kodelyth-ecc 1.2.2 → 1.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (46) hide show
  1. package/AGENTS.md +101 -181
  2. package/CHANGELOG.md +67 -0
  3. package/CLAUDE.md +72 -63
  4. package/KODELYTH.md +79 -44
  5. package/README.md +244 -192
  6. package/VERSION +1 -1
  7. package/agents/dependency-doctor.md +120 -0
  8. package/agents/env-debugger.md +154 -0
  9. package/agents/flake-hunter.md +142 -0
  10. package/agents/git-rescue.md +133 -0
  11. package/agents/kodelyth-memory.md +87 -0
  12. package/agents/release-captain.md +190 -0
  13. package/bin/kodelyth-ecc.js +18 -12
  14. package/commands/memory.md +62 -0
  15. package/hooks/hooks.json +26 -0
  16. package/hooks/memory/capture-stop.js +88 -0
  17. package/hooks/memory/inject-start.js +60 -0
  18. package/install.ps1 +28 -9
  19. package/install.sh +11 -97
  20. package/package.json +4 -2
  21. package/rules/common/agent-intent-routing.md +337 -0
  22. package/rules/common/memory-protocol.md +56 -0
  23. package/scripts/memory/cli.js +200 -0
  24. package/scripts/memory/extract.js +176 -0
  25. package/scripts/memory/inject.js +145 -0
  26. package/scripts/memory/store.js +300 -0
  27. package/skills/agent-handoff/SKILL.md +184 -0
  28. package/skills/intent-routing/SKILL.md +134 -0
  29. package/skills/kodelyth-memory/SKILL.md +136 -0
  30. package/tests/memory/store.test.js +121 -0
  31. package/dashboard/lib/agent-tracker.js +0 -366
  32. package/dashboard/lib/aggregator.js +0 -119
  33. package/dashboard/lib/cost-calculator.js +0 -50
  34. package/dashboard/lib/platform-detector.js +0 -89
  35. package/dashboard/lib/readers/antigravity-reader.js +0 -113
  36. package/dashboard/lib/readers/claude-reader.js +0 -135
  37. package/dashboard/lib/readers/codex-reader.js +0 -192
  38. package/dashboard/lib/readers/cursor-reader.js +0 -135
  39. package/dashboard/lib/readers/opencode-reader.js +0 -201
  40. package/dashboard/lib/readers/windsurf-reader.js +0 -146
  41. package/dashboard/package.json +0 -24
  42. package/dashboard/public/index.html +0 -1221
  43. package/dashboard/server.js +0 -119
  44. package/scripts/agent-tracker-hook.js +0 -81
  45. package/social/readme-lens.svg +0 -140
  46. package/social/readme-savings.svg +0 -56
package/README.md CHANGED
@@ -4,57 +4,70 @@
4
4
 
5
5
  [![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
6
6
  ![Claude Code](https://img.shields.io/badge/Claude%20Code-Ready-8A2BE2)
7
+ ![Windsurf](https://img.shields.io/badge/Windsurf-Ready-06b6d4)
7
8
  ![Antigravity](https://img.shields.io/badge/Antigravity-Ready-00ADD8)
8
- ![Version](https://img.shields.io/badge/version-1.2.0-orange)
9
- ![Agents](https://img.shields.io/badge/Agents-53-brightgreen)
10
- ![Skills](https://img.shields.io/badge/Skills-185-brightgreen)
9
+ ![Cursor](https://img.shields.io/badge/Cursor-Ready-3b82f6)
10
+ ![Codex](https://img.shields.io/badge/Codex-Ready-10b981)
11
+ ![Version](https://img.shields.io/badge/version-1.4.0-orange)
12
+ ![Agents](https://img.shields.io/badge/Agents-59-brightgreen)
13
+ ![Skills](https://img.shields.io/badge/Skills-188-brightgreen)
14
+ ![Memory](https://img.shields.io/badge/Local%20Memory-on-blueviolet)
11
15
 
12
16
  </div>
13
17
 
14
- **Kodelyth ECC** is a battle-tested, production-ready AI coding toolkit — 53 specialist agents, 185 skills, 79 commands, automated quality gates, and a real-time usage dashboard built in. Built and maintained by **Kodelyth**.
18
+ **Kodelyth ECC** is a production-grade AI coding toolkit — **59 specialist agents, 188 skills, 80 commands**, a god-tier **intent-routing system**, and **local self-learning memory** that gets smarter at helping *you* every session.
15
19
 
16
- Works with **Claude Code**, **Google Antigravity**, **Cursor**, **Codex CLI**, and **OpenCode**.
20
+ Works with **Claude Code**, **Windsurf**, **Cursor**, **Codex CLI**, **Google Antigravity**, and **OpenCode**.
21
+
22
+ > No dashboard. No telemetry. No cloud. Just rules, agents, skills, and your own private memory store — all on your disk.
17
23
 
18
24
  ---
19
25
 
20
- ## Install
26
+ ## What Makes ECC Different
21
27
 
22
- ### Option 1 npx from npm (Node.js 18+, any platform)
28
+ Most "AI agent kits" are folders of markdown files you have to remember the names of. ECC has **intent routing** baked into the rules layer — you describe your problem in plain words, the AI announces which specialist is taking over, and you get senior-grade help without memorizing a directory.
23
29
 
24
- The simplest install. Node.js is the only requirement.
30
+ ```
31
+ You: "I've been staring at this NullPointerException for two hours,
32
+ I'm losing my mind."
25
33
 
26
- ```bash
27
- npx kodelyth-ecc
34
+ AI: → Routing to debug-detective (your error + frustration matches the bug-tracking signal)
35
+
36
+ That kind of bug is exhausting — let's trace it properly so we
37
+ fix the root cause, not the symptom.
38
+
39
+ First, can you share the full stack trace and...
28
40
  ```
29
41
 
30
- Install for a specific platform:
42
+ You never typed `use debug-detective`. You didn't have to.
43
+
44
+ ---
45
+
46
+ ## Install
47
+
48
+ ### Option 1 — npx from npm (recommended, any platform)
31
49
 
32
50
  ```bash
33
- npx kodelyth-ecc --target windsurf-project # Windsurf (project)
51
+ npx kodelyth-ecc # Claude Code (default)
52
+ npx kodelyth-ecc --target windsurf-project # Windsurf (per-project)
34
53
  npx kodelyth-ecc --target windsurf-home # Windsurf (global)
35
- npx kodelyth-ecc --target antigravity # Google Antigravity
36
54
  npx kodelyth-ecc --target cursor-project # Cursor IDE
37
55
  npx kodelyth-ecc --target codex-home # Codex CLI
56
+ npx kodelyth-ecc --target antigravity # Google Antigravity
38
57
  npx kodelyth-ecc --target opencode # OpenCode
39
58
  ```
40
59
 
41
- > Node.js not installed? Download it from [nodejs.org](https://nodejs.org) LTS version recommended.
42
-
43
- ---
60
+ Node.js 18+ required. [Download Node](https://nodejs.org) if you don't have it.
44
61
 
45
62
  ### Option 2 — npx from GitHub (always latest commit)
46
63
 
47
- Use this if you want the very latest unreleased version directly from the main branch.
48
-
49
64
  ```bash
50
65
  npx github:sifxprime/kodelyth-ecc
51
66
  ```
52
67
 
53
- Same `--target` flags apply.
54
-
55
- ---
68
+ Same `--target` flags work.
56
69
 
57
- ### Option 3 — curl (macOS / Linux)
70
+ ### Option 3 — curl (macOS / Linux only)
58
71
 
59
72
  ```bash
60
73
  curl -fsSL https://raw.githubusercontent.com/sifxprime/kodelyth-ecc/main/install.sh | bash
@@ -66,198 +79,190 @@ With a target:
66
79
  curl -fsSL https://raw.githubusercontent.com/sifxprime/kodelyth-ecc/main/install.sh | bash -s -- --target windsurf-project
67
80
  ```
68
81
 
69
- ---
70
-
71
- ### Option 4 — clone and run (all platforms)
82
+ ### Option 4 — Clone and run
72
83
 
73
84
  ```bash
74
85
  git clone https://github.com/sifxprime/kodelyth-ecc.git
75
86
  cd kodelyth-ecc
76
87
 
77
88
  # macOS / Linux
78
- ./install.sh # Claude Code (default)
79
- ./install.sh --target windsurf-project # Windsurf
80
- ./install.sh --target antigravity # Google Antigravity
89
+ ./install.sh # Claude Code (default)
90
+ ./install.sh --target windsurf-project # Windsurf
81
91
 
82
92
  # Windows (PowerShell)
83
93
  .\install.ps1
84
94
  .\install.ps1 -Target windsurf-project
85
- .\install.ps1 -Target codex-home
86
95
  ```
87
96
 
88
97
  ---
89
98
 
90
- The installer automatically starts **Kodelyth Lens** and opens your browser when done (Claude Code target only).
91
-
92
- ---
93
-
94
- ## Kodelyth Lens — AI Usage Dashboard
99
+ ## How Intent Routing Works
95
100
 
96
- <img src="social/readme-lens.svg" alt="Kodelyth Lens Dashboard" width="900"/>
101
+ The toolkit ships with a single rule file (`rules/common/agent-intent-routing.md`) that the AI loads automatically on every session. It maps **what you say** to **the right specialist agent** across 10 priority tiers.
97
102
 
98
- **Kodelyth Lens** is a zero-dependency real-time dashboard included with every ECC install. It reads directly from your AI coding platform data files — no cloud, no account, no npm install.
103
+ ### Two activation paths
99
104
 
100
- <img src="social/readme-savings.svg" alt="ECC Cost Savings" width="900"/>
105
+ **1. Explicit** type it directly:
106
+ ```
107
+ use debug-detective
108
+ @code-reviewer
109
+ invoke security-reviewer
110
+ ```
101
111
 
102
- ### What Lens tracks
112
+ **2. Implicit** just describe your problem; the AI routes you:
103
113
 
104
- | Signal | How it works |
114
+ | What you write | Auto-routed to |
105
115
  |---|---|
106
- | Agent invocations | Explicit: `use <agent>`, `@agent`, `invoke agent` |
107
- | Agent intent | 12 intent categories — "bug" debug-detective, "slow" → performance-optimizer |
108
- | Token usage | Reads session JSONL files per platform |
109
- | Cache savings | Cache read tokens cost 10% — ECC prompt structure maximizes hits |
110
- | Platform breakdown | Per-platform session count, tokens, and cost |
111
- | Cost comparison | Actual paid vs. estimated without-ECC cost |
116
+ | "I'm stuck, no idea where to start" | `kodelyth-advisor` |
117
+ | "I've been debugging this for hours" | `debug-detective` |
118
+ | "Should I use Context or Zustand?" | `pair-programmer` |
119
+ | "Build failed on Vercel" | `build-error-resolver` |
120
+ | "Is this JWT signing secure?" | `security-reviewer` |
121
+ | "Why is this so slow?" | `performance-optimizer` |
122
+ | "Plan the v2 migration" | `planner` + `migration-guide` |
123
+ | "Tests pass locally but fail on CI" | `flake-hunter` + `env-debugger` |
124
+ | "I lost my commits after `reset --hard`" | `git-rescue` |
125
+ | "npm install is failing" | `dependency-doctor` |
126
+ | "Cut a 1.4 release" | `release-captain` |
127
+ | "Add accessibility to this form" | `ux-reviewer` |
128
+ | "Open-source this project" | `opensource-forker` (chain) |
129
+
130
+ The AI **always announces** which agent is taking over (`→ Routing to <agent>`) and **always teaches** you the explicit form for next time (`Tip: type "use <agent>"`). No silent personality changes.
131
+
132
+ ### Multi-agent chains
133
+
134
+ Real problems span multiple specialties. ECC ships standard handoff chains:
112
135
 
113
- ### Supported platforms
114
-
115
- | Platform | Data source | Sessions |
116
- |---|---|---|
117
- | Claude Code | `~/.claude/projects/**/*.jsonl` | Full local logs |
118
- | Codex CLI | `~/.codex/state_5.sqlite` | SQLite threads table |
119
- | Windsurf | `~/Library/Application Support/Windsurf/` | Cloud AI (server-side) |
120
- | Antigravity | `~/Library/Application Support/Antigravity/` | Cloud AI (server-side) |
121
- | Cursor | `~/.cursor/` | Local workspace data |
122
- | OpenCode | `~/.opencode/` | Local session files |
123
-
124
- Only installed platforms appear in the dashboard — nothing shown for platforms you don't have.
125
-
126
- ### Manual start
127
-
128
- ```bash
129
- node ~/.kodelyth/lens/server.js
130
- # → http://localhost:3456
131
136
  ```
132
-
133
- ### Environment overrides
134
-
135
- ```bash
136
- CLAUDE_DIR=~/.claude # Custom Claude Code data dir
137
- CURSOR_DIR=... # Custom Cursor data dir
138
- WINDSURF_DIR=... # Custom Windsurf data dir
139
- CODEX_DIR=~/.codex # Custom Codex data dir
140
- OPENCODE_DIR=~/.opencode # Custom OpenCode data dir
141
- ANTIGRAVITY_DIR=... # Custom Antigravity data dir
142
- PORT=3456 # Dashboard port (default: 3456)
137
+ pair-programmer → tdd-guide → code-reviewer → security-reviewer
138
+ (approach) (write tests) (review impl) (auth, validation)
143
139
  ```
144
140
 
145
- ---
141
+ ```
142
+ debug-detective → tdd-guide → refactor-cleaner
143
+ (root cause) (regression test) (cleanup)
144
+ ```
146
145
 
147
- ## What's Inside
146
+ ```
147
+ opensource-forker → opensource-sanitizer → opensource-packager → release-captain
148
+ (clean fork) (strip secrets) (README, license) (cut v0.1.0)
149
+ ```
148
150
 
149
- | Component | Count | Description |
150
- |---|---|---|
151
- | Agents | **53** | Specialist subagents — reviewers, planners, debuggers, architects |
152
- | Skills | **185** | Domain knowledge — patterns, testing, security, DevOps |
153
- | Commands | **79** | Slash command workflows (`/tdd`, `/plan`, `/code-review`, etc.) |
154
- | Hooks | **15+** | Automated lifecycle triggers — quality gates, session memory, cost tracking |
155
- | Rules | **15** | Language-specific coding standards |
151
+ See `skills/agent-handoff/SKILL.md` for the full handoff protocol and standard chains.
156
152
 
157
153
  ---
158
154
 
159
- ## Agent Arsenal
155
+ ## Kodelyth Memory — Local Self-Learning (new in v1.4.0)
160
156
 
161
- <img src="social/readme-agents.svg" alt="53 Specialist Agents" width="900"/>
162
-
163
- ### Kodelyth Exclusives
164
-
165
- ### `kodelyth-advisor` — The Master Guide
166
- A decade-seasoned principal engineer who reads your emotional state, understands what you're struggling with, and gives you the exact tool or approach needed. No hand-holding, no noise — direct senior-grade direction.
157
+ The first time you solve a hard problem, ECC remembers what worked. The next time you hit something similar, your AI surfaces the past solution before you ask.
167
158
 
168
159
  ```
169
- use kodelyth-advisor
160
+ Session 1 (March):
161
+ You: "Stripe webhook signatures are failing in production"
162
+ AI: [helps you debug, you discover raw body parser is required]
163
+ You: "Perfect, that worked, thanks"
164
+ → ECC's Stop hook queues the lesson for review.
165
+ → You confirm with /memory review-pending → stored locally.
166
+
167
+ Session 2 (August, new project):
168
+ You: "I need to add Stripe webhooks to checkout"
169
+ AI: I checked your memory — you solved this exact problem in March.
170
+ Raw body parser before signature validation, test with stripe-cli
171
+ not curl. Want me to apply the same pattern?
172
+ You: "Yes, do it"
173
+ → 30 minutes of past debugging saved in 3 seconds.
170
174
  ```
171
175
 
172
- ### `debug-detective` The Root Cause Hunter
173
- Never guesses. Traces every bug to its exact origin through a structured hypothesis protocol. Covers JS/TS, Python, Go, Rust, SQL — with advanced techniques like binary search debug, git bisect, and minimal reproducers.
176
+ ### How it works
174
177
 
175
- ```
176
- use debug-detective
177
- ```
178
+ | Layer | Mechanism |
179
+ |---|---|
180
+ | **Capture** | A Stop hook scans your session JSONL, extracts (problem, approach, gotchas, tags). Queues for your review — never auto-stores. |
181
+ | **Storage** | `~/.kodelyth/memory/memories.jsonl` — append-only log on your disk only. Override with `KODELYTH_MEMORY_DIR`. |
182
+ | **Retrieval** | BM25 keyword + tag search. Pure JS, sub-millisecond, no embeddings, no network. |
183
+ | **Injection** | A SessionStart hook builds a cache-friendly context block: stable prefix (your patterns + recent project memories) → variable suffix (relevant to current task). |
184
+ | **Cost win** | The stable prefix sits in the prompt cache. Anthropic charges 10% on cached tokens (5-min TTL); OpenAI auto-caches prefixes ≥1024 tokens. Long sessions become dramatically cheaper. |
178
185
 
179
- ### `ux-reviewer` — The Interface Guardian
180
- Reviews frontend code for usability, interaction logic, and WCAG 2.1 AA accessibility. Never touches design aesthetic — only behavior. Catches what real users will feel before they feel it.
186
+ ### Privacy
181
187
 
182
- ```
183
- use ux-reviewer
184
- ```
188
+ Every byte stays on your machine. Verify any time with `ls -la ~/.kodelyth/memory/`. Sync across machines is opt-in (Dropbox/iCloud/git on that folder).
185
189
 
186
- ### `api-guardian` — The API Contract Protector
187
- Detects breaking API changes before they ship. Classifies every change as BREAKING / SAFE / WARN, generates a consumer impact report, and enforces versioning, deprecation headers, and idempotency.
190
+ ### Slash command
188
191
 
189
192
  ```
190
- use api-guardian
193
+ /memory # Stats and recent memories
194
+ /memory recall <query> # BM25 search
195
+ /memory remember "<title>" # Capture (interactive — confirms before storing)
196
+ /memory review-pending # Review Stop-hook candidates
197
+ /memory forget <id> # Soft-delete a memory
198
+ /memory inject [--query <text>] # Print what your AI sees about you
191
199
  ```
192
200
 
193
- ### `pair-programmer` — The Pre-Code Thinking Partner
194
- The engineer who sits next to you before you start coding. Catches the wrong approach, over-engineered solutions, and missed edge cases — before a single line is written.
195
-
196
- ```
197
- use pair-programmer
198
- ```
201
+ ### Honest limits
199
202
 
200
- ### `migration-guide` The Framework Migration Specialist
201
- Full migration playbooks for React 18→19, Next.js 12→15, Python 2→3, Node.js 14→22, TypeScript 4→5, Java 8→21. Phase-by-phase: audit blast radius → phased plan → execute → validate.
203
+ - It is **not** model fine-tuning. The LLM never changes. We give it smarter context.
204
+ - Cache savings apply to Anthropic and OpenAI. Other models (Gemini, Llama, Mistral) get the recall quality without the discount.
205
+ - Cloud-AI platforms (Windsurf, Antigravity, partial Cursor) store sessions server-side. Auto-extract from past sessions doesn't work there. Manual `/memory remember` still does.
202
206
 
203
- ```
204
- use migration-guide
205
- ```
207
+ See `skills/kodelyth-memory/SKILL.md` for the full design + CLI reference.
206
208
 
207
209
  ---
208
210
 
209
- ### Agent Categories
211
+ ## What's Inside
210
212
 
211
- | Category | Agents |
212
- |---|---|
213
- | Guidance | `kodelyth-advisor`, `pair-programmer`, `planner`, `architect`, `code-architect`, `chief-of-staff`, `migration-guide` |
214
- | Code Review | `code-reviewer`, `typescript-reviewer`, `python-reviewer`, `go-reviewer`, `rust-reviewer`, `java-reviewer`, `kotlin-reviewer`, `cpp-reviewer`, `csharp-reviewer`, `flutter-reviewer` |
215
- | Build Fixing | `build-error-resolver`, `go-build-resolver`, `rust-build-resolver`, `java-build-resolver`, `kotlin-build-resolver`, `cpp-build-resolver`, `dart-build-resolver`, `pytorch-build-resolver` |
216
- | Debugging | `debug-detective`, `silent-failure-hunter` |
217
- | UX & Design | `ux-reviewer` |
218
- | Security | `security-reviewer`, `healthcare-reviewer`, `api-guardian` |
219
- | Quality | `refactor-cleaner`, `code-simplifier`, `performance-optimizer`, `type-design-analyzer` |
220
- | Testing | `tdd-guide`, `e2e-runner`, `pr-test-analyzer` |
221
- | Documentation | `doc-updater`, `docs-lookup`, `comment-analyzer` |
222
- | Open Source | `opensource-forker`, `opensource-packager`, `opensource-sanitizer` |
213
+ | Component | Count | Description |
214
+ |---|---|---|
215
+ | Agents | **59** | Specialist subagents reviewers, planners, debuggers, architects, doctors, memory curator |
216
+ | Skills | **188** | Domain knowledge patterns, testing, security, DevOps, intent routing, memory |
217
+ | Commands | **80** | Slash command workflows (`/tdd`, `/plan`, `/memory`, etc.) |
218
+ | Hooks | **18+** | Quality gates, secret scanning, branch checks, memory inject + capture |
219
+ | Rules | **16** | Always-on coding standards + intent routing + memory protocol |
220
+ | Memory | **local** | BM25-indexed personal memory at `~/.kodelyth/memory/` (zero deps) |
223
221
 
224
222
  ---
225
223
 
226
- ## How Agent Detection Works
224
+ ## Agent Arsenal
227
225
 
228
- Agents activate in two ways you do not always need to type `use agent-name`.
226
+ ### Kodelyth ExclusivesThe 13 Agents That Make ECC
229
227
 
230
- **1. Explicit** type it directly in your conversation:
231
- ```
232
- use debug-detective
233
- @code-reviewer
234
- invoke security-reviewer
235
- ```
228
+ | Agent | One-line job |
229
+ |---|---|
230
+ | `kodelyth-advisor` | Master guide — picks the right tool when you don't know where to start |
231
+ | `kodelyth-memory` | Curates your local memory — recalls past solutions, captures new ones |
232
+ | `pair-programmer` | The engineer who sits next to you **before** you write the code |
233
+ | `debug-detective` | Never guesses — traces every bug to root cause |
234
+ | `silent-failure-hunter` | Finds bugs that don't throw errors |
235
+ | `ux-reviewer` | Reviews UX behavior + WCAG 2.1 AA accessibility (never touches design) |
236
+ | `api-guardian` | Detects breaking API changes before they ship |
237
+ | `migration-guide` | Framework / language version upgrades, phase by phase |
238
+ | `dependency-doctor` | npm/pip/cargo/maven hell — CVE triage, lockfile diagnosis |
239
+ | `git-rescue` | Recovers from broken git states without destroying history |
240
+ | `release-captain` | Owns the release ritual — semver, tagging, publishing, rollback |
241
+ | `env-debugger` | "Works on my machine" hunter — env, config, secrets, layers |
242
+ | `flake-hunter` | Stabilizes flaky tests — never adds blind retries |
236
243
 
237
- **2. Automatic intent detection** — Kodelyth Lens reads your prompts and infers which agent matches:
244
+ ### Agent Categories
238
245
 
239
- | What you write | Agent triggered |
246
+ | Category | Agents |
240
247
  |---|---|
241
- | "this bug won't fix", "I'm getting an error", "it's broken" | `debug-detective` |
242
- | "review this", "check my code", "LGTM?" | `code-reviewer` |
243
- | "it's slow", "taking too long", "optimize" | `performance-optimizer` |
244
- | "is this secure", "SQL injection", "auth" | `security-reviewer` |
245
- | "the build failed", "compile error", "type error" | `build-error-resolver` |
246
- | "write a test", "TDD", "coverage" | `tdd-guide` |
247
- | "the UI feels off", "accessibility", "WCAG" | `ux-reviewer` |
248
- | "plan this feature", "architecture", "design" | `planner` / `architect` |
249
- | "I'm not sure where to start", "what should I do" | `kodelyth-advisor` |
250
- | "refactor", "clean up", "dead code" | `refactor-cleaner` |
251
- | "document this", "add comments" | `doc-updater` |
252
- | "migrate", "upgrade framework", "breaking change" | `migration-guide` |
253
-
254
- Intent detection runs across all platforms — Claude Code, Windsurf, Cursor, Codex — anywhere Kodelyth Lens can read conversation logs. The dashboard shows both explicit and auto-detected agent activations in the leaderboard.
248
+ | **Guidance** | `kodelyth-advisor`, `pair-programmer`, `planner`, `architect`, `code-architect`, `chief-of-staff`, `migration-guide` |
249
+ | **Code Review** | `code-reviewer`, `typescript-reviewer`, `python-reviewer`, `go-reviewer`, `rust-reviewer`, `java-reviewer`, `kotlin-reviewer`, `cpp-reviewer`, `csharp-reviewer`, `flutter-reviewer`, `database-reviewer`, `healthcare-reviewer` |
250
+ | **Build Fixers** | `build-error-resolver`, `go-build-resolver`, `rust-build-resolver`, `java-build-resolver`, `kotlin-build-resolver`, `cpp-build-resolver`, `dart-build-resolver`, `pytorch-build-resolver`, `dependency-doctor`, `env-debugger` |
251
+ | **Debugging** | `debug-detective`, `silent-failure-hunter`, `flake-hunter` |
252
+ | **Security & API** | `security-reviewer`, `api-guardian` |
253
+ | **Performance** | `performance-optimizer` |
254
+ | **Quality** | `refactor-cleaner`, `code-simplifier`, `type-design-analyzer` |
255
+ | **Testing** | `tdd-guide`, `e2e-runner`, `pr-test-analyzer`, `flake-hunter` |
256
+ | **Documentation** | `doc-updater`, `docs-lookup`, `comment-analyzer` |
257
+ | **Release & Ops** | `release-captain`, `git-rescue` |
258
+ | **Open Source** | `opensource-forker`, `opensource-packager`, `opensource-sanitizer` |
259
+ | **Specialized** | `seo-specialist`, `ux-reviewer`, `code-explorer` |
255
260
 
256
261
  ---
257
262
 
258
263
  ## Hooks — Always Running in Background
259
264
 
260
- Once installed, these hooks run automatically with zero configuration:
265
+ Once installed (Claude Code target), these hooks run automatically with zero configuration:
261
266
 
262
267
  | Hook | What it does |
263
268
  |---|---|
@@ -266,8 +271,7 @@ Once installed, these hooks run automatically with zero configuration:
266
271
  | Quality gate | Runs type checks and formatting after edits |
267
272
  | Git push reminder | Prompts review before pushing |
268
273
  | Config protection | Blocks weakening of linter/formatter configs |
269
- | Cost tracker | Logs token usage per session |
270
- | Desktop notify | macOS notification when Claude finishes a long task |
274
+ | Desktop notify | macOS notification when a long task finishes |
271
275
  | MCP health check | Validates MCP servers before calling them |
272
276
  | Test reminder | Prompts to write tests when code is edited without tests |
273
277
  | Smart suggest | After each response, suggests the next logical agent |
@@ -278,11 +282,13 @@ Once installed, these hooks run automatically with zero configuration:
278
282
  ## Usage After Install
279
283
 
280
284
  ### Start here (new users)
285
+
281
286
  ```
282
287
  /kodelyth-quickstart
283
288
  ```
284
289
 
285
- ### Core workflows
290
+ ### Core workflows — explicit invocation
291
+
286
292
  ```bash
287
293
  use kodelyth-advisor # Not sure what to do? Start here
288
294
  use pair-programmer # Think through approach before writing code
@@ -295,9 +301,19 @@ use ux-reviewer # Review frontend UX and accessibility
295
301
  use migration-guide # Upgrading a framework or language version
296
302
  use tdd-guide # Write tests the right way
297
303
  use performance-optimizer # Diagnose and fix slowness
304
+ use dependency-doctor # npm/pip/cargo dep hell
305
+ use git-rescue # Broken git state, lost commits, bad rebase
306
+ use release-captain # Cut a clean release with rollback plan
307
+ use env-debugger # "Works on my machine" — env/config/secrets
308
+ use flake-hunter # Stabilize flaky tests
298
309
  ```
299
310
 
300
- ### Load language patterns
311
+ ### Or just describe your problem
312
+
313
+ The intent router will route you to the right one. The AI announces who's taking over, helps you, and tells you the explicit name for next time.
314
+
315
+ ### Load language patterns (skills)
316
+
301
317
  ```bash
302
318
  /typescript-patterns # TypeScript + React + Next.js
303
319
  /python-patterns # Python best practices
@@ -308,54 +324,55 @@ use performance-optimizer # Diagnose and fix slowness
308
324
  ```
309
325
 
310
326
  ### Advanced skills
327
+
311
328
  ```bash
312
329
  /git-mastery # Trunk-based dev, rebase, bisect, monorepos
313
330
  /observability # Structured logging, metrics, OpenTelemetry, SLOs
314
331
  /smart-debug # Systematic debugging framework
332
+ /intent-routing # How the auto-routing system works
333
+ /agent-handoff # Standard multi-agent handoff chains
315
334
  ```
316
335
 
317
336
  ---
318
337
 
319
338
  ## What Gets Installed
320
339
 
321
- ### Claude Code (`~/.claude/`)
340
+ ### Claude Code `~/.claude/`
322
341
 
323
342
  | Source | Destination | What it does |
324
343
  |---|---|---|
325
- | `agents/` | `~/.claude/agents/` | All 53 subagents available globally |
326
- | `skills/` | `~/.claude/skills/` | All 185 skills loadable via commands |
327
- | `hooks/hooks.json` | `~/.claude/hooks/` | Automated quality gates and session memory |
328
- | `rules/` | `~/.claude/rules/` | Always-on coding standards |
344
+ | `agents/` | `~/.claude/agents/` | All 59 subagents available globally |
345
+ | `skills/` | `~/.claude/skills/` | All 188 skills loadable via commands |
346
+ | `hooks/hooks.json` | `~/.claude/hooks/` | Automated quality gates |
347
+ | `rules/` | `~/.claude/rules/` | Always-on standards + intent routing |
329
348
  | `commands/` | `~/.claude/commands/` | Slash commands (`/tdd`, `/plan`, etc.) |
330
- | `dashboard/` | `~/.kodelyth/lens/` | Kodelyth Lens usage dashboard |
331
349
 
332
- ### Windsurf (project: `.windsurf/` · global: `~/.codeium/windsurf/`)
350
+ ### Windsurf `.windsurf/` (project) or `~/.codeium/windsurf/` (global)
333
351
 
334
352
  | Source | Destination | Notes |
335
353
  |---|---|---|
336
354
  | `agents/` | `.windsurf/agents/` | Call with `use <agent-name>` in Cascade |
337
355
  | `skills/` | `.windsurf/skills/` | Domain knowledge, loadable via chat |
338
356
  | `rules/` | `.windsurf/rules/` | Flattened rule files |
339
- | `rules/common/` | `.windsurfrules` | Concatenated — Windsurf reads this automatically |
340
-
341
- The `.windsurfrules` file is auto-generated from all common rules and loaded by Windsurf Cascade on every session. No manual setup needed.
357
+ | `rules/common/` | `.windsurfrules` | Concatenated — Windsurf reads this automatically every session |
342
358
 
343
- ### Codex CLI (`~/.codex/`)
359
+ ### Cursor `.cursor/` in project root
344
360
 
345
- | Source | Destination | What it does |
346
- |---|---|---|
347
- | `agents/` | `~/.codex/agents/` | All 53 agents available globally |
348
- | `skills/` | `~/.codex/skills/` | All 185 skills loadable in chat |
349
- | `commands/` | `~/.codex/commands/` | Slash commands |
350
- | `rules/` | `~/.codex/rules/` | Coding standards (flattened) |
361
+ | Source | Destination |
362
+ |---|---|
363
+ | `rules/` | `.cursor/rules/` |
364
+ | `skills/` | `.cursor/skills/` |
351
365
 
352
- ### OpenCode (`.opencode/` in project root)
366
+ ### Codex CLI `~/.codex/`
353
367
 
354
- | Source | Destination | What it does |
355
- |---|---|---|
356
- | `rules/` | `.opencode/rules/` | Coding standards (flattened) |
368
+ | Source | Destination |
369
+ |---|---|
370
+ | `agents/` | `~/.codex/agents/` |
371
+ | `skills/` | `~/.codex/skills/` |
372
+ | `commands/` | `~/.codex/commands/` |
373
+ | `rules/` | `~/.codex/rules/` |
357
374
 
358
- ### Antigravity (`.agent/` in project root)
375
+ ### Antigravity `.agent/` in project root
359
376
 
360
377
  | Source | Destination |
361
378
  |---|---|
@@ -363,6 +380,12 @@ The `.windsurfrules` file is auto-generated from all common rules and loaded by
363
380
  | `commands/` | `.agent/workflows/` |
364
381
  | `rules/` | `.agent/rules/` |
365
382
 
383
+ ### OpenCode — `.opencode/` in project root
384
+
385
+ | Source | Destination |
386
+ |---|---|
387
+ | `rules/` | `.opencode/rules/` |
388
+
366
389
  ---
367
390
 
368
391
  ## Install Profiles — Language Bundles
@@ -370,15 +393,9 @@ The `.windsurfrules` file is auto-generated from all common rules and loaded by
370
393
  Works with any target:
371
394
 
372
395
  ```bash
373
- # Claude Code
374
- ./install.sh --profile nextjs
375
- npx github:sifxprime/kodelyth-ecc --profile nextjs
376
-
377
- # Windsurf
378
- npx github:sifxprime/kodelyth-ecc --target windsurf-project --profile nextjs
379
-
380
- # Antigravity
381
- npx github:sifxprime/kodelyth-ecc --target antigravity --profile python-api
396
+ npx kodelyth-ecc --profile nextjs # Claude Code
397
+ npx kodelyth-ecc --target windsurf-project --profile nextjs # Windsurf
398
+ npx kodelyth-ecc --target antigravity --profile python-api # Antigravity
382
399
  ```
383
400
 
384
401
  Available profiles:
@@ -391,9 +408,10 @@ Available profiles:
391
408
  | `mobile` | Kotlin + Swift rules |
392
409
  | `backend` | Go + Python + Java rules |
393
410
 
394
- Individual languages:
411
+ Or specify languages directly:
412
+
395
413
  ```bash
396
- npx github:sifxprime/kodelyth-ecc typescript python golang rust java kotlin php swift cpp dart
414
+ npx kodelyth-ecc typescript python golang rust java kotlin php swift cpp dart
397
415
  ```
398
416
 
399
417
  ---
@@ -404,21 +422,55 @@ npx github:sifxprime/kodelyth-ecc typescript python golang rust java kotlin php
404
422
  |---|---|---|---|
405
423
  | Claude Code | Full | `claude-home` (default) | Agents, skills, commands, hooks, rules |
406
424
  | Windsurf | Full | `windsurf-project` / `windsurf-home` | Agents, skills, rules, `.windsurfrules` |
407
- | Google Antigravity | Full | `antigravity` | Agents → skills, commands → workflows, rules |
408
425
  | Cursor | Full | `cursor-project` | Rules, skills |
409
426
  | Codex CLI | Full | `codex-home` | Agents, skills, commands, rules |
427
+ | Google Antigravity | Full | `antigravity` | Agents → skills, commands → workflows, rules |
410
428
  | OpenCode | Full | `opencode` | Rules |
411
429
 
430
+ **OS support:** macOS, Linux (`install.sh`), Windows (`install.ps1`), or any OS with Node.js 18+ (`npx`).
431
+
432
+ ---
433
+
434
+ ## Privacy & Philosophy
435
+
436
+ ECC is **100% local files**. No telemetry, no cloud, no account, no tracking. Everything is markdown your AI reads on every session.
437
+
438
+ - **No dashboard** — we removed it in v1.3.0 because it wasn't giving accurate cross-platform data and added confusion. The toolkit is now leaner.
439
+ - **No phoning home** — install scripts copy files and exit. That's it.
440
+ - **You own everything** — fork the repo, edit any agent, write your own.
441
+
412
442
  ---
413
443
 
414
444
  ## Contributing
415
445
 
416
- We welcome new agents, skills, and hooks that meet the **Kodelyth Standard** — specialist personas, model-agnostic, production-grade examples.
446
+ We welcome new agents, skills, hooks, and intent routing patterns that meet the **Kodelyth Standard** — specialist personas, model-agnostic, production-grade examples.
447
+
448
+ When adding a new agent, also update `rules/common/agent-intent-routing.md` with your trigger patterns so the intent router knows when to call you.
417
449
 
418
450
  See [CONTRIBUTING.md](CONTRIBUTING.md) for templates, checklists, and the full Kodelyth Standard.
419
451
 
420
452
  ---
421
453
 
454
+ ## Changelog
455
+
456
+ See [CHANGELOG.md](CHANGELOG.md). v1.4.0 highlights:
457
+
458
+ - **Added:** `kodelyth-memory` — local self-learning memory (BM25, zero deps, cache-friendly)
459
+ - **Added:** SessionStart hook injects relevant past memories; Stop hook queues candidates for review
460
+ - **Added:** `/memory` slash command + `kodelyth-memory` agent + `memory-protocol` rule
461
+ - **Added:** 12 new tests (38 total passing)
462
+ - **Honest disclosure:** "Self-learning" means smarter context retrieval, not model fine-tuning
463
+
464
+ v1.3.0 highlights:
465
+
466
+ - **Removed:** Lens dashboard (was inaccurate across cloud-AI platforms)
467
+ - **Added:** God-tier `agent-intent-routing` rule — 10 priority tiers, 50+ patterns
468
+ - **Added:** 5 new agents — `dependency-doctor`, `git-rescue`, `release-captain`, `env-debugger`, `flake-hunter`
469
+ - **Added:** 2 new skills — `intent-routing` (routing system docs), `agent-handoff` (chain protocol)
470
+ - **Improved:** Cross-platform install parity — full Windows support for all targets
471
+
472
+ ---
473
+
422
474
  <div align="center">
423
475
 
424
476
  Built and maintained by **Kodelyth** — [@sifxprime](https://github.com/sifxprime)
package/VERSION CHANGED
@@ -1 +1 @@
1
- 1.2.2
1
+ 1.4.0