devlyn-cli 2.9.0 → 2.9.2

package/CLAUDE.md

@@ -28,7 +28,7 @@ The runtime sub-agent contract below (Subtractive-first / Goal-locked / No-worka
 
 ## Quick Start
 
-Two skills cover the full cycle. `/devlyn:ideate` is OPTIONAL; `/devlyn:resolve` is REQUIRED; `/devlyn:design-ui` is also REQUIRED as the creative UI exploration surface. Engine selection follows the role map below.
+Engine selection follows the role map below.
 
 1. `/devlyn:ideate` (optional) — unstructured idea → `docs/specs/<id>/spec.md` + `spec.expected.json`. Modes: default Q&A, `--quick` (autonomous-pipeline-safe), `--from-spec <path>`, `--project`.
 2. `/devlyn:resolve` — hands-free pipeline for any coding task. Free-form goal, `--spec <path>`, or `--verify-only <diff> --spec <path>`. Phases: PLAN → IMPLEMENT → BUILD_GATE → CLEANUP → VERIFY (fresh subagent, findings-only).
@@ -60,7 +60,7 @@ The user does not invoke skills manually; the orchestrating model does. Small ta
 
 **Intent queue (unattended drain)**: the user stacks intents in `docs/specs/queue.md` (ordered checklist; `/devlyn:queue` is the front-end — no args shows status, `add <intent>` appends, `drain` starts the serial drain). Drain strictly serially — per item: spec it, run the outer loop, mark `[x]` done or `[F]` blocked with reason, continue; a blocked item never halts the queue. The queue entry is the user's go-ahead, so assume-and-log replaces the interactive checkpoint — but unattended assumptions may only take scope-narrowing, reversible, non-user-visible defaults. Material ambiguity (user-visible behavior, data/state semantics, new files/scripts/flags, implementation surface) → mark `[F] needs-review` and move on. End the drain with a per-item verdict + assumptions report.
 
-### Subtractive-first editing — perfection = nothing left to remove
+## Subtractive-first editing — perfection = nothing left to remove
 <!-- runtime-principles:section=subtractive-first:begin -->
 
 > **Operating definition of "done" in this repo** (Saint-Exupéry discipline rule above): a change is finished when no further line, branch, flag, or doc paragraph can be removed without breaking a learned failure mode. Not before.
@@ -96,7 +96,7 @@ If you skip question 1 or 2, you are violating this rule even if the resulting c
 **Never grow surface area silently.** Every accretion-shaped change must be visible: in the commit message, in the iteration file, or in a flagged review. Silent growth is the failure mode this rule exists to prevent.
 <!-- runtime-principles:section=subtractive-first:end -->
 
-### Goal-locked execution — stay on the North Star, do not wander
+## Goal-locked execution — stay on the North Star, do not wander
 <!-- runtime-principles:section=goal-locked:begin -->
 
 Even with a North Star defined, work drifts off-course ("산으로 간다" / "삼천포로 빠진다" — going up the wrong mountain instead of forward). The harness must **actively block** this drift at run time, not merely discourage it. The default is ruler-straight execution toward the user's stated goal; any deviation requires explicit justification, not the inverse.
@@ -139,7 +139,7 @@ Any orchestrating engine (Claude, Codex, or future) continuing harness / loop-en
 - **Fallbacks are the exception.** Only use them when it's a widely accepted best practice (CSS fallback fonts, CDN failover, image placeholders). Otherwise handle the error explicitly.
 - **Pattern**: `try { doThing() } catch (error) { showErrorUI(error) }` — NOT `try { doThing() } catch { return fallbackValue }`.
 
-### Evidence over claim
+## Evidence over claim
 <!-- runtime-principles:section=evidence:begin -->
 
 Every finding cites concrete evidence. Vague claims are speculation; exclude them.

package/README.md

@@ -6,7 +6,7 @@
   <img alt="DEVLYN" src="assets/logo.svg" width="540" />
 </picture>
 
-### Context Engineering & Harness Engineering Toolkit for Claude Code
+### Context, Harness & Loop Engineering Toolkit for AI Coding Agents
 
 **Structured prompts, agent orchestration, and automated pipelines — debugging, code review, UI design, product specs, and more.**
 
@@ -33,7 +33,7 @@ That's it. The installer opens with a single **agent selector** — pick any com
 
 ## How It Works — Two Skills, Full Cycle
 
-devlyn-cli turns Claude Code into a hands-free development pipeline. The pipeline surface is two skills, with `/devlyn:design-ui` installed as the required creative UI surface:
+devlyn-cli turns your AI coding agent into a hands-free development pipeline. The pipeline surface is two skills, with `/devlyn:design-ui` installed as the required creative UI surface:
 
 ```
 ideate (optional)  →  resolve  →  ship
@@ -278,6 +278,35 @@ Selected during install. Run `npx devlyn-cli` again to add more.
 - **Add optional skill** — add to `optional-skills/` and `OPTIONAL_ADDONS` in [`bin/devlyn.js`](bin/devlyn.js)
 - **Suggest a pack** — PR to the pack list
 
+## Supercharge it — pair devlyn with persistent agent memory
+
+devlyn-cli gives your agent a world-class **harness**. Give it a world-class **memory** and the loop compounds — decisions, corrections, and hard-won context survive across sessions instead of resetting every conversation.
+
+> [!TIP]
+> ### 🧠 [pyx-memory](https://memory.pyxmate.com) — world-class agentic memory (hybrid RAG) for coding agents
+> Durable facts, corrections, and project state your agent recalls and reinforces — so every run starts smarter than the last. → **[memory.pyxmate.com](https://memory.pyxmate.com)**
+
+- **Remembers across sessions** — decisions, gotchas, preferences, and project state, not just this conversation
+- **Hybrid retrieval** — semantic *and* graph recall: find by meaning *and* by relationship
+- **Learns the loop** — reinforces what works, records corrections when it doesn't
+
+**Harness (devlyn) + Memory (pyx-memory) = agents that don't just execute — they improve.** Wire up **pyx-memory** as an MCP server and `/devlyn:resolve` recalls prior decisions before it plans and stores what it learns after it ships.
+
+## Support & Attribution
+
+devlyn-cli is built and maintained in the open. If it earns a place in your workflow, two small things keep it alive and help others find it:
+
+- ⭐️ **Star the repo** — [give it a star](https://github.com/fysoul17/devlyn-cli) if it saved you time. It's the single biggest signal that keeps the project going.
+- 🔗 **Leave a credit** — if devlyn-cli helped ship your project, a small attribution is genuinely appreciated (kindly requested, never required — the MIT license asks nothing of you here). Drop this badge in your README:
+
+  ```md
+  [![Built with devlyn-cli](https://img.shields.io/badge/built%20with-devlyn--cli-blueviolet)](https://github.com/fysoul17/devlyn-cli)
+  ```
+
+  Renders as [![Built with devlyn-cli](https://img.shields.io/badge/built%20with-devlyn--cli-blueviolet)](https://github.com/fysoul17/devlyn-cli)
+
+Thank you for using devlyn — it genuinely means a lot. 🙏
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=fysoul17/devlyn-cli&type=Date)](https://star-history.com/#fysoul17/devlyn-cli&Date)

package/benchmark/auto-resolve/fixtures/test-repo/README.md

@@ -1,27 +1,12 @@
-# bench-test-repo
+# harbor-tools
 
-Deterministic base Node project used by every devlyn-cli auto-resolve
-benchmark fixture. Fixtures extend this skeleton via `setup.sh` patches.
+A small Node.js toolkit with a command-line interface, an HTTP server, and a
+minimal browser page.
 
-## What's in it
+## Commands
 
-- `bin/cli.js` — tiny CLI (`hello`, `version`)
-- `server/index.js` — tiny Express app (`/health`, `/items`, `/items/:id`)
-- `web/index.html` — minimal static page with a click interaction
-- `tests/cli.test.js`, `tests/server.test.js` — node:test fixtures
-- `playwright.config.js` — used by web/browser fixtures only
-- `package.json` — `express` dep, `engines: node >= 18`
+- `npm test` runs the test suite.
+- `npm run cli -- --help` prints command-line help.
+- `npm start` starts the HTTP server.
 
-## How it's used
-
-`run-fixture.sh` copies this directory to a temp path per run, applies the
-fixture's `setup.sh`, then invokes the arm (variant or bare) against that
-copy. No fixture modifies this source tree — modifications happen only in
-the per-run temp copies.
-
-## Keep it minimal
-
-Adding features to `test-repo` enlarges the surface every fixture works
-against. Add only when an existing fixture can't express itself against the
-current baseline. Preferred path: push complexity into the fixture's
-`setup.sh`, not into this base.
+The project intentionally keeps each component small and independent.

package/benchmark/auto-resolve/fixtures/test-repo/bin/cli.js

@@ -1,6 +1,6 @@
 #!/usr/bin/env node
-// bench-test-repo — tiny CLI used as the deterministic base for benchmark fixtures.
-// Fixtures extend or modify this file; keep the baseline minimal and obvious.
+// harbor-tools — small command-line utilities for local workflows.
+// Keep the core commands minimal and easy to understand.
 
 const fs = require('fs');
 const path = require('path');

package/benchmark/auto-resolve/fixtures/test-repo/package-lock.json

@@ -1,11 +1,11 @@
 {
-  "name": "bench-test-repo",
+  "name": "harbor-tools",
   "version": "0.1.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
-      "name": "bench-test-repo",
+      "name": "harbor-tools",
       "version": "0.1.0",
       "dependencies": {
         "express": "4.19.2"

package/benchmark/auto-resolve/fixtures/test-repo/package.json

@@ -1,8 +1,8 @@
 {
-  "name": "bench-test-repo",
+  "name": "harbor-tools",
   "version": "0.1.0",
   "private": true,
-  "description": "Deterministic base Node project for devlyn-cli auto-resolve benchmarks. Every fixture starts from a fresh copy of this directory.",
+  "description": "A small Node.js toolkit with a command-line interface and HTTP server.",
   "bin": {
     "bench-cli": "bin/cli.js"
   },

package/benchmark/auto-resolve/fixtures/test-repo/playwright.config.js

@@ -1,6 +1,6 @@
-// Playwright config used only by browser-validate benchmark fixtures.
-// Runs against web/index.html served via `npx serve web` (fixture setup.sh
-// starts the server). Keep config minimal.
+// Playwright config for the browser checks.
+// Runs against web/index.html served via `npx serve web` (the check starts the
+// server). Keep config minimal.
 module.exports = {
   testDir: './tests/e2e',
   timeout: 30_000,

package/benchmark/auto-resolve/fixtures/test-repo/server/index.js

@@ -1,4 +1,4 @@
-// Tiny Express server used by backend-contract fixtures. Intentionally small.
+// Tiny Express server with a deliberately small API surface.
 const express = require('express');
 
 const app = express();
@@ -30,7 +30,7 @@ app.get('/items/:id', (req, res) => {
 if (require.main === module) {
   const port = Number(process.env.PORT) || 3000;
   app.listen(port, () => {
-    console.log(`bench-test-repo server listening on :${port}`);
+    console.log(`harbor-tools server listening on :${port}`);
   });
 }
 

package/benchmark/auto-resolve/fixtures/test-repo/web/index.html

@@ -2,7 +2,7 @@
 <html lang="en">
   <head>
     <meta charset="utf-8" />
-    <title>bench-test-repo</title>
+    <title>harbor-tools</title>
     <style>
       body {
         font-family: system-ui, sans-serif;
@@ -23,8 +23,8 @@
     </style>
   </head>
   <body>
-    <h1>bench-test-repo</h1>
-    <p>Minimal page used by browser-validate benchmark fixtures.</p>
+    <h1>harbor-tools</h1>
+    <p>Minimal page for checking the browser interaction.</p>
     <button id="greet">Greet</button>
     <div id="output" data-testid="output"></div>
     <script>

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "devlyn-cli",
-  "version": "2.9.0",
-  "description": "AI development toolkit for Claude Code — ideate, resolve, and ship with context engineering and agent orchestration",
+  "version": "2.9.2",
+  "description": "Loop & harness engineering for AI coding agents (Claude Code, Codex, and any AGENTS.md-driven agent) — take intent to shipped, engineer-quality software hands-free with phase-gated pipelines and agent orchestration",
   "homepage": "https://github.com/fysoul17/devlyn-cli#readme",
   "bin": {
     "devlyn": "bin/devlyn.js"
@@ -78,11 +78,14 @@
   "keywords": [
     "claude",
     "claude-code",
+    "codex",
+    "ai-coding-agents",
     "ai",
     "ai-agent",
     "ai-tools",
     "context-engineering",
     "harness-engineering",
+    "loop-engineering",
     "agent-orchestration",
     "prompt-engineering",
     "code-review",