thrivekit 2.0.22 → 2.0.23
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.
- package/README.md +23 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -16,6 +16,7 @@ A toolkit for implementing [RALPH](https://ghuntley.com/ralph/) with [Claude Cod
|
|
|
16
16
|
#### Autonomous Code Loops with RALPH principles
|
|
17
17
|
Run this in the terminal not in a claude cli session. It will use your claude subscription not an API key.
|
|
18
18
|
- **`npx thrivekit run`** - RALPH Autonomous loop: Brainstorm ideas → turn ideas into atomic prds → implement → verify → commit → repeat
|
|
19
|
+
- **`npx thrivekit run --fast`** - Fast mode: skips code review for quicker iterations (~2-3 min/story vs 5-8 min)
|
|
19
20
|
|
|
20
21
|
#### Guardrails
|
|
21
22
|
- **`/vibe-check`** - manually run the same automated tests and guardrail checks at any time
|
|
@@ -89,12 +90,21 @@ Review and approve when prompted.
|
|
|
89
90
|
Type `/exit` or open a new terminal, then run:
|
|
90
91
|
|
|
91
92
|
```bash
|
|
93
|
+
# Standard mode (with code review)
|
|
92
94
|
npx thrivekit run
|
|
95
|
+
|
|
96
|
+
# Fast mode (skip code review, ~2x faster)
|
|
97
|
+
npx thrivekit run --fast
|
|
98
|
+
|
|
99
|
+
# Limit iterations
|
|
100
|
+
npx thrivekit run --max 10
|
|
93
101
|
```
|
|
94
102
|
|
|
95
103
|
Ralph loops through stories one at a time, writes tests, verifies, and commits.
|
|
96
104
|
|
|
97
105
|
> **Pro tip:** Use two terminals - plan with Claude in one, run Ralph in another.
|
|
106
|
+
>
|
|
107
|
+
> **Performance:** Fast mode skips the AI code review step, running lint and tests in parallel. Use it when iterating quickly on known-good patterns.
|
|
98
108
|
|
|
99
109
|
## Ralph Details
|
|
100
110
|
|
|
@@ -106,7 +116,11 @@ Ralph loops through stories one at a time, writes tests, verifies, and commits.
|
|
|
106
116
|
│ 1. Read prd.json → find next story where passes=false │
|
|
107
117
|
│ 2. Build prompt (story + context + failures + signs) │
|
|
108
118
|
│ 3. Spawn Claude with prompt │
|
|
109
|
-
│ 4. Run verification
|
|
119
|
+
│ 4. Run verification: │
|
|
120
|
+
│ - Code review (skipped in --fast mode) │
|
|
121
|
+
│ - Lint + tests (run in parallel) │
|
|
122
|
+
│ - Playwright/API tests │
|
|
123
|
+
│ - Browser validation │
|
|
110
124
|
│ 5. Pass? → commit, next story │
|
|
111
125
|
│ Fail? → save error, retry with failure context │
|
|
112
126
|
│ 6. Repeat until all stories pass │
|
|
@@ -114,6 +128,14 @@ Ralph loops through stories one at a time, writes tests, verifies, and commits.
|
|
|
114
128
|
└─────────────────────────────────────────────────────────────┘
|
|
115
129
|
```
|
|
116
130
|
|
|
131
|
+
### Performance Options
|
|
132
|
+
|
|
133
|
+
| Flag | Effect | Best For |
|
|
134
|
+
|------|--------|----------|
|
|
135
|
+
| `--fast` | Skip code review, parallel lint+tests | Rapid iteration, trusted patterns |
|
|
136
|
+
| `--max N` | Limit to N iterations | Preventing runaway loops |
|
|
137
|
+
| (default) | Full verification with code review | Production-quality code |
|
|
138
|
+
|
|
117
139
|
---
|
|
118
140
|
|
|
119
141
|
## Documentation
|
package/package.json
CHANGED