agentic-loop 3.2.0 → 3.2.1

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.
@@ -306,7 +306,7 @@ For frontend stories, acceptance criteria MUST include:
306
306
  - "Required elements render" (specify which: header, form, button, etc.)
307
307
  - "Works on mobile viewport (375px)"
308
308
 
309
- These get verified by Playwright, not just code review.
309
+ These get verified by Playwright tests and MCP browser tools.
310
310
 
311
311
  ### Test Steps - CRITICAL
312
312
  **Test steps MUST be executable shell commands.** Ralph runs them with bash.
@@ -352,7 +352,7 @@ The Playwright test file can check:
352
352
  ]
353
353
  ```
354
354
 
355
- **If a step can't be automated**, leave it out of testSteps and put it in acceptanceCriteria instead. Ralph will verify acceptanceCriteria via code review, not by running commands.
355
+ **If a step can't be automated**, leave it out of testSteps and put it in acceptanceCriteria instead. Claude will verify acceptanceCriteria visually using MCP browser tools.
356
356
 
357
357
  ### Architecture Guidelines
358
358
  - **Domain-driven directories** - Group by feature (`src/contact/`) not type (`src/components/`)
@@ -283,4 +283,4 @@ The Playwright test file can check:
283
283
  ]
284
284
  ```
285
285
 
286
- **If a step can't be automated**, leave it out of testSteps and put it in acceptanceCriteria instead. Ralph will verify acceptanceCriteria via code review, not by running commands.
286
+ **If a step can't be automated**, leave it out of testSteps and put it in acceptanceCriteria instead. Claude will verify acceptanceCriteria visually using MCP browser tools.
package/README.md CHANGED
@@ -45,8 +45,7 @@ claude --dangerously-skip-permissions
45
45
 
46
46
  **Terminal 2 - Ralph Loop:**
47
47
  ```bash
48
- npx agentic-loop run # Execute PRDs autonomously
49
- npx agentic-loop run --fast # Skip code review (~2x faster)
48
+ npx agentic-loop run # Execute PRDs autonomously
50
49
  ```
51
50
 
52
51
  > **Tip:** Use two terminals. Plan with Claude in one, run Ralph in the other.
@@ -61,8 +60,8 @@ npx agentic-loop run --fast # Skip code review (~2x faster)
61
60
  ├─────────────────────────────────────────────────────────────┤
62
61
  │ 1. Read prd.json → find next story where passes=false │
63
62
  │ 2. Build prompt (story + context + failures + signs) │
64
- │ 3. Spawn Claude with prompt
65
- │ 4. Run verification (lint, tests, browser, code review)
63
+ │ 3. Spawn Claude with prompt + MCP browser tools
64
+ │ 4. Run verification (lint, tests, testSteps)
66
65
  │ 5. Pass? → commit, next story │
67
66
  │ Fail? → save error, retry with failure context │
68
67
  │ 6. Repeat until all stories pass │
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agentic-loop",
3
- "version": "3.2.0",
3
+ "version": "3.2.1",
4
4
  "description": "Autonomous AI coding loop - PRD-driven development with Claude Code",
5
5
  "author": "Allie Jones <allie@allthrive.ai>",
6
6
  "license": "MIT",