Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/kint4/autoframe/load-k6npx skills add kint4/autoframe --skill load-k6git clone --depth 1 https://github.com/kint4/autoframeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kint4/autoframe/load-k6)<a href="https://agentmods.dev/skills/kint4/autoframe/load-k6"><img src="https://agentmods.dev/badge/skills/kint4/autoframe/load-k6.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00039 | $0.00630 |
| Opus 5 | $0.00019 | $0.00315 |
| Sonnet 5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
load-k6 scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(`curl -o /dev/null -w "%{http_code}"`) before generating the script. How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/load-k6 — Generate a k6 Load Test
Type: Load Description: Generates a k6 load test script for a described scenario, with real ramp-up/sustain/ramp-down stages, thresholds, and a readable report.
Input Format
The user describes the scenario:
- The endpoint or flow to load test
- Expected/target traffic (concurrent users)
- Performance goals (acceptable latency, error rate)
If targets aren't given, use Autoframe defaults: 50 ramp-up → 100 sustained, p95 < 500ms, error rate < 1%.
Output Format
A k6 script at performance/load/[scenario].load.js following the k6 conventions in CLAUDE.md:
options.stages: ramp up, sustained load, ramp down — real numbers, never placeholdersoptions.thresholds: p95 response time and error rate__ENV.BASE_URLfor the base URL — never hardcodedcheck()assertions and asleep()per iteration
Step-by-Step Instructions
- Read the k6 conventions in CLAUDE.md.
- Confirm the target URL is not production. If it is, require explicit user confirmation before generating or running.
- Check the target path is HTTP-reachable. Single-page apps route paths like
/inventory.htmlclient-side — a rawhttp.getto them returns 404. For SPAs, target the document root or real API endpoints instead. Verify with one request (curl -o /dev/null -w "%{http_code}") before generating the script. - Translate the scenario into concrete stages and thresholds (use defaults if unspecified).
- Write the script:
import http from 'k6/http'and{ check, sleep } from 'k6'.export const optionswithstages(real durations/targets) andthresholds.export default function ()that hits${__ENV.BASE_URL}/[path], runscheck()s, andsleep(1).
- Use kebab-case +
.load.jssuffix. - Save to
performance/load/[scenario].load.js. - Tell the user how to run it:
BASE_URL=... k6 run performance/load/[scenario].load.js(or via theload.ymlworkflow).
Rules
- Never use placeholder text like
[ramp-up]in stage targets — always real numbers. - Always use
__ENV.BASE_URL; never hardcode URLs. - Always define ramp up, sustained, ramp down stages and both thresholds.
- Never run against production without explicit user confirmation.
- k6 scripts are JavaScript (the one exception to the TypeScript rule).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 54 lines · 39 tokens per session scan A 1b708f40bb46
load-k6 is a skill published in the GitHub repository kint4/autoframe (6 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 630 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
k6-load-testing
Comprehensive k6 load testing skill for API, browser, and scalability testing. Write realistic load scenarios, analyze results, and integrate with CI/CD.
qawolf-cli
Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; request automation of…
tokenless
Use when a task can be delegated through the globally installed Tokenless CLI without directly writing to the workspace; route it to a visible AI provider website to save agent tokens.
tokenless-install
Install, upgrade, repair, and verify Tokenless, its agent skills, and local Playwright runtime. Use only when the user explicitly asks for installation, upgrade, repair, browser sign-in handoff, a failed doctor check, or an installation integrity check.
agent-qa-authoring
Use when creating, editing, validating, or running agent-qa tests, suites, or hooks. Prefer agent-qa MCP tools, enforce canonical agent-qa IDs, and use the bundled schema reference to avoid hallucinated config keys or YAML fields.
agent-qa-debug-fix
Use after an agent-qa run has failed and you need to debug, patch, and verify the issue using MCP evidence, logs, artifacts, and local code changes instead of generated fix suggestions.