ragarciaruben 1.20.24 → 1.20.26
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/.github/prompts/set-profile.prompt.md +3 -3
- package/bin/install.js +2 -2
- package/get-shit-done/templates/opencode/agents/executor.md +1 -1
- package/get-shit-done/templates/opencode/agents/planner.md +1 -1
- package/get-shit-done/templates/opencode/agents/product-owner.md +1 -1
- package/get-shit-done/templates/opencode/agents/verifier.md +1 -1
- package/get-shit-done/templates/opencode/commands/set-profile.md +11 -11
- package/get-shit-done/templates/opencode.json +1 -1
- package/package.json +1 -1
|
@@ -16,7 +16,7 @@ Switch the model used by the Planner, Executor, and Verifier agents. This edits
|
|
|
16
16
|
| Profile | Planner | Executor | Verifier | Best for |
|
|
17
17
|
|---------|---------|----------|----------|----------|
|
|
18
18
|
| `quality` | claude-opus-4 | claude-opus-4 | claude-sonnet-4 | Critical architecture, max reasoning |
|
|
19
|
-
| `balanced` | claude-
|
|
19
|
+
| `balanced` | claude-opus-4 | claude-sonnet-4 | claude-sonnet-4 | Normal development (default) |
|
|
20
20
|
| `budget` | gpt-4.1 | gpt-4.1 | gpt-4.1-mini | High-volume, cost-sensitive work |
|
|
21
21
|
| `gpt` | gpt-4.1 | gpt-4.1 | gpt-4.1 | Prefer OpenAI models throughout |
|
|
22
22
|
|
|
@@ -38,7 +38,7 @@ Switch the model used by the Planner, Executor, and Verifier agents. This edits
|
|
|
38
38
|
|
|
39
39
|
| Agent file | quality | balanced | budget | gpt |
|
|
40
40
|
|------------|---------|----------|--------|-----|
|
|
41
|
-
| planner.agent.md | claude-opus-4 | claude-
|
|
41
|
+
| planner.agent.md | claude-opus-4 | claude-opus-4 | gpt-4.1 | gpt-4.1 |
|
|
42
42
|
| executor.agent.md | claude-opus-4 | claude-sonnet-4 | gpt-4.1 | gpt-4.1 |
|
|
43
43
|
| verifier.agent.md | claude-sonnet-4 | claude-sonnet-4 | gpt-4.1-mini | gpt-4.1 |
|
|
44
44
|
|
|
@@ -58,7 +58,7 @@ Switch the model used by the Planner, Executor, and Verifier agents. This edits
|
|
|
58
58
|
6. **Confirm** — report the final state:
|
|
59
59
|
```
|
|
60
60
|
Profile: balanced
|
|
61
|
-
Planner → claude-
|
|
61
|
+
Planner → claude-opus-4
|
|
62
62
|
Executor → claude-sonnet-4
|
|
63
63
|
Verifier → claude-sonnet-4
|
|
64
64
|
```
|
package/bin/install.js
CHANGED
|
@@ -110,7 +110,7 @@ function showBanner() {
|
|
|
110
110
|
for (const line of bannerLines) {
|
|
111
111
|
process.stdout.write('\x1b[2K\x1b[2;38;2;64;200;248m' + scramble(line, pct) + '\x1b[0m\n');
|
|
112
112
|
}
|
|
113
|
-
sleepMs(
|
|
113
|
+
sleepMs(100);
|
|
114
114
|
}
|
|
115
115
|
|
|
116
116
|
// Phase 2 — bright flash (~80 ms)
|
|
@@ -118,7 +118,7 @@ function showBanner() {
|
|
|
118
118
|
for (const line of bannerLines) {
|
|
119
119
|
process.stdout.write('\x1b[2K\x1b[1;38;2;64;200;248m' + line + '\x1b[0m\n');
|
|
120
120
|
}
|
|
121
|
-
sleepMs(
|
|
121
|
+
sleepMs(160);
|
|
122
122
|
|
|
123
123
|
// Phase 3 — settle to turquoise
|
|
124
124
|
process.stdout.write(`\x1b[${h}A`);
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
description: Implements planned phases — writes code, runs tests, and makes atomic commits following established conventions. Use me to execute a ready plan.
|
|
3
3
|
mode: primary
|
|
4
|
-
model: anthropic/claude-sonnet-4
|
|
4
|
+
model: anthropic/claude-sonnet-4-20250514
|
|
5
5
|
tools:
|
|
6
6
|
write: true
|
|
7
7
|
edit: true
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
description: Plans implementation phases — reads requirements and codebase context to produce executable step-by-step plans. Use me before starting new work.
|
|
3
3
|
mode: primary
|
|
4
|
-
model: anthropic/claude-
|
|
4
|
+
model: anthropic/claude-opus-4-20250514
|
|
5
5
|
tools:
|
|
6
6
|
write: true
|
|
7
7
|
edit: true
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
description: Creates and refines Jira tickets from ideas, epics, or requirements — turns vague requests into well-structured specs. Use me to define WHAT to build.
|
|
3
3
|
mode: subagent
|
|
4
|
-
model: anthropic/claude-sonnet-4
|
|
4
|
+
model: anthropic/claude-sonnet-4-20250514
|
|
5
5
|
tools:
|
|
6
6
|
write: false
|
|
7
7
|
edit: false
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
description: Verifies completed work against requirements — checks tests, inspects implementation, and produces a verification report. Use me after implementing a phase.
|
|
3
3
|
mode: subagent
|
|
4
|
-
model: anthropic/claude-sonnet-4
|
|
4
|
+
model: anthropic/claude-sonnet-4-20250514
|
|
5
5
|
tools:
|
|
6
6
|
write: true
|
|
7
7
|
edit: true
|
|
@@ -11,8 +11,8 @@ Switch the model used by the Planner, Executor, and Verifier agents. This edits
|
|
|
11
11
|
|
|
12
12
|
| Profile | Planner | Executor | Verifier | Best for |
|
|
13
13
|
|---------|---------|----------|----------|----------|
|
|
14
|
-
| `quality` | anthropic/claude-opus-4 | anthropic/claude-opus-4 | anthropic/claude-sonnet-4 | Critical architecture, max reasoning |
|
|
15
|
-
| `balanced` | anthropic/claude-
|
|
14
|
+
| `quality` | anthropic/claude-opus-4-20250514 | anthropic/claude-opus-4-20250514 | anthropic/claude-sonnet-4-20250514 | Critical architecture, max reasoning |
|
|
15
|
+
| `balanced` | anthropic/claude-opus-4-20250514 | anthropic/claude-sonnet-4-20250514 | anthropic/claude-sonnet-4-20250514 | Normal development (default) |
|
|
16
16
|
| `budget` | openai/gpt-4.1 | openai/gpt-4.1 | openai/gpt-4.1-mini | High-volume, cost-sensitive work |
|
|
17
17
|
| `gpt` | openai/gpt-4.1 | openai/gpt-4.1 | openai/gpt-4.1 | Prefer OpenAI models throughout |
|
|
18
18
|
|
|
@@ -31,13 +31,13 @@ Switch the model used by the Planner, Executor, and Verifier agents. This edits
|
|
|
31
31
|
|
|
32
32
|
| Agent file | quality | balanced | budget | gpt |
|
|
33
33
|
|------------|---------|----------|--------|-----|
|
|
34
|
-
| planner.md | anthropic/claude-opus-4 | anthropic/claude-
|
|
35
|
-
| executor.md | anthropic/claude-opus-4 | anthropic/claude-sonnet-4 | openai/gpt-4.1 | openai/gpt-4.1 |
|
|
36
|
-
| verifier.md | anthropic/claude-sonnet-4 | anthropic/claude-sonnet-4 | openai/gpt-4.1-mini | openai/gpt-4.1 |
|
|
34
|
+
| planner.md | anthropic/claude-opus-4-20250514 | anthropic/claude-opus-4-20250514 | openai/gpt-4.1 | openai/gpt-4.1 |
|
|
35
|
+
| executor.md | anthropic/claude-opus-4-20250514 | anthropic/claude-sonnet-4-20250514 | openai/gpt-4.1 | openai/gpt-4.1 |
|
|
36
|
+
| verifier.md | anthropic/claude-sonnet-4-20250514 | anthropic/claude-sonnet-4-20250514 | openai/gpt-4.1-mini | openai/gpt-4.1 |
|
|
37
37
|
|
|
38
38
|
The line to change looks like:
|
|
39
39
|
```
|
|
40
|
-
model: anthropic/claude-sonnet-4
|
|
40
|
+
model: anthropic/claude-sonnet-4-20250514
|
|
41
41
|
```
|
|
42
42
|
Change only that line in the frontmatter block (between the `---` delimiters).
|
|
43
43
|
|
|
@@ -50,15 +50,15 @@ Switch the model used by the Planner, Executor, and Verifier agents. This edits
|
|
|
50
50
|
6. **Confirm** — report the final state:
|
|
51
51
|
```
|
|
52
52
|
Profile: balanced
|
|
53
|
-
Planner → anthropic/claude-
|
|
54
|
-
Executor → anthropic/claude-sonnet-4
|
|
55
|
-
Verifier → anthropic/claude-sonnet-4
|
|
53
|
+
Planner → anthropic/claude-opus-4-20250514
|
|
54
|
+
Executor → anthropic/claude-sonnet-4-20250514
|
|
55
|
+
Verifier → anthropic/claude-sonnet-4-20250514
|
|
56
56
|
```
|
|
57
57
|
|
|
58
58
|
## Available model IDs (OpenCode format: provider/model)
|
|
59
59
|
|
|
60
|
-
- `anthropic/claude-opus-4` — Claude Opus 4 (most capable)
|
|
61
|
-
- `anthropic/claude-sonnet-4` — Claude Sonnet 4 (fast + smart)
|
|
60
|
+
- `anthropic/claude-opus-4-20250514` — Claude Opus 4 (most capable)
|
|
61
|
+
- `anthropic/claude-sonnet-4-20250514` — Claude Sonnet 4 (fast + smart)
|
|
62
62
|
- `openai/gpt-4.1` — GPT-4.1
|
|
63
63
|
- `openai/gpt-4.1-mini` — GPT-4.1 Mini (fastest/cheapest)
|
|
64
64
|
- `openai/o3` — OpenAI o3 (reasoning)
|
package/package.json
CHANGED