@baselane/packs 0.1.0

package/packs/database-review/rendered/AGENTS.md

@@ -0,0 +1,66 @@
+# AGENTS.md
+
+<!-- generated from workflow-pack database-review v1.2.0 -->
+<!-- adapted from affaan-m/ECC (MIT) — https://github.com/affaan-m/ECC -->
+
+## Database review discipline
+
+`sqlfluff` catches SQL style and obvious mistakes — this pack is the judgment it can't encode, applied in review of any query, schema, or migration before it reaches production.
+
+### Query performance
+
+- Every column in a `WHERE` or `JOIN` should be indexed — confirm with `EXPLAIN ANALYZE`, don't assume.
+- Watch for N+1: a query inside a loop over rows from a previous query. Batch or join it.
+- Composite indexes put equality columns before range columns.
+
+### Schema design
+
+- Use precise types: timestamp-with-timezone for times, decimal/numeric for money, `text` over an arbitrary varchar cap.
+- Every foreign key gets an index — no exceptions.
+- Put constraints (`NOT NULL`, `CHECK`, `ON DELETE`) in the schema, not only in application code.
+
+### Migration safety
+
+- Adding a `NOT NULL` column to a large table needs a backfill, not just a default — check in-flight writes during the migration.
+- Don't hold locks across an external call or a slow backfill; batch the backfill.
+- Every migration has a rollback path.
+
+### Data-layer security
+
+- Queries are parameterized, never string-concatenated with user input.
+- Multi-tenant tables enforce row-level access at the database, not only in application code.
+- Application database users get least-privilege grants, never blanket admin.
+
+### Flag in review
+
+- `SELECT *` in application code shipped to production.
+- Offset pagination on large, frequently-written tables — prefer cursor pagination.
+- `INSERT`s in a loop instead of a batch/multi-row insert.
+- Inconsistent lock ordering across transactions touching the same tables (deadlock risk).
+
+## Harness capabilities
+
+- system-map · repo · analyze — provisioned
+
+### System map
+
+`ARCHITECTURE.md` carries a generated, baselane-managed system map — languages, layout, commands, import-graph hotspots, and measured conventions including hidden rules (consistent but unenforced). Read its conventions section before writing code, and regenerate with `baselane map .` (or `/map regenerate`) after structural changes.
+
+## Workflow pack: Database review
+
+Query, schema, and migration review judgment a linter can't encode — index every foreign key, kill N+1s, keep queries parameterized, ship migrations that don't lock production — with a reviewer and a sqlfluff guard.
+
+### Roles
+
+- **database-reviewer** — Reviews SQL, schema changes, and migrations for missing indexes, N+1 queries, unsafe migrations, and injection risk. Use when writing queries, schemas, or migrations, or troubleshooting database performance.
+
+### Commands
+
+- **/db-review** `[optional: path or diff ref]` — Run the database-reviewer over the current query, schema, or migration changes.
+  - How it runs: Invoke the database-reviewer subagent over the current diff (or $ARGUMENTS if given). Report findings grouped by area (indexing, schema, migration safety, security) with file:line and fix for each. End with a clear verdict.
+
+### Guardrails
+
+- After an edit, lint SQL and migrations with sqlfluff when it is installed.
+
+Tool-specific implementations live alongside this file (see `CLAUDE.md` for the Claude Code implementation). Tools without a native subagent/command surface should treat the sections above as operating instructions.

package/packs/database-review/rendered/CLAUDE.md

@@ -0,0 +1,9 @@
+# CLAUDE.md
+
+@AGENTS.md
+
+This project defines a native Claude Code implementation of this workflow pack:
+- Subagent: `.claude/agents/database-reviewer.md`
+- Command: `.claude/commands/db-review.md`
+- Command: `.claude/commands/map.md`
+- Hooks: see `.claude/settings.json`

package/packs/database-review/rendered/GEMINI.md

@@ -0,0 +1,3 @@
+# GEMINI.md
+
+@AGENTS.md

package/packs/disciplined-workflow/pack.json

@@ -0,0 +1,63 @@
+{
+  "$schema": "https://baselane.dev/schema/workflow-pack-v1.json",
+  "id": "disciplined-workflow",
+  "version": "1.1.0",
+  "title": "Disciplined workflow",
+  "summary": "The plan-first pipeline with hard approval gates: a written design signed off before any code, a path-exact task plan, then task-by-task spec-then-quality review — for teams that need explicit sign-off at each stage. Pick the software-engineer harness instead for the same loop without gates.",
+  "scope": "both",
+  "attribution": { "source": "obra/superpowers", "url": "https://github.com/obra/superpowers", "license": "MIT" },
+  "context": {
+    "markdown": "## Disciplined workflow\n\n- Plan before you build: for any change beyond a one-sentence diff, produce a short written design and get it approved before writing implementation code.\n- Decompose the approved design into small, independently verifiable tasks — each with exact file paths and a verification step.\n- Evidence before claims: never report work done without the verification output (the command you ran and its result) to back it.\n- Isolate feature work in a git worktree or branch — never directly on the main line.\n"
+  },
+  "agents": [
+    {
+      "name": "plan-reviewer",
+      "description": "Checks a plan for placeholders, undefined references, and coverage gaps before execution starts.",
+      "tools": ["Read", "Grep", "Glob"],
+      "model": "sonnet",
+      "prompt": "You are a plan reviewer. Read the plan and the design it derives from. Flag every placeholder (TBD/TODO/\"handle edge cases\"), every reference to a file, type, or function that no task defines, and every design requirement no task covers — citing the exact location in the plan for each. Approve only when the plan is executable with zero placeholders and full design coverage."
+    },
+    {
+      "name": "task-reviewer",
+      "description": "Reviews one completed task in two ordered verdicts: spec compliance first, then code quality.",
+      "tools": ["Read", "Grep", "Glob", "Bash"],
+      "model": "sonnet",
+      "prompt": "You are a task reviewer returning two ordered verdicts. Part 1 — Spec compliance: does the change do exactly what the task specified, nothing missing and nothing extra? Part 2 — Code quality: error handling, edge cases, test realism, naming. Cite file:line for every finding, categorize each Critical/Important/Minor, and give both verdicts explicitly. Do not pass a task while any Critical or Important finding is open."
+    }
+  ],
+  "commands": [
+    {
+      "name": "brainstorm",
+      "description": "Interview toward an approved written design before any implementation.",
+      "argument_hint": "[what to build]",
+      "prompt": "Interview the requester about $ARGUMENTS to surface intent, constraints, and edge cases, then write a short design doc and get explicit approval. Do not write or invoke any implementation until the design is approved."
+    },
+    {
+      "name": "write-plan",
+      "description": "Decompose an approved design into verifiable, path-exact tasks.",
+      "argument_hint": "[design doc or feature]",
+      "prompt": "Turn the approved design for $ARGUMENTS into a task-by-task plan: each task names the exact files to create or modify, the failing test to write first, and how it will be verified. No task may contain a placeholder or a reference to anything no task defines. Then invoke the plan-reviewer subagent and fix anything it flags before execution."
+    },
+    {
+      "name": "execute-plan",
+      "description": "Run the plan task-by-task with per-task spec-then-quality review.",
+      "argument_hint": "[plan file]",
+      "prompt": "Execute the plan in $ARGUMENTS one task at a time. After each task, invoke the task-reviewer subagent for its two ordered verdicts — spec compliance, then code quality — and do not advance while any Critical or Important finding is open."
+    }
+  ],
+  "hooks": [
+    {
+      "event": "Stop",
+      "matcher": "",
+      "description": "Reminds that a claim of done must carry its verification output.",
+      "action": "print-reminder",
+      "message": "Before reporting done, show the verification output — the command you ran and its result. Evidence before claims."
+    }
+  ],
+  "onboarding": [
+    { "id": "init-task-ledger", "title": "Initialize the task ledger", "description": "Create the task ledger for planning and progress tracking.", "command": "baselane tasks init" }
+  ],
+  "capabilities": [
+    { "type": "tasks", "store": "repo", "method": "ledger" }
+  ]
+}

package/packs/disciplined-workflow/rendered/.baselane/capabilities.json

@@ -0,0 +1,10 @@
+{
+  "version": 1,
+  "capabilities": [
+    {
+      "type": "tasks",
+      "store": "repo",
+      "method": "ledger"
+    }
+  ]
+}

package/packs/disciplined-workflow/rendered/.baselane/tasks/README.md

@@ -0,0 +1,36 @@
+# Tasks & progress ledger
+
+This directory anchors multi-session AI work so it survives context compaction — the
+plan lives in one file, completed work is logged in another, and neither depends on
+what an agent remembers from a prior session.
+
+## Files
+
+- `PLAN.md` — at the repo root, or `.baselane/tasks/PLAN.md` if the root is reserved
+  for something else. The plan, as bite-size checkboxed tasks:
+
+  ```markdown
+  - [ ] Add the tasks-ledger capability
+  - [x] Wire render-pack.ts and bundle.ts
+  ```
+
+- `.baselane/tasks/progress.md` — an append-only ledger, one line per completed step,
+  each with a commit reference:
+
+  ```markdown
+  - 2026-07-09: Wired render-pack.ts and bundle.ts — commit `a1b2c3d`
+  ```
+
+  Never rewrite a line once it's committed to the ledger — only append.
+
+## Rule
+
+- **On session start, read the ledger before the plan.** `progress.md` says what is
+  actually done; `PLAN.md` says what was intended. Trust the ledger and `git log`
+  over either your own memory or a stale-looking checkbox — a checkbox can lag behind
+  reality, but a completed-and-committed ledger line cannot.
+- **Append after each completed step**, not in a batch at the end of the session. The
+  ledger's value is that it survives a compaction or a dropped session mid-task; a step
+  that isn't logged until "later" is a step that can be lost.
+- Use `/plan-work` to draft or refresh `PLAN.md` as checkboxed tasks from a spec or
+  requirement.

package/packs/disciplined-workflow/rendered/.claude/agents/plan-reviewer.md

@@ -0,0 +1,8 @@
+---
+name: plan-reviewer
+description: Checks a plan for placeholders, undefined references, and coverage gaps before execution starts.
+tools: Read, Grep, Glob
+model: sonnet
+---
+
+You are a plan reviewer. Read the plan and the design it derives from. Flag every placeholder (TBD/TODO/"handle edge cases"), every reference to a file, type, or function that no task defines, and every design requirement no task covers — citing the exact location in the plan for each. Approve only when the plan is executable with zero placeholders and full design coverage.

package/packs/disciplined-workflow/rendered/.claude/agents/task-reviewer.md

@@ -0,0 +1,8 @@
+---
+name: task-reviewer
+description: Reviews one completed task in two ordered verdicts: spec compliance first, then code quality.
+tools: Read, Grep, Glob, Bash
+model: sonnet
+---
+
+You are a task reviewer returning two ordered verdicts. Part 1 — Spec compliance: does the change do exactly what the task specified, nothing missing and nothing extra? Part 2 — Code quality: error handling, edge cases, test realism, naming. Cite file:line for every finding, categorize each Critical/Important/Minor, and give both verdicts explicitly. Do not pass a task while any Critical or Important finding is open.

package/packs/disciplined-workflow/rendered/.claude/commands/brainstorm.md

@@ -0,0 +1,6 @@
+---
+description: Interview toward an approved written design before any implementation.
+argument-hint: [what to build]
+---
+
+Interview the requester about $ARGUMENTS to surface intent, constraints, and edge cases, then write a short design doc and get explicit approval. Do not write or invoke any implementation until the design is approved.

package/packs/disciplined-workflow/rendered/.claude/commands/execute-plan.md

@@ -0,0 +1,6 @@
+---
+description: Run the plan task-by-task with per-task spec-then-quality review.
+argument-hint: [plan file]
+---
+
+Execute the plan in $ARGUMENTS one task at a time. After each task, invoke the task-reviewer subagent for its two ordered verdicts — spec compliance, then code quality — and do not advance while any Critical or Important finding is open.

package/packs/disciplined-workflow/rendered/.claude/commands/plan-work.md

@@ -0,0 +1,6 @@
+---
+description: Draft or refresh PLAN.md as bite-size checkboxed tasks.
+argument-hint: <goal or spec>
+---
+
+Draft or refresh `PLAN.md` (repo root, or `.baselane/tasks/PLAN.md` if the root is reserved) for $ARGUMENTS: break the goal into bite-size, independently verifiable, checkboxed tasks (`- [ ] ...`). If `PLAN.md` already exists, first reconcile it against `.baselane/tasks/progress.md` — check off anything the ledger shows as done — then add only the tasks still remaining.

package/packs/disciplined-workflow/rendered/.claude/commands/write-plan.md

@@ -0,0 +1,6 @@
+---
+description: Decompose an approved design into verifiable, path-exact tasks.
+argument-hint: [design doc or feature]
+---
+
+Turn the approved design for $ARGUMENTS into a task-by-task plan: each task names the exact files to create or modify, the failing test to write first, and how it will be verified. No task may contain a placeholder or a reference to anything no task defines. Then invoke the plan-reviewer subagent and fix anything it flags before execution.

package/packs/disciplined-workflow/rendered/.claude/settings.json

@@ -0,0 +1,24 @@
+{
+  "hooks": {
+    "Stop": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "echo \"Before reporting done, show the verification output — the command you ran and its result. Evidence before claims.\""
+          }
+        ]
+      },
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "echo \"Before finishing, append any steps completed this session to .baselane/tasks/progress.md with a commit reference, and check off finished tasks in PLAN.md.\""
+          }
+        ]
+      }
+    ]
+  }
+}

package/packs/disciplined-workflow/rendered/.github/copilot-instructions.md

@@ -0,0 +1,24 @@
+# Copilot instructions
+
+## Disciplined workflow
+
+- Plan before you build: for any change beyond a one-sentence diff, produce a short written design and get it approved before writing implementation code.
+- Decompose the approved design into small, independently verifiable tasks — each with exact file paths and a verification step.
+- Evidence before claims: never report work done without the verification output (the command you ran and its result) to back it.
+- Isolate feature work in a git worktree or branch — never directly on the main line.
+
+## Workflow pack: Disciplined workflow
+
+The plan-first pipeline with hard approval gates: a written design signed off before any code, a path-exact task plan, then task-by-task spec-then-quality review — for teams that need explicit sign-off at each stage. Pick the software-engineer harness instead for the same loop without gates.
+
+When acting as the plan-reviewer role: You are a plan reviewer. Read the plan and the design it derives from. Flag every placeholder (TBD/TODO/"handle edge cases"), every reference to a file, type, or function that no task defines, and every design requirement no task covers — citing the exact location in the plan for each. Approve only when the plan is executable with zero placeholders and full design coverage.
+
+When acting as the task-reviewer role: You are a task reviewer returning two ordered verdicts. Part 1 — Spec compliance: does the change do exactly what the task specified, nothing missing and nothing extra? Part 2 — Code quality: error handling, edge cases, test realism, naming. Cite file:line for every finding, categorize each Critical/Important/Minor, and give both verdicts explicitly. Do not pass a task while any Critical or Important finding is open.
+
+Workflow steps:
+
+- brainstorm: Interview the requester about $ARGUMENTS to surface intent, constraints, and edge cases, then write a short design doc and get explicit approval. Do not write or invoke any implementation until the design is approved.
+- write-plan: Turn the approved design for $ARGUMENTS into a task-by-task plan: each task names the exact files to create or modify, the failing test to write first, and how it will be verified. No task may contain a placeholder or a reference to anything no task defines. Then invoke the plan-reviewer subagent and fix anything it flags before execution.
+- execute-plan: Execute the plan in $ARGUMENTS one task at a time. After each task, invoke the task-reviewer subagent for its two ordered verdicts — spec compliance, then code quality — and do not advance while any Critical or Important finding is open.
+
+- Before reporting done, show the verification output — the command you ran and its result. Evidence before claims.

package/packs/disciplined-workflow/rendered/AGENTS.md

@@ -0,0 +1,43 @@
+# AGENTS.md
+
+<!-- generated from workflow-pack disciplined-workflow v1.1.0 -->
+<!-- adapted from obra/superpowers (MIT) — https://github.com/obra/superpowers -->
+
+## Disciplined workflow
+
+- Plan before you build: for any change beyond a one-sentence diff, produce a short written design and get it approved before writing implementation code.
+- Decompose the approved design into small, independently verifiable tasks — each with exact file paths and a verification step.
+- Evidence before claims: never report work done without the verification output (the command you ran and its result) to back it.
+- Isolate feature work in a git worktree or branch — never directly on the main line.
+
+## Harness capabilities
+
+- tasks · repo · ledger — provisioned
+
+### Tasks
+
+On session start, read `.baselane/tasks/progress.md` before `PLAN.md` — trust the ledger and `git log` over memory. Use `/plan-work` to draft or refresh `PLAN.md`, and append to the ledger after each completed step.
+
+## Workflow pack: Disciplined workflow
+
+The plan-first pipeline with hard approval gates: a written design signed off before any code, a path-exact task plan, then task-by-task spec-then-quality review — for teams that need explicit sign-off at each stage. Pick the software-engineer harness instead for the same loop without gates.
+
+### Roles
+
+- **plan-reviewer** — Checks a plan for placeholders, undefined references, and coverage gaps before execution starts.
+- **task-reviewer** — Reviews one completed task in two ordered verdicts: spec compliance first, then code quality.
+
+### Commands
+
+- **/brainstorm** `[what to build]` — Interview toward an approved written design before any implementation.
+  - How it runs: Interview the requester about $ARGUMENTS to surface intent, constraints, and edge cases, then write a short design doc and get explicit approval. Do not write or invoke any implementation until the design is approved.
+- **/write-plan** `[design doc or feature]` — Decompose an approved design into verifiable, path-exact tasks.
+  - How it runs: Turn the approved design for $ARGUMENTS into a task-by-task plan: each task names the exact files to create or modify, the failing test to write first, and how it will be verified. No task may contain a placeholder or a reference to anything no task defines. Then invoke the plan-reviewer subagent and fix anything it flags before execution.
+- **/execute-plan** `[plan file]` — Run the plan task-by-task with per-task spec-then-quality review.
+  - How it runs: Execute the plan in $ARGUMENTS one task at a time. After each task, invoke the task-reviewer subagent for its two ordered verdicts — spec compliance, then code quality — and do not advance while any Critical or Important finding is open.
+
+### Guardrails
+
+- Reminds that a claim of done must carry its verification output.
+
+Tool-specific implementations live alongside this file (see `CLAUDE.md` for the Claude Code implementation). Tools without a native subagent/command surface should treat the sections above as operating instructions.

package/packs/disciplined-workflow/rendered/CLAUDE.md

@@ -0,0 +1,12 @@
+# CLAUDE.md
+
+@AGENTS.md
+
+This project defines a native Claude Code implementation of this workflow pack:
+- Subagent: `.claude/agents/plan-reviewer.md`
+- Subagent: `.claude/agents/task-reviewer.md`
+- Command: `.claude/commands/brainstorm.md`
+- Command: `.claude/commands/write-plan.md`
+- Command: `.claude/commands/execute-plan.md`
+- Command: `.claude/commands/plan-work.md`
+- Hooks: see `.claude/settings.json`

package/packs/disciplined-workflow/rendered/GEMINI.md

@@ -0,0 +1,3 @@
+# GEMINI.md
+
+@AGENTS.md