claude-load-test-agent 1.0.0 → 1.0.1
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.
- package/README.md +43 -108
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,38 +1,17 @@
|
|
|
1
|
-
#
|
|
1
|
+
# claude-load-test-agent
|
|
2
2
|
|
|
3
|
-
|
|
4
|
-
Share, discover, and compose skills that make your agent smarter.
|
|
3
|
+
k6 load test execution and automated report generation agent for Claude Code.
|
|
5
4
|
|
|
6
|
-
|
|
5
|
+
Install the agent, point it at your k6 scripts, and it will run tests, parse metrics, and generate structured markdown reports automatically.
|
|
7
6
|
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
## How It Works
|
|
11
|
-
|
|
12
|
-
Skills are defined as `SKILL.md` files — structured markdown documents that AI agents automatically recognize and execute. Each skill encodes a specific workflow (e.g., conducting a requirements interview and producing a specification document), turning a multi-step process into a single command.
|
|
13
|
-
|
|
14
|
-
- **Agent-native**: Skills are plain markdown with frontmatter metadata. Any agent that reads files can pick them up.
|
|
15
|
-
- **Self-contained**: Each skill lives in its own directory with everything it needs — instructions, examples, and output templates.
|
|
16
|
-
- **Composable**: Skills are independent units. Use one at a time or chain them together for complex workflows.
|
|
17
|
-
|
|
18
|
-
## Skills
|
|
19
|
-
|
|
20
|
-
| Skill | Description | Status |
|
|
21
|
-
| --- | --- | --- |
|
|
22
|
-
| [spec-interview](skills/spec-interview/SKILL.md) | Transforms vague requirements into actionable specifications (`SPEC.md`) through structured multi-round interviews | ✅ |
|
|
23
|
-
| [release-notes](skills/release-notes/SKILL.md) | Analyzes git history to generate structured release notes (`RELEASE_NOTES.md`) with categorized changes and contributors | ✅ |
|
|
24
|
-
|
|
25
|
-
> ✅ Ready | 🚧 In Progress | 📋 Planned
|
|
26
|
-
|
|
27
|
-
## Agents
|
|
7
|
+
## Installation
|
|
28
8
|
|
|
29
|
-
|
|
9
|
+
```bash
|
|
10
|
+
npm install claude-load-test-agent
|
|
11
|
+
```
|
|
30
12
|
|
|
31
|
-
|
|
32
|
-
| --- | --- | --- | --- |
|
|
33
|
-
| [load-test](.claude/agents/load-test.md) | k6 load test execution and automated report generation with performance metrics | Bash, Read, Write, Glob | ✅ |
|
|
13
|
+
After installation, the agent is available in Claude Code. Just ask:
|
|
34
14
|
|
|
35
|
-
**Usage:**
|
|
36
15
|
```
|
|
37
16
|
"Run API load test"
|
|
38
17
|
"Execute k6 performance test"
|
|
@@ -40,18 +19,23 @@ Agents are autonomous task executors that can be invoked via the Task tool in Cl
|
|
|
40
19
|
|
|
41
20
|
**Trigger Keywords:** load test, performance test, k6, stress test
|
|
42
21
|
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
/
|
|
46
|
-
|
|
22
|
+
## Prerequisites
|
|
23
|
+
|
|
24
|
+
- [k6](https://k6.io/) installed (`brew install k6` on macOS)
|
|
25
|
+
- [Claude Code](https://claude.com/claude-code)
|
|
26
|
+
|
|
27
|
+
## What It Does
|
|
47
28
|
|
|
48
|
-
|
|
29
|
+
1. **Discovers** k6 test scripts in your project
|
|
30
|
+
2. **Executes** the tests via `k6 run`
|
|
31
|
+
3. **Parses** metrics from k6 output (TPS, p95, avg response time, error rate)
|
|
32
|
+
4. **Generates** a structured markdown report
|
|
49
33
|
|
|
50
|
-
##
|
|
34
|
+
## Demo Results
|
|
51
35
|
|
|
52
|
-
|
|
36
|
+
Real results from running the agent against [test-api.k6.io](https://test-api.k6.io):
|
|
53
37
|
|
|
54
|
-
###
|
|
38
|
+
### Health Check Test
|
|
55
39
|
|
|
56
40
|
**Script:** [`examples/scripts/health-check.js`](examples/scripts/health-check.js) — 10 VUs, 40s duration
|
|
57
41
|
|
|
@@ -63,7 +47,7 @@ The load-test agent automatically discovers k6 scripts, executes them, and gener
|
|
|
63
47
|
| Error Rate | 0.00% |
|
|
64
48
|
| Total Requests | 508 |
|
|
65
49
|
|
|
66
|
-
###
|
|
50
|
+
### Multi-Endpoint Test
|
|
67
51
|
|
|
68
52
|
**Script:** [`examples/scripts/api-endpoints.js`](examples/scripts/api-endpoints.js) — 20 VUs, 50s duration, 3 endpoints
|
|
69
53
|
|
|
@@ -77,83 +61,34 @@ The load-test agent automatically discovers k6 scripts, executes them, and gener
|
|
|
77
61
|
|
|
78
62
|
Full generated reports: [`examples/results/`](examples/results/)
|
|
79
63
|
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
```bash
|
|
83
|
-
# 1. Install the agent
|
|
84
|
-
npm install claude-load-test-agent
|
|
85
|
-
|
|
86
|
-
# 2. Place your k6 scripts in the project
|
|
87
|
-
cp examples/scripts/health-check.js your-project/load-test/scripts/
|
|
88
|
-
|
|
89
|
-
# 3. Ask Claude Code to run the test
|
|
90
|
-
"Run load test on health-check"
|
|
91
|
-
```
|
|
64
|
+
## Report Format
|
|
92
65
|
|
|
93
|
-
The agent
|
|
66
|
+
The agent generates reports following this structure:
|
|
94
67
|
|
|
95
|
-
|
|
68
|
+
```markdown
|
|
69
|
+
# {Feature} Load Test Results
|
|
96
70
|
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
|
|
71
|
+
## Test Environment
|
|
72
|
+
| Item | Value |
|
|
73
|
+
|------|-------|
|
|
74
|
+
| Date | 2026-02-06 |
|
|
75
|
+
| Target URL | https://api.example.com |
|
|
76
|
+
| VUsers | 20 |
|
|
77
|
+
| Duration | 50s |
|
|
100
78
|
|
|
101
|
-
|
|
102
|
-
|
|
79
|
+
## Results
|
|
80
|
+
| Metric | Value |
|
|
81
|
+
|--------|-------|
|
|
82
|
+
| TPS | 36.93 req/s |
|
|
83
|
+
| p95 Response Time | 195.1ms |
|
|
84
|
+
| Avg Response Time | 99.7ms |
|
|
85
|
+
| Error Rate | 0.00% |
|
|
103
86
|
|
|
104
|
-
|
|
105
|
-
|
|
87
|
+
## Analysis
|
|
88
|
+
{Auto-generated analysis of the results}
|
|
106
89
|
```
|
|
107
90
|
|
|
108
|
-
|
|
109
|
-
|
|
110
|
-
## Contributing
|
|
111
|
-
|
|
112
|
-
New skill contributions are welcome. To add a skill:
|
|
113
|
-
|
|
114
|
-
1. Create a new directory under `skills/`:
|
|
115
|
-
```
|
|
116
|
-
skills/
|
|
117
|
-
└── your-skill-name/
|
|
118
|
-
└── SKILL.md
|
|
119
|
-
```
|
|
120
|
-
|
|
121
|
-
2. Write your `SKILL.md` with the following structure:
|
|
122
|
-
```markdown
|
|
123
|
-
---
|
|
124
|
-
name: your-skill-name
|
|
125
|
-
description: A short one-line description of what the skill does.
|
|
126
|
-
---
|
|
127
|
-
|
|
128
|
-
# Skill Title
|
|
129
|
-
|
|
130
|
-
## Overview
|
|
131
|
-
What the skill does and when to use it.
|
|
132
|
-
|
|
133
|
-
## Instructions
|
|
134
|
-
Step-by-step instructions the agent will follow.
|
|
135
|
-
|
|
136
|
-
## Examples
|
|
137
|
-
Input/output examples demonstrating the skill.
|
|
138
|
-
|
|
139
|
-
## Guidelines
|
|
140
|
-
Best practices and constraints.
|
|
141
|
-
```
|
|
142
|
-
|
|
143
|
-
3. Register the skill in `.claude-plugin/marketplace.json` by adding it to the appropriate plugin group:
|
|
144
|
-
```json
|
|
145
|
-
{
|
|
146
|
-
"name": "your-plugin-group",
|
|
147
|
-
"description": "Group description",
|
|
148
|
-
"source": "./",
|
|
149
|
-
"strict": false,
|
|
150
|
-
"skills": [
|
|
151
|
-
"./skills/your-skill-name"
|
|
152
|
-
]
|
|
153
|
-
}
|
|
154
|
-
```
|
|
155
|
-
|
|
156
|
-
4. Submit a pull request.
|
|
91
|
+
The agent also supports **Before/After comparison reports** for performance optimization tracking.
|
|
157
92
|
|
|
158
93
|
## License
|
|
159
94
|
|