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/keploy/keploy/keploy-docsnpx skills add keploy/keploy --skill keploy-docsgit clone --depth 1 https://github.com/keploy/keployWhat 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 | $0.00116 | $0.02855 |
| Opus 5 | $0.00058 | $0.01427 |
| Sonnet 5 | $0.00023 | $0.00571 |
| Haiku 4.5 | $0.00012 | $0.00285 |
Grade A, and why
keploy-docs 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 yesterday.
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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
keploy-docs
When to use
- A change in
keploy/keployalters user-visible behavior: a new or renamed CLI flag, a changed default, a new command, a new configuration field, a new on-disk file format. - The user reports a docs bug, confusing passage, broken example, or stale screenshot.
- You are about to claim "feature X is documented" without having checked.
Do not touch docs for internal refactors, CI changes, performance work, or bug fixes that don't change user-visible behavior. The docs are a contract with users — edit only when the contract changes.
Repository layout
- Upstream:
github.com/keploy/docs— Docusaurus 2 site, published athttps://docs.keploy.io. - Node version:
.nvmrcpins the project; the CI workflows use Node 20. Usenvm usebeforeyarn. - Package manager:
yarn(classic —yarn.lockpresent).npm installalso works and is what CI runs.
keploy-docs/
├── docs/ # Shared content (components, GSoC, Hacktoberfest). NOT feature docs.
├── versioned_docs/
│ ├── version-4.0.0/ # ← LATEST VERSION. All feature-doc edits go here.
│ ├── version-3.0.0/ # Archived. Touch only for explicit back-ports.
│ ├── version-2.0.0/ # Archived.
│ └── version-1.0.0/ # Archived.
├── versioned_sidebars/
│ ├── version-4.0.0-sidebars.json # Sidebar for v4 — update when adding a new page.
│ └── ...
├── versions.json # Ordered list; first entry ("4.0.0") is current.
├── src/ # Site React code (theme, components). Infrastructure, not content.
├── plugins/ # Docusaurus plugins. Infrastructure.
├── static/ # Images, binary assets.
├── STYLE.md # Keploy-specific prose rules (see §Style).
├── CONTRIBUTING.md # Contribution flow.
├── ADDING_A_QUICKSTART.md # Checklist for new quickstart guides.
└── .vale.ini, vale_styles/ # Vale prose linter config.
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.
- yesterday First seen · 201 lines · 116 tokens per session scan A e50dd6aef95b
keploy-docs is a skill published in the GitHub repository keploy/keploy (18,436 stars, last pushed 2d ago), licensed Apache-2.0. It adds 116 tokens to every session and 2,855 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 2026-08-30.
Other skills, from other repositories
API Test Suite Generator
Automatically generate comprehensive API test suites from OpenAPI specifications covering CRUD operations, error handling, authentication, pagination, and edge cases.
RBT Manual Testing
Skill sinh manual test cases với 2 modes — QUICK (sinh nhanh từ requirements) và FULL RBT (quy trình AI-RBT 6 bước có đánh giá rủi ro). Master skill cho mọi tác vụ manual test case.
Framework Architect
Skill thiết kế và scaffold automation framework hoàn chỉnh cho Playwright, Selenium, và Appium — bao gồm project structure, base classes, config management, reporting, và CI/CD integration.
UI Debug Agent
Skill inspect web/mobile applications bằng browser tools, phân tích DOM elements, xác định locators ổn định, debug UI automation failures, và hỗ trợ sinh Page Object classes.
Test Data Generator
Skill sinh test data có cấu trúc, unique, traceable cho automation tests, bao gồm positive, negative, boundary và edge cases.
jira_integration
Skill tích hợp Jira/Xray — lấy requirements từ Jira, xác thực Xray, và đẩy kết quả test lên Xray Cloud/Server.