivered, shelved), run the **wrap protocol** (WORKFLOW §1e): sweep lesson and decision records for generalizable lessons, run the propagation prompt in **Harvest mode**, set **`project_status`** to **`wrapped`** on the profile, and add a final session record with end state and handoff pointers. Do not write `workflow_tracking.json`.
+- **When the project ends** (shipped, delivered, shelved), run the **wrap protocol** (WORKFLOW §1e): sweep lesson and decision records for generalizable lessons, run the propagation prompt in **Harvest mode**, set **`project_status`** to **`wrapped`** on the profile, and add a final session record with end state and handoff pointers.
 - **Git commits:** `git commit -F <file>` or plain `-m` at natural stopping points with concise summaries. Run verification checks prior to commit.
 
 ---
@@ -157,7 +157,7 @@ ForgeTrail’s reference implementation used **SvelteKit (Svelte 5), TypeScript,
 
 If the user has [gstack](https://github.com/garrytan/gstack) installed (Claude Code slash-command skills), ForgeTrail and gstack are **complementary** — ForgeTrail provides the lifecycle methodology, project memory, and business/brand layer; gstack provides sprint execution, browser-based QA, and deploy automation. Use both:
 
-**ForgeTrail owns the lifecycle.** Phase transitions, exit criteria, `appledger/`, progressive docs, lessons, and audits all come from ForgeTrail MCP. Do not write `workflow_tracking.json`.
+**ForgeTrail owns the lifecycle.** Phase transitions, exit criteria, `appledger/`, progressive docs, lessons, and audits all come from ForgeTrail MCP.
 
 **gstack owns the sprint inner loop.** Within a ForgeTrail phase, use gstack skills for the build → review → test → ship cycle:
 
@@ -171,7 +171,7 @@ If the user has [gstack](https://github.com/garrytan/gstack) installed (Claude C
 | **Phase 6** (Align) | `/design-consultation` for design system, `/plan-ceo-review` for scope check | Create **`BRAND_AND_PRODUCT.md`** and restructure **`TODO.md`** via ForgeTrail templates — gstack doesn't have brand/strategy tooling. |
 | **Phase 7** (Harden) | `/cso` for security audit, `/qa` for full regression, `/ship` + `/land-and-deploy` + `/canary` for production | ForgeTrail's `runAudit("black-hat")` and gstack's `/cso` are complementary — run both. ForgeTrail produces **`BLACK_HAT_REPORT.md`** and **`CODE_QUALITY.md`** as persistent docs; gstack's `/cso` catches runtime exploits. Use `/land-and-deploy` → `/canary` for the actual deploy pipeline, then fill ForgeTrail's **`DEPLOYMENT.md`** to document the process. |
 
-**Key rule:** After every gstack sprint that completes meaningful work, **update `appledger/`** (criteria when evidence exists, decision records, lessons or questions, the session). Do not write `workflow_tracking.json`. gstack persists some sprint artifacts (design docs from `/office-hours` in `~/.gstack/projects/`, retro snapshots in `.context/retros/`, review overrides, skill analytics), but it has **no lifecycle state, no decision rationale log, and no architecture context document**. ForgeTrail's `appledger/` plus `CONTEXT_PROMPT.md` are the system of record for the phase, the decisions, the lessons, and the architecture — none of which gstack tracks.
+**Key rule:** After every gstack sprint that completes meaningful work, **update `appledger/`** (criteria when evidence exists, decision records, lessons or questions, the session). gstack persists some sprint artifacts (design docs from `/office-hours` in `~/.gstack/projects/`, retro snapshots in `.context/retros/`, review overrides, skill analytics), but it has **no lifecycle state, no decision rationale log, and no architecture context document**. ForgeTrail's `appledger/` plus `CONTEXT_PROMPT.md` are the system of record for the phase, the decisions, the lessons, and the architecture — none of which gstack tracks.
 
 ---
 

package/content/PLAN_MODE_PATTERNS.md

@@ -14,7 +14,7 @@ When your host agent supports a first-class plan mode (Grok Build `/plan` + ente
 3. On user approval (the agent's `exit_plan_mode` or equivalent):
    - Immediately call `getTemplate({ name: "PHASE_1_BRIEF", mode: "full" })`.
    - Map/synthesize the approved plan content into the brief template (especially sections on architecture, data model, state persistence, content generation, and v1 scope).
-   - Write each major decision as a decision record in `appledger/`. Do not write `.forgetrail/workflow_tracking.json`.
+   - Write each major decision as a decision record in `appledger/`.
    - Optionally call `ingestPlanArtifact` with the full approved plan text to produce a `PHASE_1_BRIEF.md` draft and decision records (review and lock before Phase 2).
 
 4. The approved `docs/PHASE_1_BRIEF.md` and those decision records become the handoff so Phase 2 can begin "cold" without replaying the entire planning conversation.
@@ -35,7 +35,7 @@ When your host agent supports a first-class plan mode (Grok Build `/plan` + ente
 ## Artifacts That Must Result from Phase 1 (Plan or Not)
 
 - `docs/PHASE_1_BRIEF.md` (locked)
-- `appledger/` with the `plan` phase in progress and those decision records. Do not create `.forgetrail/workflow_tracking.json`.
+- `appledger/` with the `plan` phase in progress and those decision records.
 - (Later) `CONTEXT_PROMPT.md` will merge the brief in Phase 2
 
 Never proceed to scaffolding until the user confirms the plan/brief is locked.

package/content/POCKETBASE_SCHEMA_SCRIPT.md

@@ -18,7 +18,7 @@ Manual admin-UI collection setup (click-through wizards) does not scale across m
 4. **Schema (agent or one terminal):** `pnpm run pocketbase:schema` after PocketBase is up — idempotent; replaces manual Admin UI collection wizards.
 5. **PocketBase broken?** double-click **`test-pocketbase.bat`** / **`pnpm run test:pocketbase`** — isolated health check (**`SYSTEM_HEALTH_CHECKS.md`**).
 6. **Check progress:** double-click **`status.bat`** / **`status.sh`** or open **`docs/FORGETRAIL_PROGRESS.md`**.
-7. Walk the hero flow; tick Phase 2 exit items in `.forgetrail/workflow_tracking.json` when dev runs, data appears, CRUD works, and the full journey passes.
+7. Walk the hero flow; mark Phase 2 criteria met in `appledger/profiles/forgetrail.yaml`, with evidence, when dev runs, data appears, CRUD works, and the full journey passes.
 
 ---
 

package/content/POST_BOOTSTRAP_USER_MESSAGE.md

@@ -1,6 +1,6 @@
 # Post-bootstrap: first reply to the user
 
-**When:** Right after `appledger/` exists (and, for Cursor, the phase rule file if you use it). Do not mention `workflow_tracking.json` to the user.
+**When:** Right after `appledger/` exists (and, for Cursor, the phase rule file if you use it).
 
 **Purpose:** Confirm what happened in **plain language** and give **one clear ask**—what the human should do or answer next. This is not an implementation report.
 
@@ -12,7 +12,7 @@ Assume the reader is a **product owner**, not a methodology engineer. They shoul
 
 - MCP or ForgeTrail server/tool names (`getChecklist`, `getGreenfieldIntakePrompt`, “bundle”, “methodology stays on the MCP side”, etc.)
 - Paths like `.cursor/rules/…` unless they need to edit something themselves
-- Field-by-field descriptions of `workflow_tracking.json` or other “for your reference only” inventories
+- Field-by-field descriptions of `appledger/` files or other “for your reference only” inventories
 - ForgeTrail **footers** (phase · exit criteria · “Next: …”)—those are for **agent** orientation in later turns, not for this first message
 
 Agents keep planning steps **internal** until they turn user answers into `docs/PHASE_1_BRIEF.md`.

package/content/SESSION_RESUME_MCP.md

@@ -19,7 +19,7 @@ Do **not** require `_forgetrail/WORKFLOW.md` or `_forgetrail/TRACKING_SCHEMA.md`
 ## Rules for this session
 
 - When exit criteria for the current phase appear met, say so explicitly and **wait for user confirmation** before changing `current_phase_instance`.
-- After work, update the **session record** and any new **decision records** in **`appledger/`**. Do not write **`workflow_tracking.json`**.
+- After work, update the **session record** and any new **decision records** in **`appledger/`**.
 - Keep **`CONTEXT_PROMPT.md`** the source of truth for architecture; edit it when decisions change.
 - If stuck after **~5 turns** on one issue, propose a **fundamentally different approach**.
 - If the repo has **gstack** installed, use its skills for sprint execution (build/review/qa/ship) within ForgeTrail phases — see **WORKFLOW.md §1b** or call **`getPhaseGuidance`** for phase-specific gstack integration. After each gstack sprint, update the **appledger** session.

package/content/companion-tools.json

@@ -4,7 +4,7 @@
     "Companions are optional. Decline is success. Never block a phase on an install.",
     "Suggest at the moment of need. Do not dump the shelf at kickoff or in the first user-facing message.",
     "Do not install, enroll, or publish unless the user asked.",
-    "After a companion run that matters, persist the outcome on the appledger session as data.companion_outcomes and in the matching progressive doc. Do not write workflow_tracking.json.",
+    "After a companion run that matters, persist the outcome on the appledger session as data.companion_outcomes and in the matching progressive doc.",
     "Do not mention the mapping file, spec paths, or MCP tool names in human-facing offers.",
     "When wiring LocalSlip, follow that tool's how. Do not write ensure-lease.mjs. Do not add the localslip package just to read a port."
   ],

package/content/cursor-rules/forgetrail-phase-status.mdc

@@ -5,7 +5,7 @@ alwaysApply: true
 
 # ForgeTrail phase awareness
 
-This repo uses **ForgeTrail**. **Source of truth:** `appledger/profiles/forgetrail.yaml` and the latest session record. Do **not** read or write `.forgetrail/workflow_tracking.json`. If that file exists and is not a pointer, it is a legacy conflict: run `appledger migrate preview`, then apply.
+This repo uses **ForgeTrail**. **Source of truth:** `appledger/profiles/forgetrail.yaml` and the latest session record. If a legacy `.forgetrail/workflow_tracking.json` exists and is not a pointer, it is a legacy conflict: run `appledger migrate preview`, then apply.
 
 ## When to surface status
 
@@ -19,7 +19,7 @@ Include a short **ForgeTrail** footer in replies when it helps orientation—esp
 
 Skip the footer for trivial one-line answers (typos, single-token replies) unless the user asked for status.
 
-**Product-facing / non-technical users:** Do **not** show ForgeTrail footers, phase IDs, MCP/tool names, or internal checklists unless they ask how the workflow is wired up. Plain language only. For phase progress without an agent, point them to **`docs/FORGETRAIL_PROGRESS.md`**. The durable phase is `appledger/profiles/forgetrail.yaml`, not `.forgetrail/workflow_tracking.json`.
+**Product-facing / non-technical users:** Do **not** show ForgeTrail footers, phase IDs, MCP/tool names, or internal checklists unless they ask how the workflow is wired up. Plain language only. For phase progress without an agent, point them to **`docs/FORGETRAIL_PROGRESS.md`**. The durable phase is `appledger/profiles/forgetrail.yaml`.
 
 **Right after bootstrap:** **Omit** the footer entirely—user should get a simple “what’s done + what I need from you next,” not methodology. If you already followed **`getPostBootstrapUserMessage`** in the same turn, do not duplicate status blocks.
 
@@ -57,4 +57,4 @@ Do **not** bury three or more paths in a single long sentence—**list them**, t
 
 ## Phase transitions
 
-Do **not** advance `current_phase_instance` or mark a phase completed without **explicit user confirmation**. If criteria look satisfied, say so and ask before updating the profile. Do not write `workflow_tracking.json`.
+Do **not** advance `current_phase_instance` or mark a phase completed without **explicit user confirmation**. If criteria look satisfied, say so and ask before updating the profile.

package/content/examples/two-session-continuity.md

@@ -2,7 +2,7 @@
 
 This is a labeled example. The project is fictional. It shows how ForgeTrail Lite state survives a closed chat, and how the next session is supposed to consume it.
 
-Nothing here is a benchmark, an adoption claim, or a client record. The record shape matches `appledger/` records, not the legacy `workflow_tracking.json` starter.
+Nothing here is a benchmark, an adoption claim, or a client record. The record shape matches `appledger/` records.
 
 ## The job
 
@@ -14,7 +14,7 @@ The human created an empty folder, wrote `docs/GENESIS.md`, and added Lite by co
 
 The human pasted the kickoff line from [TRY_FORGETRAIL.md](../../TRY_FORGETRAIL.md). The **agent** (not the CLI) then:
 
-1. Created `appledger/` with a manifest, a ForgeTrail profile, an application record, and a session record. It did not create `.forgetrail/workflow_tracking.json`.
+1. Created `appledger/` with a manifest, a ForgeTrail profile, an application record, and a session record.
 2. Drafted `docs/PHASE_1_BRIEF.md`.
 3. Recorded one decision and one lesson.
 4. Stopped after the human approved the brief. No application scaffold yet.

package/content/hooks/README.md

@@ -9,7 +9,7 @@ Enforces ForgeTrail rules and guards at the host tool level, rather than relying
 - `session-start.mjs`: on session start, points the session at `appledger/`. A writable `workflow_tracking.json` is reported as a legacy conflict, not the live phase.
 - `validate-tracking.mjs`: after editing `workflow_tracking.json`, runs structural validation. A pointer is accepted. A legacy writable document is a conflict.
 - `validate-tracking-core.mjs`: standalone zero-dependency tracking validator.
-- `session-stop.mjs`: on session stop, reminds the agent to update the appledger session record. It does not ask for a new JSON session entry.
+- `session-stop.mjs`: when a turn ends, reminds the agent to update the appledger session record if project files changed after that record was last written. It stays quiet on follow-up turns, on read-only turns, and when only `appledger/`, `.forgetrail/`, `.cursor/`, or `.claude/` changed. It names `workflow_tracking.json` only when a legacy copy is present.
 - `cursor-hooks.json`: standard Cursor hooks configuration.
 - `claude-settings-hooks.json`: standard Claude Code configuration fragment.
 

package/content/hooks/session-start.mjs

@@ -54,7 +54,6 @@ function main() {
     lines.push("Project record: appledger/");
     lines.push("Read appledger/profiles/forgetrail.yaml for the current phase.");
     lines.push("Read the latest session record for left_off and next_steps.");
-    lines.push("Do not update workflow_tracking.json.");
   }
 
   if (trackingPath) {

package/content/hooks/session-stop.mjs

@@ -3,10 +3,11 @@
 /**
  * ForgeTrail Session Stop Check
  * Hook event: stop (Cursor)
- * Reminds the agent to update the AppLedger session, not a tracking JSON file.
+ * Reminds the agent to update the AppLedger session record when work happened after it was last written.
  */
 
-import { existsSync, readFileSync } from "node:fs";
+import { execFileSync } from "node:child_process";
+import { existsSync, readFileSync, readdirSync, statSync } from "node:fs";
 import { join, resolve } from "node:path";
 
 function walkUp(startDir, found) {
@@ -37,7 +38,78 @@ function isPointer(data) {
   return data?.status === "pointer" && typeof data.record === "string" && data.record.replaceAll("\\", "/").includes("appledger");
 }
 
+function readHookInput() {
+  try {
+    const raw = readFileSync(0, "utf-8");
+    return raw.trim() ? JSON.parse(raw) : {};
+  } catch {
+    return {};
+  }
+}
+
+function latestSessionMs(root) {
+  const dir = join(root, "appledger", "records", "session");
+  if (!existsSync(dir)) return 0;
+  let latest = 0;
+  for (const name of readdirSync(dir)) {
+    if (!name.endsWith(".md")) continue;
+    latest = Math.max(latest, statSync(join(dir, name)).mtimeMs);
+  }
+  return latest;
+}
+
+function git(root, args) {
+  return execFileSync("git", args, { cwd: root, encoding: "utf-8", stdio: ["ignore", "pipe", "ignore"] });
+}
+
+const NOT_PROJECT_WORK = ["appledger/", ".forgetrail/", ".cursor/", ".claude/"];
+
+function outsideLedger(path) {
+  const p = path.replaceAll("\\", "/");
+  return p !== "" && !NOT_PROJECT_WORK.some((prefix) => p.startsWith(prefix));
+}
+
+/** True when project files changed after the newest session record, or when that cannot be told. Ledger and host-config paths do not count. */
+function workSinceSession(root) {
+  const sessionMs = latestSessionMs(root);
+  if (sessionMs === 0) return true;
+  try {
+    const since = `@${Math.floor(sessionMs / 1000)}`;
+    const hasCommits = (() => {
+      try {
+        git(root, ["rev-parse", "--verify", "--quiet", "HEAD"]);
+        return true;
+      } catch {
+        return false;
+      }
+    })();
+    if (hasCommits) {
+      const committed = git(root, ["log", `--since=${since}`, "--name-only", "--format="]).split("\n").filter(outsideLedger);
+      if (committed.length > 0) return true;
+    }
+    const pending = git(root, ["status", "--porcelain", "--untracked-files=all"])
+      .split("\n")
+      .map((line) => line.slice(3).split(" -> ").pop()?.replace(/^"|"$/g, "") ?? "")
+      .filter(outsideLedger);
+    return pending.some((path) => {
+      try {
+        return statSync(join(root, path)).mtimeMs > sessionMs;
+      } catch {
+        return true;
+      }
+    });
+  } catch {
+    return true;
+  }
+}
+
 function main() {
+  const input = readHookInput();
+  if ((input.loop_count ?? 0) > 0 || (input.status && input.status !== "completed")) {
+    console.log(JSON.stringify({}));
+    return;
+  }
+
   const ledgerRoot = findLedger(process.cwd());
   const trackingPath = findProjectTracking(process.cwd());
   let legacy = false;
@@ -59,11 +131,11 @@ function main() {
     return;
   }
 
-  if (ledgerRoot) {
+  if (ledgerRoot && workSinceSession(ledgerRoot)) {
     console.log(
       JSON.stringify({
         followup_message:
-          "ForgeTrail reminder: update the appledger session record (what was accomplished, left_off, next_steps) before ending. Do not write workflow_tracking.json.",
+          "ForgeTrail reminder: files changed after the latest appledger session record. Update that record (what was accomplished, left_off, next_steps) before ending.",
       })
     );
     return;

package/content/scripts/forgetrail-dev-launcher.mjs

@@ -144,7 +144,7 @@ async function cmdRun() {
 function renderProgress() {
   if (!existsSync(trackingPath)) {
     return {
-      text: "No workflow_tracking.json. Phase state belongs in appledger/profiles/forgetrail.yaml.",
+      text: "Phase state: appledger/profiles/forgetrail.yaml.",
       md: null,
     };
   }

package/content/skills/forgetrail/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: forgetrail
-description: "Enforce the ForgeTrail 7-phase lifecycle (Plan → Build → Stabilize → Iterate → Refine → Align → Harden), maintain appledger/ as the system of record, pause at explicit phase transitions for user approval, prefer native plan modes when available, and use subagents for parallel audits/research where the host agent supports it. Do not write workflow_tracking.json. Activate for any non-trivial full-stack app development. Follow progressive documentation rules and propagate lessons back."
+description: "Enforce the ForgeTrail 7-phase lifecycle (Plan → Build → Stabilize → Iterate → Refine → Align → Harden), maintain appledger/ as the system of record, pause at explicit phase transitions for user approval, prefer native plan modes when available, and use subagents for parallel audits/research where the host agent supports it. Activate for any non-trivial full-stack app development. Follow progressive documentation rules and propagate lessons back."
 user-invocable: true
 argument-hint: "kickoff new project | resume session | Phase 4 feature work | run black-hat audit | stabilize current issues"
 allowed-tools: "read_file, search_replace, run_terminal_command, todo_write, spawn_subagent, getPhaseGuidance, getCompanionSuggestions, runAudit, searchLessons, validateTracking, suggestSubagentDecomposition, getTemplate, getNewProjectKickoff, getResumeSessionInstructions"
@@ -21,7 +21,7 @@ You are operating under the ForgeTrail methodology. Your primary job is to give
    - 6. Align (map to brand/strategy)
    - 7. Harden (security, perf, docs, production readiness)
 
-   Phases 4 and 5 commonly alternate. Update `current_phase_instance` and criteria in `appledger/profiles/forgetrail.yaml`. Do not write `workflow_tracking.json`.
+   Phases 4 and 5 commonly alternate. Update `current_phase_instance` and criteria in `appledger/profiles/forgetrail.yaml`.
 
 2. **At the start of every session or major turn**:
    - Read `appledger/profiles/forgetrail.yaml` and the latest session record.
@@ -39,10 +39,9 @@ You are operating under the ForgeTrail methodology. Your primary job is to give
    - Mark a criterion `met` only when an evidence ref exists.
    - Add a lesson or question record when something surprising or painful happens.
    - Update the session record at natural breaks.
-   - Do not create or update `workflow_tracking.json`.
 
 5. **Use native agent capabilities**:
-   - If the agent supports a native plan mode (e.g. Grok `/plan`), use it for Phase 1. On approval, export the plan into `docs/PHASE_1_BRIEF.md` (via `getTemplate`) and decision records in `appledger/`. Do not write `workflow_tracking.json`.
+   - If the agent supports a native plan mode (e.g. Grok `/plan`), use it for Phase 1. On approval, export the plan into `docs/PHASE_1_BRIEF.md` (via `getTemplate`) and decision records in `appledger/`.
    - When the host supports `spawn_subagent`, use `suggestSubagentDecomposition` (or reason directly) to run audits, research, and reviews in parallel with appropriate `capability_mode`, `isolation`, and personas. Synthesize results in the parent thread and update tracking/docs.
    - Prefer `read-only` or `execute` modes for subagents doing analysis.
 
@@ -71,11 +70,11 @@ You are operating under the ForgeTrail methodology. Your primary job is to give
 When ready to advance:
 - Confirm the phase criteria that have evidence.
 - Ask the user: "Ready to move to Phase X?"
-- Only after confirmation, update the phase status in `appledger/profiles/forgetrail.yaml` and the session record. Do not write `workflow_tracking.json`.
+- Only after confirmation, update the phase status in `appledger/profiles/forgetrail.yaml` and the session record.
 
 ## For New Projects (Greenfield)
 
-Prefer calling `getNewProjectKickoff` (or `kickoffGreenfield`) at the very beginning. When `appledger` is installed, run `appledger init` as that bundle describes. Do not write `workflow_tracking.json`. Write optional Cursor rules, and follow the post-bootstrap instructions exactly. Then start with Phase 1.
+Prefer calling `getNewProjectKickoff` (or `kickoffGreenfield`) at the very beginning. When `appledger` is installed, run `appledger init` as that bundle describes. Write optional Cursor rules, and follow the post-bootstrap instructions exactly. Then start with Phase 1.
 
 ## For Resuming
 

package/docs/PHASE_1_BRIEF.md

@@ -4,7 +4,7 @@ _Structured capture of planning and architecture **before** code scaffolding. Go
 
 **Status:** `[draft | locked]`  
 **Last updated:** `[ISO date]`  
-**Phase 1 exit:** Do not mark the `plan` phase complete in `appledger/profiles/forgetrail.yaml` until this brief is **locked** and major commitments are decision records. Do not write `workflow_tracking.json`.
+**Phase 1 exit:** Do not mark the `plan` phase complete in `appledger/profiles/forgetrail.yaml` until this brief is **locked** and major commitments are decision records.
 
 ---
 
@@ -158,7 +158,7 @@ _Ordered list of what to build after the spine runs — aligns with initial `TOD
 
 - [ ] User has confirmed stack, folder shape, data sketch, hero flow, and v1 boundaries
 - [ ] This brief is **locked** (no `[draft]` ambiguity) or remaining items are only in §9 Open questions
-- [ ] `appledger/` updated: a decision record for each major D#, and the session records the sign-off. Do not write `workflow_tracking.json`.
+- [ ] `appledger/` updated: a decision record for each major D#, and the session records the sign-off.
 - [ ] Phase 2 opener will read **this file**, `appledger/profiles/forgetrail.yaml`, and the latest session record first
 
 > 💡 **Lesson learned:** Treat the brief and the decision records as a pair. The brief is what the next human or agent reads in one pass. Duplicated rationale is OK — drift between them is not. After Phase 2 starts, **merge** this content into `CONTEXT_PROMPT.md` per the mapping in that template’s “Handoff from Phase 1” section.

package/docs/SPEC_FEATURE_TEMPLATE.md

@@ -132,7 +132,7 @@ _Testable binary pass/fail checks. Avoid vague qualifiers ("performant", "clean"
 
 ## 10. Decisions (optional)
 
-_Lock choices here (and mirror major ones into `.forgetrail/workflow_tracking.json` → `decisions[]` when they are architectural)._
+_Lock choices here (and record major ones as decision records in `appledger/` when they are architectural)._
 
 **D1.**
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "forgetrail",
-  "version": "0.5.4",
+  "version": "0.5.5",
   "private": false,
   "description": "ForgeTrail: a persistent development system for building software with AI agents. CLI, Lite protocol, and methodology templates.",
   "license": "Apache-2.0",

package/scripts/install.mjs

@@ -86,7 +86,7 @@ export function runInstallForgetrail(rawArgv, { defaultToCwd = false } = {}) {
   console.log("\nDone.");
   console.log("  Methodology:  _forgetrail/WORKFLOW.md");
   console.log("  First chat:   _forgetrail/INITIAL_PROMPT.md");
-  console.log("  Project record: appledger/ (not workflow_tracking.json)");
+  console.log("  Project record: appledger/");
   console.log("  Hooks:        .forgetrail/hooks/ (enforced via .cursor/hooks.json)");
   printLedgerNext();
   return { target, mode: "full" };

package/scripts/tracking-cutover.test.mjs

@@ -1,5 +1,5 @@
 import { spawnSync } from "node:child_process";
-import { mkdtempSync, readFileSync, writeFileSync, mkdirSync } from "node:fs";
+import { mkdtempSync, readFileSync, writeFileSync, mkdirSync, utimesSync } from "node:fs";
 import { tmpdir } from "node:os";
 import { dirname, join } from "node:path";
 import { fileURLToPath } from "node:url";
@@ -101,10 +101,10 @@ test("Lite and workflow instructions name the ledger", () => {
   assert.ok(legacyAt > 0 && resumeAt > legacyAt);
   const instructional = `${lite.slice(0, legacyAt)}\n${lite.slice(resumeAt)}`;
   assert.match(lite.slice(legacyAt, resumeAt), /"schemaVersion": "lite-1"/);
-  assert.match(instructional, /ForgeTrail Lite v2\.2\.1/);
+  assert.match(instructional, /ForgeTrail Lite v2\.2\.2/);
   for (const line of instructional.split("\n")) {
     if (!line.includes("workflow_tracking.json")) continue;
-    assert.match(line, /[Dd]o not|does not|not the live phase|not recreate/, line);
+    assert.match(line, /legacy/, line);
   }
   const workflow = readFileSync(join(root, "WORKFLOW.md"), "utf8");
   assert.match(workflow, /not_applicable/);
@@ -112,10 +112,72 @@ test("Lite and workflow instructions name the ledger", () => {
   assert.doesNotMatch(workflow, /Where this file names that JSON/);
   for (const line of workflow.split("\n")) {
     if (!line.includes("workflow_tracking.json")) continue;
-    assert.match(line, /[Dd]o not|does not|not the system of record|not the live phase/, line);
+    assert.match(line, /legacy/, line);
   }
 });
 
+test("fresh-project instructions do not name the tracking file", () => {
+  const files = [
+    "INITIAL_PROMPT.md",
+    "CONTINUATION_PROMPT.md",
+    "content/AGENT_INTEGRATION_claude.md",
+    "content/AGENT_INTEGRATION_cursor.md",
+    "content/AGENT_INTEGRATION_generic.md",
+    "content/AGENT_INTEGRATION_grok.md",
+    "content/COMPANION_TOOLS.md",
+    "content/FORGETRAIL_PROGRESS.md",
+    "content/GENESIS_SPEC_PROMPT.md",
+    "content/GENESIS_STUB.md",
+    "content/GREENFIELD_INTAKE.md",
+    "content/KICKOFF_WITHOUT_MCP.md",
+    "content/NEW_PROJECT_BOOTSTRAP.md",
+    "content/PLAN_MODE_PATTERNS.md",
+    "content/POCKETBASE_SCHEMA_SCRIPT.md",
+    "content/POST_BOOTSTRAP_USER_MESSAGE.md",
+    "content/SESSION_RESUME_MCP.md",
+    "content/companion-tools.json",
+    "content/cursor-rules/forgetrail-phase-status.mdc",
+    "content/skills/forgetrail/SKILL.md",
+    "docs/PHASE_1_BRIEF.md",
+    "docs/SPEC_FEATURE_TEMPLATE.md",
+  ];
+  for (const file of files) {
+    for (const line of readFileSync(join(root, file), "utf8").split("\n")) {
+      if (!line.includes("workflow_tracking.json")) continue;
+      assert.match(line, /legacy|exists|validateTracking/, `${file}: ${line}`);
+    }
+  }
+});
+
+function stopHook(dir, input) {
+  const result = spawnSync(process.execPath, [join(root, "content", "hooks", "session-stop.mjs")], {
+    cwd: dir,
+    input: JSON.stringify(input),
+    encoding: "utf8",
+  });
+  assert.equal(result.status, 0, result.stderr);
+  return JSON.parse(result.stdout);
+}
+
+test("session stop reminds only after work newer than the session record", () => {
+  const dir = mkdtempSync(join(tmpdir(), "ft-stop-"));
+  mkdirSync(join(dir, "appledger", "records", "session"), { recursive: true });
+  writeFileSync(join(dir, "appledger", "manifest.yaml"), "format: appledger\n");
+  const session = join(dir, "appledger", "records", "session", "session-1.md");
+  writeFileSync(session, "session\n");
+  spawnSync("git", ["init", "-q"], { cwd: dir });
+  const old = new Date(Date.now() - 60_000);
+  utimesSync(session, old, old);
+  assert.deepEqual(stopHook(dir, { status: "completed", loop_count: 0 }), {});
+  writeFileSync(join(dir, "app.ts"), "export {};\n");
+  const reminder = stopHook(dir, { status: "completed", loop_count: 0 });
+  assert.match(reminder.followup_message, /session record/);
+  assert.doesNotMatch(reminder.followup_message, /workflow_tracking/);
+  assert.deepEqual(stopHook(dir, { status: "completed", loop_count: 1 }), {});
+  writeFileSync(session, "session updated\n");
+  assert.deepEqual(stopHook(dir, { status: "completed", loop_count: 0 }), {});
+});
+
 test("kickoff names appledger init and does not require the tracking file", () => {
   const kickoff = readFileSync(join(root, "mcp-server", "src", "index.ts"), "utf8");
   assert.match(kickoff, /appledger init/);
@@ -123,7 +185,7 @@ test("kickoff names appledger init and does not require the tracking file", () =
   const plan = readFileSync(join(root, "content", "PLAN_MODE_PATTERNS.md"), "utf8");
   assert.match(plan, /decision record/);
   assert.doesNotMatch(plan, /decisions\[\]/);
-  assert.match(plan, /Do not create `\.forgetrail\/workflow_tracking\.json`/);
+  assert.doesNotMatch(plan, /workflow_tracking/);
   const genesis = readFileSync(join(root, "content", "GENESIS_STUB.md"), "utf8");
   assert.match(genesis, /appledger init/);
   assert.doesNotMatch(genesis, /Create `\.forgetrail\/workflow_tracking\.json`/);