claudify-agent 1.0.4 → 1.0.6

package/.claude/commands/learn.md

@@ -0,0 +1,16 @@
+---
+description: Turn a mistake I just corrected into a rule so it never repeats
+argument-hint: <what went wrong and what is right>
+---
+
+Lesson to learn: $ARGUMENTS
+
+If the argument is empty, infer the lesson from the correction I made earlier in this conversation.
+
+1. State the lesson as one imperative line: what to do (or never do) and when. Add a one-line why if not obvious.
+2. Pick where it belongs, most specific first:
+   - business invariant of this project → Invariants in `spec/config.md`;
+   - a technology or practice covered by a skill → that `.claude/skills/<name>/SKILL.md`, under a `## Lessons` section;
+   - general working style → `.claude/rules/lessons.md` (always loaded, keep it under 30 lines).
+3. Check the target for an existing rule that covers it; if so, sharpen that line instead of adding a duplicate.
+4. Show me the exact diff and wait for my approval before writing.

package/.claude/commands/spec-apply.md

@@ -0,0 +1,14 @@
+---
+description: Implement the next unchecked tasks of a spec change
+argument-hint: <change-name> [task number]
+---
+
+Implement spec change: $ARGUMENTS
+
+1. Read `spec/changes/<change-name>.md` and the Invariants in `spec/config.md`. Nothing else up front; read code only as each task needs it.
+2. Take the requested task, or the first unchecked `- [ ]` task. Work one task at a time.
+3. Implement it, then run its DoD. Fix until it passes (max 5 attempts, then stop and report).
+4. Tick it `- [x]` in the change file. If reality differs from the spec, update the spec (Requirements/Design) in the same step and tell me.
+5. Report in 2-3 lines: task done, proof run, next task. Continue to the next task only if I asked for more than one.
+
+When every task is ticked, set `Status: done` and suggest `/spec-archive <change-name>`.

package/.claude/commands/spec-archive.md

@@ -0,0 +1,14 @@
+---
+description: Merge a finished change's requirements into the spec backbone and archive it
+argument-hint: <change-name>
+---
+
+Archive spec change: $ARGUMENTS
+
+1. Read `spec/changes/<change-name>.md`. Refuse if any task is unchecked; list them.
+2. For each `### <capability>` block under Requirements, update `spec/specs/<capability>.md` (create if new):
+   - Keep only Requirements and Scenarios: the current truth of the system, no history, no tasks.
+   - ADDED → append. MODIFIED → replace the requirement of the same name in full. REMOVED → delete it.
+   - If a MODIFIED/REMOVED name does not exist in the backbone, stop and ask instead of guessing.
+3. Move the change file to `spec/changes/archive/YYYY-MM-DD-<change-name>.md`.
+4. Show me the diff of `spec/specs/` in a short summary.

package/.claude/commands/spec-new.md

@@ -0,0 +1,39 @@
+---
+description: Draft a lightweight spec for a new feature (single file, ~800 words)
+argument-hint: <change-name> <what the feature should do>
+---
+
+Create a spec change for: $ARGUMENTS
+
+1. Read `spec/config.md` (stop and offer to create it from the template if missing). Read only the `spec/specs/*.md` capabilities this feature touches, and only the source-of-truth sections it needs.
+2. Ask me (one batched question) anything that changes scope. Do not guess scope.
+3. Write `spec/changes/<change-name>.md` with exactly these sections, following the rules in `spec/config.md`:
+
+```markdown
+# <change-name>
+Status: draft | Depends on: <change or none>
+
+## Why
+## Scope
+- In: ...
+- Out (non-goals): ...
+## Requirements
+<!-- One block per affected capability, named like spec/specs/<capability>.md -->
+### <capability> (new | modified)
+#### ADDED Requirement: <name>
+<statement with SHALL/MUST>
+- Scenario <name>: GIVEN ... WHEN ... THEN ...
+#### MODIFIED Requirement: <existing name>
+<full new text, not just the diff>
+#### REMOVED Requirement: <existing name>
+<reason>
+## Design
+<only decisions not obvious from the code: data flow, schema, API, edge cases. Omit section if trivial.>
+## Risks
+## Tasks
+- [ ] 1. <task> — files: ... — DoD: ...
+```
+
+4. Keep the whole file under ~800 words, plus ~300 per extra capability. No restating config, docs or code; link them.
+   If it still does not fit (e.g. more than 4 capabilities), propose splitting into smaller changes with `Depends on:` instead of one giant spec.
+5. Do not write code. Finish by showing the task list and asking me to approve before `/spec-apply`.

package/.claude/rules/context-tier-1.md

@@ -29,9 +29,9 @@ npm run typecheck  # After TypeScript changes
 ## Canonical Examples
 
 ```
-Component pattern: @components/Button.tsx
-API route pattern: @app/api/users/route.ts
-Test pattern: @__tests__/auth.test.ts
+Component pattern: `components/Button.tsx`
+API route pattern: `app/api/users/route.ts`
+Test pattern: `__tests__/auth.test.ts`
 ```
 
 ---

package/.claude/rules/context-tier-2.md

@@ -33,9 +33,9 @@ npm run test:coverage     # With coverage report
 npm run test -- path/to   # Specific file
 
 ## Test Examples
-- Unit test: @__tests__/auth.test.ts
-- Integration: @__tests__/api/users.test.ts
-- E2E: @e2e/checkout.spec.ts
+- Unit test: `__tests__/auth.test.ts`
+- Integration: `__tests__/api/users.test.ts`
+- E2E: `e2e/checkout.spec.ts`
 ```
 
 ---
@@ -55,7 +55,7 @@ npm run test -- path/to   # Specific file
 - Export GET, POST, PUT, DELETE handlers
 
 ## Authentication
-- Validate JWT with @src/auth/validateToken.ts
+- Validate JWT with `src/auth/validateToken.ts`
 - Extract user from token claims
 - Return 401 for unauthorized, 403 for forbidden
 
@@ -78,9 +78,9 @@ try {
 ```
 
 ## API Examples
-- REST pattern: @app/api/users/route.ts
-- Error handling: @app/api/orders/route.ts
-- Validation: @src/validators/orderSchema.ts
+- REST pattern: `app/api/users/route.ts`
+- Error handling: `app/api/orders/route.ts`
+- Validation: `src/validators/orderSchema.ts`
 ```
 
 ---
@@ -124,9 +124,9 @@ export function Button({ variant = 'primary', children }: Props) {
 - Test on multiple screen sizes
 
 ## UI Examples
-- Button: @components/Button.tsx
-- Form: @components/forms/TextInput.tsx
-- Layout: @components/Layout.tsx
+- Button: `components/Button.tsx`
+- Form: `components/forms/TextInput.tsx`
+- Layout: `components/Layout.tsx`
 ```
 
 ---
@@ -152,9 +152,9 @@ export function Button({ variant = 'primary', children }: Props) {
 - Lighthouse Performance: >90
 
 ## Performance Examples
-- Memoization: @components/ExpensiveList.tsx
-- Code splitting: @app/dashboard/page.tsx
-- Caching: @lib/react-query.ts
+- Memoization: `components/ExpensiveList.tsx`
+- Code splitting: `app/dashboard/page.tsx`
+- Caching: `lib/react-query.ts`
 ```
 
 ---
@@ -179,9 +179,9 @@ export function Button({ variant = 'primary', children }: Props) {
 - Index frequently queried fields
 
 ## Database Examples
-- Schema: @prisma/schema.prisma
-- Query pattern: @src/db/queries/users.ts
-- Migration: @prisma/migrations/[latest]
+- Schema: `prisma/schema.prisma`
+- Query pattern: `src/db/queries/users.ts`
+- Migration: `prisma/migrations/[latest]`
 ```
 
 ---
@@ -212,9 +212,9 @@ export function Button({ variant = 'primary', children }: Props) {
 - Escape output to prevent XSS
 
 ## Security Examples
-- Auth middleware: @src/middleware/auth.ts
-- Password hashing: @src/lib/password.ts
-- Input validation: @src/validators/userSchema.ts
+- Auth middleware: `src/middleware/auth.ts`
+- Password hashing: `src/lib/password.ts`
+- Input validation: `src/validators/userSchema.ts`
 ```
 
 ---
@@ -240,9 +240,9 @@ export function Button({ variant = 'primary', children }: Props) {
 - Manual approval for production
 
 ## Deployment Examples
-- CI config: @.github/workflows/ci.yml
-- Build script: @scripts/build.ts
-- Deploy: @scripts/deploy.ts
+- CI config: `.github/workflows/ci.yml`
+- Build script: `scripts/build.ts`
+- Deploy: `scripts/deploy.ts`
 ```
 
 ---

package/.claude/rules/general.md

@@ -22,4 +22,4 @@
 - [ ] Tests passing (auto-run)
 - [ ] Cost within budget (check `.claude/cost-dashboard.md`)
 
-**Note**: See @.claude/rules/ for task-specific rules. Anti-patterns: @.claude/rules/anti-patterns.md
+**Note**: See `.claude/rules/` for task-specific rules. Anti-patterns: `.claude/rules/anti-patterns.md`

package/.claude/rules/plan-mode-structure.md

@@ -85,7 +85,7 @@ Add login button to header navigation following existing button patterns.
 
 ## Files to Modify
 - `components/Header.tsx` - Add login button to nav
-  - Pattern: Follow @components/Button.tsx
+  - Pattern: Follow `components/Button.tsx`
   - Tools: Edit for edit, Lint check for validation
 
 ## Implementation Steps
@@ -119,13 +119,13 @@ Create user dashboard with stats, activity feed, and settings panel.
 
 ## Files to Create
 - `app/dashboard/page.tsx` - Main dashboard page
-  - Pattern: Follow @app/profile/page.tsx
+  - Pattern: Follow `app/profile/page.tsx`
   - Tools: Write for new file
 - `components/dashboard/StatsCard.tsx` - Stats component
-  - Pattern: Follow @components/Card.tsx
+  - Pattern: Follow `components/Card.tsx`
   - Tools: Write for new file
 - `app/api/dashboard/stats/route.ts` - Stats API
-  - Pattern: Follow @app/api/users/route.ts
+  - Pattern: Follow `app/api/users/route.ts`
   - Tools: Write for new file
 
 ## Implementation Steps

package/.claude/rules/tool-strategy.md

@@ -19,4 +19,4 @@ Tier 4: Parallel subagents, Browser MCP
 - context7: Library documentation
 
 ## Pattern
-Follow tool selection examples in @.claude/skills/tool-selection/SKILL.md
+Follow tool selection examples in `.claude/skills/tool-selection/SKILL.md`

package/CLAUDE.md

@@ -1,6 +1,6 @@
 # CLAUDE CORE OPERATING SYSTEM
 
-> **Universal Directive:** You are an autonomous Senior Software Engineer operating via Claude Code / Anthropic Agent loop. Follow these concise, modular instructions. Do not load all guidelines into context; inspect modular files on-demand using `@path` mentions.
+> **Universal Directive:** You are an autonomous Senior Software Engineer operating via Claude Code / Anthropic Agent loop. Follow these concise, modular instructions. Do not load all guidelines into context; Read the referenced files only when the task needs them.
 
 ---
 
@@ -8,43 +8,48 @@
 - Keep responses concise and targeted. Never dump entire files when diffs suffice.
 - Do NOT read whole directory trees. Inspect shallow structure first.
 - Context Tiers (Inspect when prompted):
-  - **Tier 1 (Base):** @.claude/rules/context-tier-1.md
-  - **Tier 2 (Deep Task):** @.claude/rules/context-tier-2.md
-  - **Anti-Patterns:** @.claude/rules/anti-patterns.md
+  - **Tier 1 (Base):** `.claude/rules/context-tier-1.md`
+  - **Tier 2 (Deep Task):** `.claude/rules/context-tier-2.md`
+  - **Anti-Patterns:** `.claude/rules/anti-patterns.md`
 
 ## 2. 📋 Plan First Protocol (Anti-Drift)
 - For tasks touching **>= 2 files** or core architecture:
   - Generate a concise Plan before modifying files.
-  - Research protocol: @.claude/rules/plan-mode-research.md
-  - Execution checklist: @.claude/rules/plan-mode-execution.md
-  - Validation steps: @.claude/rules/plan-mode-validation.md
-  - Plan structure guide: @.claude/rules/plan-mode-structure.md
+  - Research protocol: `.claude/rules/plan-mode-research.md`
+  - Execution checklist: `.claude/rules/plan-mode-execution.md`
+  - Validation steps: `.claude/rules/plan-mode-validation.md`
+  - Plan structure guide: `.claude/rules/plan-mode-structure.md`
+
+## 2b. 📐 Spec Workflow (features only, opt-in by command)
+- `/spec-new` → `/spec-apply` → `/spec-archive`. Specs live in `spec/` (config, changes, specs backbone).
+- Bugs and small tasks: no spec, work directly.
+- After the user corrects a mistake, suggest `/learn` so it never repeats.
 
 ## 3. 🧪 Zero-Token Local Verification Loop
 After modifying code, execute local verification based on project stack:
 - **Node/TS/NestJS:** `npm run lint:fix && npm run typecheck`
 - **Go Backend:** `go vet ./... && go test -race ./...`
 - **Solidity (SMC):** `forge test -vvv` hoặc `npx hardhat test`
-- Core standards: @.claude/rules/general.md & @.claude/rules/security-critical.md
+- Core standards: `.claude/rules/general.md` & `.claude/rules/security-critical.md`
 
 ## 4. 📚 On-Demand Skills Index (Load ONLY When Tech Is Used)
-- **Backend Concurrency & Locking:** @.claude/skills/backend-concurrency/SKILL.md
-- **NestJS Enterprise:** @.claude/skills/nestjs-guide/SKILL.md
-- **Golang Backend:** @.claude/skills/golang-guide/SKILL.md
-- **Solidity (Smart Contracts):** @.claude/skills/solidity-guide/SKILL.md
-- **Next.js:** @.claude/skills/nextjs-guide/SKILL.md
-- **React:** @.claude/skills/react-guide/SKILL.md
-- **Python:** @.claude/skills/python-guide/SKILL.md
-- **Security (OWASP):** @.claude/skills/security-guide/SKILL.md
-- **Vite:** @.claude/skills/vite-guide/SKILL.md
-- **MCP Mastery:** @.claude/skills/mcp-mastery/SKILL.md
-- **Tool Selection:** @.claude/skills/tool-selection/SKILL.md
-- **Debug Optimizer:** @.claude/skills/debug-optimizer/SKILL.md
-- **Parallel Exploration:** @.claude/skills/parallel-exploration/SKILL.md
-- **Learning Loop:** @.claude/skills/learning-loop/SKILL.md
+- **Backend Concurrency & Locking:** `.claude/skills/backend-concurrency/SKILL.md`
+- **NestJS Enterprise:** `.claude/skills/nestjs-guide/SKILL.md`
+- **Golang Backend:** `.claude/skills/golang-guide/SKILL.md`
+- **Solidity (Smart Contracts):** `.claude/skills/solidity-guide/SKILL.md`
+- **Next.js:** `.claude/skills/nextjs-guide/SKILL.md`
+- **React:** `.claude/skills/react-guide/SKILL.md`
+- **Python:** `.claude/skills/python-guide/SKILL.md`
+- **Security (OWASP):** `.claude/skills/security-guide/SKILL.md`
+- **Vite:** `.claude/skills/vite-guide/SKILL.md`
+- **MCP Mastery:** `.claude/skills/mcp-mastery/SKILL.md`
+- **Tool Selection:** `.claude/skills/tool-selection/SKILL.md`
+- **Debug Optimizer:** `.claude/skills/debug-optimizer/SKILL.md`
+- **Parallel Exploration:** `.claude/skills/parallel-exploration/SKILL.md`
+- **Learning Loop:** `.claude/skills/learning-loop/SKILL.md`
 
 ## 5. 🔌 Tool & MCP Strategy
-- Auto Tool Selection: @.claude/rules/tool-auto-selection.md
-- Tool Strategy: @.claude/rules/tool-strategy.md
-- MCP Auto-Usage: @.claude/rules/mcp-auto-use.md
-- MCP Integration Guide: @.claude/docs/MCP-INTEGRATION-GUIDE.md
+- Auto Tool Selection: `.claude/rules/tool-auto-selection.md`
+- Tool Strategy: `.claude/rules/tool-strategy.md`
+- MCP Auto-Usage: `.claude/rules/mcp-auto-use.md`
+- MCP Integration Guide: `.claude/docs/MCP-INTEGRATION-GUIDE.md`

package/bin/cli.js

@@ -41,6 +41,15 @@ if (command === 'init') {
       console.log(`  ⚠️  Kept your existing .claude/settings.json — merge the "hooks" block from ${settingsSrc} manually.`);
     }
 
+    // 3. Scaffold spec/ for the feature workflow (never overwrite an existing config)
+    const specConfig = join(targetDir, 'spec', 'config.md');
+    if (existsSync(specConfig)) {
+      console.log('  ⚠️  Kept your existing spec/config.md');
+    } else {
+      await cp(join(packageRoot, 'templates', 'spec', 'config.md'), specConfig);
+      console.log('  ✅ Created spec/config.md (fill in context & invariants, then use /spec-new)');
+    }
+
     console.log('\n🎉 Successfully initialized Claudify!');
     console.log('👉 Next Steps:');
     console.log('   - Review CLAUDE.md in your project root.');

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claudify-agent",
-  "version": "1.0.4",
+  "version": "1.0.6",
   "description": "Enterprise-grade workflow & context optimization framework for Claude Code, Claude Desktop, and AI coding agents.",
   "repository": {
     "type": "git",
@@ -16,6 +16,7 @@
     "CLAUDE.md",
     ".claude",
     "bin",
+    "templates",
     "README.md",
     "package.json"
   ],

package/templates/spec/config.md

@@ -0,0 +1,27 @@
+# Spec Config
+
+> Read by `/spec-new` and `/spec-apply` only. Keep it short: every line here is paid for on each spec command.
+
+## Context
+- Project: <one or two lines: what the system does>
+- Stack: <languages, frameworks>
+- Sources of truth (read before writing a change): <design docs, ADRs>. If a change contradicts them, stop and say so.
+
+## Invariants
+<!-- Rules every change MUST respect. One line each. -->
+- <e.g. money amounts are integers in base units, never floats>
+
+## Style
+- Language: <e.g. Vietnamese prose, English technical terms and spec keywords>
+- Concise: bullets, tables, short snippets. Reference docs by section instead of copying them.
+
+## Rules
+### Proposal
+- Must have Why, Scope (in / out = Non-goals), Depends on, Affected capabilities, Risks.
+### Requirements
+- `### Requirement: <name>` containing SHALL or MUST.
+- Each has `#### Scenario:` GIVEN / WHEN / THEN with concrete values: at least one happy path and one failure.
+### Tasks
+- Each task fits in 2-4 hours, lists files/packages touched and its DoD.
+- Tests ship with the task that adds the logic, not at the end.
+- DoD default: <e.g. `npm run lint && npm run typecheck && npm test`>