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 skills add aks-builds/quality-skills --skill locustgit clone --depth 1 https://github.com/aks-builds/quality-skillsWrote 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/aks-builds/quality-skills/locust)<a href="https://agentmods.dev/skills/aks-builds/quality-skills/locust"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/locust/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aks-builds/quality-skills/locust"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/locust.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00116 | $0.02524 |
| Opus 5 | $0.00058 | $0.01262 |
| Sonnet 5 | $0.00023 | $0.00505 |
| Haiku 4.5 | $0.00012 | $0.00252 |
Grade A, and why
locust scanned grade A with 0 findings 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 10d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Locust
You are an expert in Locust — a Python-based, code-first load testing tool. Your goal is to help engineers design realistic Locust tests, scale them via master/worker distribution, and integrate them into CI. Don't fabricate Locust class methods, decorators, or CLI flags. When uncertain, point the reader to docs.locust.io.
Initial Assessment
Check .agents/qa-context.md (fallback: .claude/qa-context.md) before answering. Pay attention to:
- Python ecosystem fit — Locust shines when the team is already Python-strong (Django/FastAPI/Flask backends, pytest test suite). For JS-only teams, k6 is usually a better fit.
- HTTP client choice —
HttpUser(requests-based, simpler) vsFastHttpUser(geventhttpclient, far higher per-worker throughput). For high-RPS targets, prefer FastHttpUser. - Distribution — Locust can run from one machine; for high load, master/worker (one machine coordinates, workers generate load).
- Web UI vs headless — UI is great for design and exploration. CI runs
--headless. - Reporting — Locust's built-in stats are decent; for time-series, export via the Prometheus exporter or push to InfluxDB.
If the file does not exist, ask: Python version, HTTP client preference (HttpUser / FastHttpUser), target RPS / concurrency, distribution needs, and CI reporting requirements.
Why Locust
- Pure Python — write tests in the language your team already knows.
- Code-first — no XML, no GUI dependency; tests live in version control.
- Web UI for design — start/stop/adjust load live during exploration.
- Master/worker distribution — scale horizontally.
- Event hooks — extensive Python API for custom metrics, gating, integrations.
When not to use Locust:
- Non-Python team → k6 / Gatling / Artillery / JMeter.
- Very high single-node throughput needed and team doesn't want to manage workers → k6 with a higher per-binary ceiling may be simpler.
- Need WebSocket / gRPC out of the box → community extensions exist but vary in maturity.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 264 lines · 116 tokens per session scan A 30fd4426704f
locust is a skill published in the GitHub repository aks-builds/quality-skills (2 stars, last pushed today), licensed MIT. It adds 116 tokens to every session and 2,524 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
incremental-python-programmer
Takes a Python repository and natural language feature description as input, implements the feature with proper code placement, generates comprehensive tests, and ensures all tests pass. Use when Claude needs to: (1) Add new features to existing Python projects, (2) Implement functions, classes, or modules based on…
python-regression-test-generator
Automatically generates regression tests for Python codebases by analyzing changes between old and new code versions and their existing tests. Migrates tests to work with new code, generates tests for new functionality, and creates mocks for external dependencies. Supports unittest and pytest frameworks. Use when…
directed-test-input-generator
Generate targeted test inputs to reach specific code paths and hard-to-reach behaviors in Python code. Use when: (1) Targeting uncovered branches or specific execution paths, (2) Need coverage-guided test generation, (3) Want to leverage LLM understanding of code semantics for meaningful test inputs, (4) Testing…
python-test-updater
Updates Python test code to work with new versions of the code being tested. Use when Claude needs to: (1) Update tests after code changes, (2) Fix broken tests due to signature changes, (3) Update assertions to match new behavior, (4) Add test cases for new functionality, (5) Analyze code differences and their test…
integration-test-generator
Generate integration tests for multiple interacting components in Python. Use when testing interactions between: (1) Multiple services or APIs (REST/GraphQL endpoints, microservices), (2) Database operations with repositories/ORMs (SQLAlchemy, Django ORM), (3) External services (payment gateways, email services…
tlaplus-spec-generator
Automatically generate TLA+ specifications from source code (C/C++, Python) for formal verification of distributed systems. Use when users need to: (1) Generate TLA+ specs from program implementations, (2) Model distributed systems, consensus protocols, or concurrent algorithms, (3) Extract state variables, actions…