diff --git a/.stage-pilot/bootstrap/baseline.yaml b/.stage-pilot/bootstrap/baseline.yaml
new file mode 100644
index 0000000..e45cae2
--- /dev/null
+++ b/.stage-pilot/bootstrap/baseline.yaml
@@ -0,0 +1,176 @@
+schema_version: 1
+capture_mode: observed
+
+project:
+  repository_name: jarca-ledger-mcp
+  display_name: Jarca Ledger MCP
+  summary: Jarca 가계부 전용 MCP 서버와 Streamlit 대시보드로 계좌/카드 거래, 예산, 분류 규칙, import, 현금흐름 분석을 SQLite에 저장하고 운영한다.
+  primary_domain: Korean household finance ledger and transaction reconciliation
+
+stack:
+  tech_stack:
+    - Python >=3.11
+    - FastMCP / MCP server
+    - SQLite
+    - Streamlit dashboard
+    - pandas / plotly dashboard dependencies
+    - PyMuPDF PDF parsing
+    - openpyxl + msoffcrypto-tool for encrypted Excel imports
+    - pytest test suite
+
+runtime:
+  primary_runtime: mixed
+  primary_entrypoints:
+    - name: jarca-ledger-mcp
+      purpose: MCP stdio server exposing ledger/account/category/import/report tools to Hermes Agent.
+    - name: dashboard/app.py
+      purpose: Streamlit dashboard for local ledger review, categorization, import, and manual reconciliation.
+    - name: pytest
+      purpose: Regression tests for service logic, import parsers, categorization rules, and transfer matching.
+
+interfaces:
+  contracts:
+    - name: MCP tool surface
+      type: internal-service
+      actors: Hermes Agent and MCP clients
+      purpose: Provide structured tools for ledger transactions, categories, budgets, imports, reports, and reconciliation.
+      stability: internal
+      inputs:
+        - Python function/tool arguments validated by server.py signatures.
+        - File paths and optional passwords for import preview/import tools.
+      outputs:
+        - Dictionary responses with success/error payloads; existing success shapes should remain backward compatible.
+      errors:
+        - validation_error for invalid parameters.
+        - parser/import-specific errors for unreadable files, password issues, validation failures, or duplicate handling.
+      compatibility_rules:
+        - Preserve existing success response shapes for existing tools unless a planned migration states otherwise.
+        - Additive optional fields are preferred over breaking argument changes.
+    - name: Streamlit dashboard
+      type: web-app
+      actors: Local operator using browser UI
+      purpose: Display actual cashflow, transaction lists, uncategorized triage, rule management, import batches, and review queues.
+      stability: internal
+      inputs:
+        - Local SQLite database selected through JARCA_LEDGER_DB_PATH or default path.
+        - Uploaded PDF/XLS/XLSX files for supported import paths.
+      outputs:
+        - Streamlit pages, tables, dialogs, categorization updates, import results, and reconciliation actions.
+      errors:
+        - UI-level error messages for unavailable service functions, parser failures, and validation problems.
+      compatibility_rules:
+        - User-facing category/cashflow semantics must remain stable; UI should surface cashflow_kind where classification matters.
+  shared_constraints:
+    - Financial import evidence must preserve raw provenance fields where available.
+    - Actual income/expense must stay separate from account movement, investment movement, and excluded double-count candidates.
+    - Destructive DB migrations are not allowed without explicit backup/approval flow.
+  current_gaps:
+    - Streamlit UX needs final verification for rule deletion, cancel/original linking, and import E2E flows.
+    - No formal CI workflow is present yet.
+    - Project was recently initialized as a git/GitHub repository; release and deployment policy is not yet documented.
+
+structure:
+  planned_top_level_areas:
+    - path: jarca_ledger_mcp/
+      responsibility: MCP server package, SQLite schema, service layer, import parsers, categorization, and reports.
+    - path: dashboard/
+      responsibility: Streamlit operator UI for ledger review and manual workflows.
+    - path: tests/
+      responsibility: pytest regression tests for parsers, service operations, categorization, and matching.
+    - path: docs/
+      responsibility: StagePilot baseline, Discovery, SRS, Batch, and Release documentation.
+    - path: .stage-pilot/
+      responsibility: StagePilot bootstrap seed and local process metadata.
+
+data_model:
+  persistence_backend: SQLite database at ~/.local/share/jarca/ledger.sqlite3 by default, overrideable through JARCA_LEDGER_DB_PATH.
+  entities:
+    - name: LedgerAccount
+      purpose: Represents bank, card, cash, investment, or loan accounts used to attach transaction evidence and balances.
+      source_of_truth: ledger_accounts table
+      lifecycle: created -> updated -> inactive/archived
+      key_fields:
+        - id :: text :: stable account identifier
+        - name :: text :: operator-facing account name
+        - type :: text :: bank/card/cash/investment/loan classification
+        - last_balance :: integer :: latest known balance when available
+      relationships:
+        - Transaction :: account_id links transaction rows to an account
+      state_rules:
+        - active=false hides accounts from default listings without deleting history.
+    - name: Transaction
+      purpose: Represents imported or manually entered financial event evidence with direction, amount, classification, provenance, and memo tags.
+      source_of_truth: transactions table
+      lifecycle: created/imported -> categorized/reconciled -> soft-deleted or retained
+      key_fields:
+        - transaction_date :: date text :: ledger date
+        - type :: text :: income/expense/transfer/refund/adjustment direction
+        - amount :: integer :: positive KRW amount
+        - category/subcategory :: text :: household ledger classification
+        - source/external_id/import_batch_id :: text :: import provenance and dedupe evidence
+      relationships:
+        - LedgerAccount :: account_id
+        - LedgerCategory :: category/subcategory
+        - ImportBatch :: import_batch_id
+      state_rules:
+        - amount is stored as a positive integer; type determines direction.
+        - refund/cancel rows should be linked to the original transaction when confirmed.
+    - name: LedgerCategory
+      purpose: Defines category/subcategory semantics and cashflow_kind used by reports.
+      source_of_truth: ledger_categories table
+      lifecycle: seeded/created -> updated -> inactive/deleted
+      key_fields:
+        - category :: text :: top-level category
+        - subcategory :: text :: optional subcategory
+        - cashflow_kind :: text :: income/expense/transfer/investment/debt_payment/exclude/unknown
+      relationships:
+        - Transaction :: category/subcategory lookup
+        - CategoryRule :: rule target category/subcategory
+      state_rules:
+        - cashflow_kind controls actual household cashflow inclusion semantics.
+    - name: CategoryRule
+      purpose: Defines automatic categorization rules with field, pattern, priority, and optional amount/day constraints.
+      source_of_truth: category_rules table
+      lifecycle: created -> previewed/applied -> updated/deactivated/deleted
+      key_fields:
+        - match_field :: text :: merchant/counterparty/raw_summary/etc.
+        - pattern :: text :: contains/equals/regex match pattern
+        - amount_min/amount_max/day_of_month :: integer :: optional match constraints
+        - priority :: integer :: deterministic rule ordering
+      relationships:
+        - Transaction :: candidate rows updated by matching rules
+      state_rules:
+        - Preview before broad application when changing rules.
+    - name: ImportBatch
+      purpose: Tracks grouped imports for rollback and audit.
+      source_of_truth: import_batches table
+      lifecycle: previewed -> imported -> optionally rolled back
+      key_fields:
+        - id :: text :: batch identifier
+        - source :: text :: import source kind
+        - imported_count/skipped_duplicate_count :: integer :: result summary
+      relationships:
+        - Transaction :: import_batch_id
+      state_rules:
+        - Rollback should soft-delete by default unless explicitly hard-deleted.
+  consistency_rules:
+    - transfer/investment/exclude cashflow kinds are excluded from actual income/expense reports unless an account-movement report is requested.
+    - Cross-account matches require same date, same amount, opposite direction, and compatible source labels before auto-confirmation.
+    - Imported rows should retain raw_summary/raw_payload/counterparty/balance_after when available.
+  persistence_notes:
+    - Schema changes should be idempotent and additive by default.
+    - Manual DB corrections should be narrow, ID-based, and memo-tagged for auditability.
+  current_gaps:
+    - Need formal migration/back-up procedure before destructive or structural migrations.
+    - Need final UI verification for rule deletion and cancel/original linkage.
+
+notes:
+  known_unknowns:
+    - Whether to add CI workflow and deployment/service management for the Streamlit dashboard.
+    - Final UX acceptance criteria for mobile dashboard pages and rule deletion behavior.
+    - Long-term handling policy for accounts where downloadable transaction statements are unavailable.
+
+metadata:
+  captured_at_kst: 2026-06-26 22:24
+  source: bootstrap-baseline-repo-observation
+  updated_from: repo-observation
diff --git a/docs/batches/index.md b/docs/batches/index.md
new file mode 100644
index 0000000..158750c
--- /dev/null
+++ b/docs/batches/index.md
@@ -0,0 +1,10 @@
+# Batch Index
+
+## 목적
+- 이 문서는 batch delivery 단위의 전역 인덱스다.
+- 각 batch는 `docs/batches/<BAT_ID>/` 아래에서 profile(`standard` | `batch-lite`)에 맞는 산출물을 관리한다.
+
+## Batch Register
+
+| BAT ID | Profile | Status | Included REQ | Discovery | Folder |
+| --- | --- | --- | --- | --- | --- |
diff --git a/docs/data-model.md b/docs/data-model.md
new file mode 100644
index 0000000..9f9cc18
--- /dev/null
+++ b/docs/data-model.md
@@ -0,0 +1,140 @@
+# Jarca Ledger MCP Data Model
+
+- Baseline Mode: observed
+- Baseline Seed: `.stage-pilot/bootstrap/baseline.yaml`
+- Status: draft
+- Owner: Jarca / project maintainer
+- Last Updated (KST): 2026-06-26 22:24
+- Source Discovery / Batch: bootstrap-baseline
+
+## Project Summary
+- Jarca 가계부 전용 MCP 서버와 Streamlit 대시보드로 계좌/카드 거래, 예산, 분류 규칙, import, 현금흐름 분석을 SQLite에 저장하고 운영한다.
+
+## Purpose
+- This document captures the current data-model baseline for future Discovery, REQ, Batch, and Release work.
+- It focuses on durable entities, state rules, consistency rules, and persistence boundaries rather than implementation-only details.
+
+## Persistence Backend
+- SQLite database at `~/.local/share/jarca/ledger.sqlite3` by default.
+- Override path through `JARCA_LEDGER_DB_PATH`.
+- Schema initialization and migrations are managed by `jarca_ledger_mcp/db.py`.
+
+## Entity: LedgerAccount
+- Source of Truth: `ledger_accounts`
+- Purpose: Represents bank, card, cash, investment, or loan accounts used to attach transaction evidence and balances.
+- Lifecycle: created -> updated -> inactive/archived
+- Key Fields:
+  - `id` :: text :: stable account identifier
+  - `name` :: text :: operator-facing account name
+  - `type` :: text :: bank/card/cash/investment/loan classification
+  - `institution` :: text :: financial institution or source
+  - `account_number_masked` :: text :: masked account identifier
+  - `holder_name` :: text :: owner context for transfer matching
+  - `last_balance` :: integer :: latest known balance when available
+- Relationships:
+  - `transactions.account_id` links rows to accounts.
+- State Rules:
+  - `active=false` hides accounts from default lists without deleting history.
+
+## Entity: Transaction
+- Source of Truth: `transactions`
+- Purpose: Represents imported or manually entered financial event evidence.
+- Lifecycle: created/imported -> categorized/reconciled -> soft-deleted or retained
+- Key Fields:
+  - `transaction_date` :: date text :: ledger date
+  - `posted_date` / `transaction_datetime` :: text :: source timing detail where available
+  - `type` :: text :: `income`, `expense`, `transfer`, `refund`, or `adjustment`
+  - `amount` :: integer :: positive KRW amount
+  - `category` / `subcategory` :: text :: household classification
+  - `merchant`, `counterparty`, `description`, `payment_method` :: text :: evidence and display fields
+  - `source`, `external_id`, `import_batch_id`, `raw_summary`, `raw_payload` :: text :: provenance and audit fields
+  - `memo` :: text :: operator notes and reconciliation tags
+  - `status` :: text :: active/deleted/review lifecycle state where used
+- Relationships:
+  - belongs to LedgerAccount through `account_id`
+  - linked to ImportBatch through `import_batch_id`
+  - interpreted with LedgerCategory through `category`/`subcategory`
+- State Rules:
+  - Amount is stored positive; `type` determines direction.
+  - Cancellation/refund rows should use `refund` type when confirmed.
+  - Manual link evidence should be memo-tagged rather than silently rewritten.
+
+## Entity: LedgerCategory
+- Source of Truth: `ledger_categories`
+- Purpose: Defines category/subcategory labels and their cashflow semantics.
+- Lifecycle: seeded/created -> updated -> inactive/deleted
+- Key Fields:
+  - `category` :: text
+  - `subcategory` :: text
+  - `cashflow_kind` :: text :: `income`, `expense`, `transfer`, `investment`, `debt_payment`, `exclude`, `unknown`
+  - `sort_order`, `memo`, `active`
+- Relationships:
+  - Referenced by Transaction classification.
+  - Targeted by CategoryRule results.
+- State Rules:
+  - `cashflow_kind` controls inclusion in actual household cashflow reports.
+  - Transfer, investment, exclude, and unresolved kinds are not actual household spending unless a report explicitly asks for account movements.
+
+## Entity: CategoryRule
+- Source of Truth: `category_rules`
+- Purpose: Automatic classification policy for transactions.
+- Lifecycle: created -> previewed/applied -> updated/deactivated/deleted
+- Key Fields:
+  - `match_field` :: text :: field to inspect
+  - `pattern` :: text :: match pattern
+  - `match_type` :: text :: contains/equals/regex
+  - `category` / `subcategory` :: text :: classification target
+  - `priority` :: integer :: deterministic ordering
+  - `amount_min`, `amount_max`, `day_of_month` :: integer nullable :: optional constraints
+  - `person`, `is_fixed`, `confidence`, `memo`, `active`
+- Relationships:
+  - Applies to Transaction rows.
+  - Should target valid or intentional category/subcategory labels.
+- State Rules:
+  - Preview should precede broad application when changing classification behavior.
+  - More specific/high-priority rules should avoid accidentally overriding unrelated evidence.
+
+## Entity: ImportBatch
+- Source of Truth: `import_batches`
+- Purpose: Tracks grouped imports for audit and rollback.
+- Lifecycle: previewed -> imported -> optionally rolled back
+- Key Fields:
+  - `id` :: text :: import batch identifier
+  - `source` :: text :: source kind
+  - `file_path` / source metadata where stored
+  - `inserted_count`, `skipped_duplicate_count`, `created_at`, `rolled_back_at`
+- Relationships:
+  - Transaction rows reference `import_batch_id`.
+- State Rules:
+  - Rollback should soft-delete by default.
+  - Duplicate imports with `skip_duplicates=True` may insert zero rows; that is not automatically an error.
+
+## Entity: Budget
+- Source of Truth: budget table/service functions
+- Purpose: Monthly category/subcategory/person budget target.
+- Lifecycle: created/updated -> compared against actual spending
+- Key Fields:
+  - `month`, `category`, `subcategory`, `person`, `amount`, `currency`, `memo`
+- Relationships:
+  - Compared against Transaction aggregates by report functions.
+
+## Consistency Rules
+- Actual cashflow reports include only categories whose `cashflow_kind` represents actual income or expense according to report semantics.
+- Account movement summaries should be separate from actual household income/expense summaries.
+- Cross-account auto-matching requires same date, same amount, opposite direction, and compatible source/owner evidence.
+- External counterparty securities transfers are review items unless matched or explicitly confirmed.
+- Import evidence fields are retained for audit and future correction.
+- DB corrections should be narrow and memo-tagged.
+
+## Persistence Notes
+- Schema changes should be additive/idempotent unless a destructive migration is explicitly approved and backed up.
+- Passwords for encrypted imports are runtime-only inputs and are not part of the persisted model.
+- Raw payloads may contain sensitive financial evidence and should not be committed to git.
+
+## Current Gaps / Planned Changes
+- Formal schema migration documentation should be added before larger DB changes.
+- Some UI workflows need final E2E verification against real rows.
+- Statement-unavailable account handling needs a documented manual evidence model.
+
+## Change Log
+- 2026-06-26 22:24 KST: Created by `bootstrap-baseline` from repository observation.
diff --git a/docs/discovery/index.md b/docs/discovery/index.md
new file mode 100644
index 0000000..8dab12d
--- /dev/null
+++ b/docs/discovery/index.md
@@ -0,0 +1,8 @@
+# Discovery 전체 인덱스
+
+<!-- 아래 테이블은 /new-discovery 실행 시 자동 갱신된다. 수동 편집 금지. -->
+
+## Discovery 목록
+
+| ID | 날짜 | 이슈명 | 문서 | 상태 |
+|---|---|---|---|---|
diff --git a/docs/interface-contract.md b/docs/interface-contract.md
new file mode 100644
index 0000000..7b5f41b
--- /dev/null
+++ b/docs/interface-contract.md
@@ -0,0 +1,101 @@
+# Jarca Ledger MCP Interface Contract
+
+- Baseline Mode: observed
+- Baseline Seed: `.stage-pilot/bootstrap/baseline.yaml`
+- Status: draft
+- Owner: Jarca / project maintainer
+- Last Updated (KST): 2026-06-26 22:24
+- Source Discovery / Batch: bootstrap-baseline
+
+## Project Summary
+- Jarca 가계부 전용 MCP 서버와 Streamlit 대시보드로 계좌/카드 거래, 예산, 분류 규칙, import, 현금흐름 분석을 SQLite에 저장하고 운영한다.
+
+## Purpose
+- This document captures the current external and operator-facing interface baseline.
+- It is a reference for future Discovery, REQ, Batch, and Release work that changes tool signatures, dashboard behavior, or file import contracts.
+
+## Interface: MCP Tool Surface
+- Type: internal-service
+- Actors: Hermes Agent and MCP clients
+- Entrypoint: `jarca-ledger-mcp` script -> `jarca_ledger_mcp.server:main`
+- Stability: internal but should preserve existing success response shapes for compatibility.
+
+### Representative Tool Groups
+- Health: `ledger_health_check`
+- Accounts: `create_ledger_account`, `list_ledger_accounts`
+- Transactions: `create_ledger_transaction`, `list_ledger_transactions`, `update_ledger_transaction`, `delete_ledger_transaction`
+- Budgets/reports: `create_ledger_budget`, `list_ledger_budgets`, monthly/category/fixed/budget/investable reports
+- Imports: KB Bank PDF, Toss Bank PDF, Toss Securities PDF, SeoulPay XLSX, CSV preview/import where implemented
+- Categories/rules: category CRUD, rule CRUD, categorization preview/apply, uncategorized summaries
+- Reconciliation: cross-account preview/run/review queue, self-transfer candidates/linking, cancel-original candidates/linking
+
+### Inputs
+- Structured MCP tool arguments as declared in `server.py` signatures.
+- File paths and optional passwords for encrypted or password-protected documents.
+- Transaction/account/category identifiers for update, delete, and link operations.
+
+### Outputs
+- Python dictionary payloads containing success data, counts, records, previews, reports, or error details.
+- Existing success shape compatibility is preferred; new fields should be additive where possible.
+
+### Errors
+- Validation errors for invalid parameters or missing IDs.
+- Parser errors for unreadable or unsupported source files.
+- Password/validation errors for encrypted import files.
+- Candidate-not-found errors for link operations when the chosen pair is not in the preview set.
+
+### Compatibility Rules
+- Preserve existing success response shapes unless a migration/REQ explicitly approves a breaking change.
+- Do not write secrets or raw passwords into persistent output, skill files, or committed documentation.
+- Source evidence should remain auditable through raw fields and import batch records.
+
+## Interface: Streamlit Dashboard
+- Type: web-app
+- Actors: Local operator
+- Entrypoint: `streamlit run dashboard/app.py --server.address 0.0.0.0 --server.port 8501`
+- Stability: internal operator UI
+
+### Pages
+- 요약
+- 거래내역
+- 확인필요 큐
+- 미분류
+- 분류 규칙
+- 카테고리
+- 계좌
+- Import
+
+### Inputs
+- Local SQLite database selected by `JARCA_LEDGER_DB_PATH` or default path.
+- Uploaded transaction history files.
+- User edits for categories, rules, transactions, and manual links.
+
+### Outputs
+- Tables, charts, dialogs, previews, import results, and transaction/category updates.
+
+### UI Contract Rules
+- Surface `cashflow_kind` where classification affects actual cashflow interpretation.
+- Keep actual income/expense separated from account movement summaries.
+- Rule page should support create/edit/delete and condition fields `amount_min`, `amount_max`, `day_of_month`.
+- Dialog-based triage actions should avoid losing context where possible.
+
+## Interface: File Import Contracts
+- KB Bank PDF: encrypted/password-protected PDF account history; preserve transaction datetime, counterparty, balance, branch, raw summary, and raw payload.
+- Toss Bank PDF: transaction history PDF parsed into ledger transaction candidates.
+- Toss Securities PDF: securities transaction history with investment movement, dividend, interest, and external transfer handling.
+- SeoulPay XLSX: possibly encrypted Office XLSX/OLE file; decrypt with supplied password and import usage details as actual spending evidence.
+- CSV: generic preview-first import path.
+
+## Shared Constraints
+- All import flows should support preview before mutation where implemented.
+- Dedupe should use deterministic source/external IDs or same-account/date/type/amount/merchant evidence.
+- Import batch metadata should support rollback and audit.
+- Financial data and passwords are sensitive runtime inputs and should not be committed.
+
+## Current Gaps / Planned Changes
+- Formal versioning for MCP response contracts is not yet defined.
+- Browser-level UI acceptance criteria for Streamlit flows are not yet captured as REQ documents.
+- CI contract for tests/lint is not yet present.
+
+## Change Log
+- 2026-06-26 22:24 KST: Created by `bootstrap-baseline` from repository observation.
diff --git a/docs/project-structure.md b/docs/project-structure.md
new file mode 100644
index 0000000..0b17f48
--- /dev/null
+++ b/docs/project-structure.md
@@ -0,0 +1,123 @@
+# Jarca Ledger MCP Project Structure
+
+- Baseline Mode: observed
+- Baseline Seed: `.stage-pilot/bootstrap/baseline.yaml`
+- Status: draft
+- Owner: Jarca / project maintainer
+- Last Updated (KST): 2026-06-26 22:24
+- Source Discovery / Batch: bootstrap-baseline
+
+## Project Summary
+- Jarca 가계부 전용 MCP 서버와 Streamlit 대시보드로 계좌/카드 거래, 예산, 분류 규칙, import, 현금흐름 분석을 SQLite에 저장하고 운영한다.
+
+## Primary Domain
+- Korean household finance ledger and transaction reconciliation
+
+## Tech Stack
+- Python >=3.11
+- FastMCP / MCP server
+- SQLite
+- Streamlit dashboard
+- pandas / plotly dashboard dependencies
+- PyMuPDF, openpyxl, msoffcrypto-tool
+- pytest
+
+## Primary Runtime
+- Type: mixed
+- Planned Entry Points:
+  - `jarca-ledger-mcp` :: MCP stdio server for Hermes Agent tools.
+  - `dashboard/app.py` :: Streamlit dashboard for local ledger operations.
+  - `pytest` :: Regression test entry point.
+
+## Purpose
+- This document is the current repository and package structure baseline.
+- It is a cross-cutting reference document for Discovery, REQ, Batch Design, Batch Verification, and implementation updates.
+
+## Scope
+- Covers top-level repository layout and package/module boundaries.
+- Does not duplicate detailed business rules, acceptance criteria, or implementation-only function signatures.
+
+## Top-Level Structure
+
+```text
+jarca-ledger-mcp/
+├── README.md
+├── pyproject.toml
+├── uv.lock
+├── .env.example
+├── dashboard/
+│   └── app.py
+├── jarca_ledger_mcp/
+│   ├── __init__.py
+│   ├── db.py
+│   ├── service.py
+│   ├── server.py
+│   ├── kb_bank_pdf.py
+│   ├── toss_bank_pdf.py
+│   ├── toss_securities_pdf.py
+│   └── seoulpay_xlsx.py
+├── tests/
+│   ├── test_service.py
+│   ├── test_categorization.py
+│   ├── test_category_rule_filters.py
+│   ├── test_cross_account_transfer_matching.py
+│   ├── test_kb_bank_pdf.py
+│   ├── test_toss_securities_pdf.py
+│   ├── test_seoulpay_xlsx.py
+│   └── test_ledger_categories.py
+├── docs/
+│   ├── discovery/
+│   ├── srs/
+│   ├── batches/
+│   ├── releases/
+│   ├── project-structure.md
+│   ├── runtime-flows.md
+│   ├── interface-contract.md
+│   └── data-model.md
+└── .stage-pilot/
+    └── bootstrap/baseline.yaml
+```
+
+## Package / Module Responsibilities
+- `jarca_ledger_mcp/db.py`
+  - SQLite connection, schema initialization, migrations, row conversion, and database path resolution.
+- `jarca_ledger_mcp/service.py`
+  - Domain service layer for accounts, transactions, categories, category rules, imports, reports, transfer matching, and manual link operations.
+- `jarca_ledger_mcp/server.py`
+  - FastMCP tool registration layer that exposes service functions to Hermes/MCP clients.
+- `jarca_ledger_mcp/kb_bank_pdf.py`
+  - KB 국민은행 encrypted PDF transaction parsing.
+- `jarca_ledger_mcp/toss_bank_pdf.py`
+  - Toss Bank transaction-history PDF parsing.
+- `jarca_ledger_mcp/toss_securities_pdf.py`
+  - Toss Securities transaction-history PDF parsing and transaction preview conversion.
+- `jarca_ledger_mcp/seoulpay_xlsx.py`
+  - SeoulPay encrypted XLSX parsing and preview conversion.
+- `dashboard/app.py`
+  - Streamlit operator UI for summaries, transaction filtering, uncategorized triage, rule management, review queues, categories, accounts, and import operations.
+- `tests/`
+  - Regression tests for service behavior, parser behavior, categorization, category rules, cross-account transfer matching, and ledger category semantics.
+
+## Dependency Rules
+- `server.py` should remain a thin tool adapter and delegate business logic to `service.py`.
+- Parser modules should parse source documents into structured records and avoid direct UI responsibilities.
+- `dashboard/app.py` may call service functions but should not duplicate core classification/report semantics.
+- DB schema migrations should be additive and idempotent by default.
+
+## Shared Boundaries
+- `cashflow_kind` is the boundary between actual household income/expense and account movement/exclusion semantics.
+- Import evidence fields (`source`, `external_id`, `raw_summary`, `raw_payload`, `counterparty`, `import_batch_id`) are audit boundaries and should be preserved.
+- Manual reconciliation is represented through memo tags and narrow transaction updates, not broad rewrites.
+
+## Current Gaps / Planned Changes
+- Final UX verification is still needed for 분류 규칙 삭제, 취소/환급 원거래 연결, and import E2E flows.
+- CI workflow and deployment/service management are not yet defined.
+- Long-term policy for accounts without downloadable statements remains partially operational/documentation work.
+
+## Update Triggers
+- Update this document when package boundaries change.
+- Update this document when new top-level runtime or domain modules are added.
+- Update this document when a batch changes the approved structure baseline.
+
+## Change Log
+- 2026-06-26 22:24 KST: Created by `bootstrap-baseline` from repository observation.
diff --git a/docs/releases/index.md b/docs/releases/index.md
new file mode 100644
index 0000000..1b66789
--- /dev/null
+++ b/docs/releases/index.md
@@ -0,0 +1,10 @@
+# Release Index
+
+## 목적
+- 이 문서는 release 단위의 전역 인덱스다.
+- 각 release는 하나 이상의 release-candidate batch를 묶고, profile(`docs-only` | `tooling` | `app-service`)에 맞는 배포와 후속 환류를 추적한다.
+
+## Release Register
+
+| REL ID | Profile | Status | Included Batch | Discovery/REQ Input | Link |
+| --- | --- | --- | --- | --- | --- |
diff --git a/docs/runtime-flows.md b/docs/runtime-flows.md
new file mode 100644
index 0000000..1e01600
--- /dev/null
+++ b/docs/runtime-flows.md
@@ -0,0 +1,84 @@
+# Jarca Ledger MCP Runtime Flows
+
+- Baseline Mode: observed
+- Baseline Seed: `.stage-pilot/bootstrap/baseline.yaml`
+- Status: draft
+- Owner: Jarca / project maintainer
+- Last Updated (KST): 2026-06-26 22:24
+- Source Discovery / Batch: bootstrap-baseline
+- Primary Runtime: mixed
+
+## Project Summary
+- Jarca 가계부 전용 MCP 서버와 Streamlit 대시보드로 계좌/카드 거래, 예산, 분류 규칙, import, 현금흐름 분석을 SQLite에 저장하고 운영한다.
+
+## Purpose
+- This document is the current execution-flow baseline for the project.
+- It is a cross-cutting reference document for Discovery, REQ, Batch Design, Batch Verification, and implementation updates.
+
+## Scope
+- Covers representative command, MCP, dashboard, import, and reconciliation flows.
+- Does not duplicate full acceptance criteria or low-level implementation details.
+
+## Covered Entry Points
+- `jarca-ledger-mcp` :: MCP stdio server for Hermes tool calls.
+- `dashboard/app.py` :: Streamlit local dashboard.
+- `pytest` :: regression test runner.
+
+## Shared Components
+- SQLite database at `~/.local/share/jarca/ledger.sqlite3` by default.
+- `jarca_ledger_mcp.service` as the central domain/service layer.
+- Parser modules for KB/Toss/SeoulPay sources.
+- Category and `cashflow_kind` semantics shared by reports and UI.
+
+## Flow: `MCP server tool call`
+1. Hermes MCP client invokes a tool exposed by `jarca_ledger_mcp.server`.
+2. `server.py` forwards arguments to the matching `service.py` function.
+3. `service.py` opens the SQLite database path from env/default, validates inputs, and performs the operation.
+4. Service returns a dictionary payload with success data or error information.
+5. Hermes surfaces the tool result to the user or uses it in a follow-up workflow.
+
+## Flow: `Streamlit dashboard operation`
+1. Operator starts `streamlit run dashboard/app.py --server.address 0.0.0.0 --server.port 8501`.
+2. Dashboard reads the configured/default SQLite database.
+3. User navigates to 요약, 거래내역, 확인필요 큐, 미분류, 분류 규칙, 카테고리, 계좌, or Import pages.
+4. UI calls service functions for reads, updates, imports, categorization, and manual linking.
+5. UI displays success/error status and refreshes visible tables.
+
+## Flow: `Import preview and import`
+1. Operator chooses or supplies a supported source file: KB Bank PDF, Toss Bank PDF, Toss Securities PDF, SeoulPay XLSX, or CSV.
+2. Preview function parses the file and reports counts, sample rows, duplicate status, and classification preview.
+3. On explicit import, service creates/fetches the target account, inserts non-duplicate transactions, writes raw provenance, and records an import batch.
+4. Reports and dashboard views read the inserted rows using category and cashflow semantics.
+5. If an import is wrong, rollback uses import batch data and soft-deletes by default.
+
+## Flow: `Categorization rule lifecycle`
+1. Operator creates or edits a category rule with match field, pattern, target category/subcategory, priority, and optional amount/day constraints.
+2. Preview categorization shows candidate matches without mutating rows.
+3. Apply categorization updates matching transactions and preserves audit information.
+4. Category `cashflow_kind` controls actual cashflow/report inclusion.
+
+## Flow: `Cross-account and cancel/original reconciliation`
+1. Preview functions search candidate pairs by amount, date, direction, account/source compatibility, and text similarity.
+2. Operator reviews candidates in the dashboard or runs the automatic matcher where confidence rules are satisfied.
+3. Matched self-transfers become `이체 / 본인계좌이동`; investment movements become `이체 / 투자이동`; ambiguous rows remain `확인필요`.
+4. Cancel/refund rows can be linked to original expense rows; memo tags preserve manual link evidence.
+
+## Flow Constraints
+- Preview before broad import or categorization mutation where supported.
+- Do not include `transfer`, `investment`, `exclude`, or unresolved rows in actual household spending totals unless a report explicitly asks for account movement.
+- Preserve raw import evidence for audit and future reclassification.
+- Avoid destructive migrations without a backup/approval plan.
+- Sensitive passwords are runtime inputs and must not be committed.
+
+## Current Gaps / Planned Changes
+- Need final browser-level UX verification for rule delete and cancel/original linking dialogs.
+- Need CI/deployment flow if this project will be maintained beyond local operation.
+- Need a documented operational process for statement-unavailable accounts.
+
+## Update Triggers
+- Update this document when a command entry point changes.
+- Update this document when a runtime orchestration path changes.
+- Update this document when a batch changes the approved flow baseline.
+
+## Change Log
+- 2026-06-26 22:24 KST: Created by `bootstrap-baseline` from repository observation.
diff --git a/docs/srs/index.md b/docs/srs/index.md
new file mode 100644
index 0000000..e8fa934
--- /dev/null
+++ b/docs/srs/index.md
@@ -0,0 +1,46 @@
+# Software Requirement Specification Index
+
+## 목적
+- 이 문서는 프로젝트의 SRS 운영 기준과 requirement 목록을 관리하는 entry point이다.
+- 개별 requirement의 상세 내용은 타입별 폴더 하위 `req-XXX_*.md` 파일에서 관리한다.
+
+## 사용 방법
+1. 새로운 requirement가 필요하면 `Next Requirement ID`를 확인하고 `docs/srs/<Type>/req-XXX_<slug>.md` 파일을 생성한다.
+2. 초안 작성은 `draft-req`, 승인 전환은 `confirm-req`, 변경 대응은 `change-req`, 구현 완료 전환은 `confirm-req-implemented` skill을 기준으로 수행한다.
+3. requirement 추가 또는 변경 후 `Next Requirement ID`, `Requirement Register`, `Recent Change Log Summary`를 함께 갱신한다.
+
+## 상태 정의
+- Proposed: 초안 상태이며 구현 기준으로 확정되지 않음
+- Approved: 구현 기준으로 승인됨
+- Implemented: 구현과 검증이 완료됨
+- Deprecated: 더 이상 유지하지 않음
+
+## Requirement 타입 분류 도표
+
+| 타입 | 정의 | 예시 |
+|------|------|------|
+| **Configuration** | 설정 옵션, 커스터마이징 포인트 | 환경 변수, 옵션 항목 |
+| **Data** | 데이터 구조, 저장/로드, 파일 형식, 스키마 | DB 스키마, import payload |
+| **Deployment** | 배포 방식, 운영 절차, 배포 환경 | 서비스 실행, 운영 가이드 |
+| **Documentation** | 문서 작성, 가이드, 매뉴얼, 안내서 | 사용자 가이드, API 문서 |
+| **Exception** | 오류 처리, 예외 복구, 재시도 전략 | parser 오류, validation 실패 |
+| **Installation** | 시스템 설치, 환경 구성, 초기화 절차 | venv, MCP 등록, DB 초기화 |
+| **Integration** | 외부 시스템 연동, 플러그인, 확장 | KB/토스/서울페이 import |
+| **Interface** | 사용자 상호작용 방식 | MCP tool, Streamlit UI |
+| **Migration** | 데이터 이전, 버전 업그레이드 | SQLite schema migration |
+| **Non-Functional** | 성능, 보안, 확장성, 호환성, 신뢰성 | 개인정보/금융정보 보호, UX 성능 |
+| **Testing** | 테스트 전략, QA 요구사항, 검증 방식 | parser regression, report validation |
+
+## Next Requirement ID
+
+- Current: `REQ-001`
+- Rule: `Requirement Register`에 있는 가장 큰 REQ 번호보다 정확히 1 커야 한다.
+
+## Requirement Register
+
+| ID | Title | Type | Status | Priority | Owner | Link |
+| --- | --- | --- | --- | --- | --- | --- |
+
+## Recent Change Log Summary
+
+- 없음