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/oumaimah-qa/qios/api-deep-analyzernpx skills add oumaimah-QA/QIOS --skill api-deep-analyzergit clone --depth 1 https://github.com/oumaimah-QA/QIOSWrote 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/oumaimah-qa/qios/api-deep-analyzer)<a href="https://agentmods.dev/skills/oumaimah-qa/qios/api-deep-analyzer"><img src="https://agentmods.dev/badge/skills/oumaimah-qa/qios/api-deep-analyzer.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 | $0.00117 | $0.01073 |
| Opus 5 | $0.00059 | $0.00536 |
| Sonnet 5 | $0.00023 | $0.00215 |
| Haiku 4.5 | $0.00012 | $0.00107 |
Grade A, and why
api-deep-analyzer 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 4d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Deep Analyzer
Purpose
Given an API endpoint, produce complete, structured test coverage ready to execute. No manual brainstorming. No forgotten edge cases. Consistent quality every time.
Input Accepted
- Endpoint: method + path (e.g.
POST /orders/checkout) - Headers, body schema, query params
- Swagger/OpenAPI snippet or full spec
- Plain business description of the endpoint
- Existing collection to extend
Analysis Process
Step 1 — API Profile
Extract and document:
Method : POST / GET / PUT / DELETE / PATCH
Path : /resource/action
Auth : Bearer / API Key / None / Other
Headers : Content-Type, Authorization, custom headers
Body Fields : name, type, required/optional, constraints
Query Params : name, type, description
Business Goal : what this endpoint does in the system
Dependencies : which services / DB / events are involved
Sensitive Data: financial? PII? session? audit required?
Step 2 — Risk Assessment
Tag every test area:
[CRITICAL] → auth, financial data, data integrity, security breach
[HIGH] → business rules, state changes, data persistence
[MEDIUM] → error messages, response format, performance
[LOW] → optional fields, cosmetic, non-critical behavior
Step 3 — Test Generation
✅ Happy Path
- Standard success with valid, complete data
- Success with minimum required fields only
- Success with boundary values (min, max)
- Success with different valid user roles (if applicable)
❌ Negative Cases
- Each required field missing independently
- Invalid field type (string where number expected, etc.)
- Invalid value (negative amount, future date where past expected, etc.)
- No authentication token → 401
- Invalid / expired token → 401
- Wrong role → 403
- Duplicate / idempotency request
⚠️ Edge Cases
- Null vs empty string vs missing field (3 distinct cases)
- Special characters in string fields
- Whitespace-only string values
- Maximum payload size exceeded
- Concurrent requests (race condition)
What ships with it
5 files 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.
- 4d ago First seen · 126 lines · 117 tokens per session scan A 35f01be11f5b
api-deep-analyzer is a skill published in the GitHub repository oumaimah-QA/QIOS (3 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 1,073 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
BDD/Cucumber Patterns
Behavior-Driven Development skill using Cucumber, covering feature files, step definitions, Gherkin best practices, data tables, scenario outlines, and hooks.
JMeter Load Testing
Load and performance testing skill using Apache JMeter, covering test plans, thread groups, assertions, listeners, timers, and distributed testing.
bruno
Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize Bruno API Client, Bru markup language (.bru), CLI runner (@usebruno/cli), and CI/CD test pipelines.
BDD Gherkin Testing Patterns
Behavior-Driven Development with Gherkin syntax, step definitions, scenario outlines, data tables, and living documentation generation.
Playwright API Testing
API testing with Playwright APIRequestContext for REST and GraphQL endpoints.
Cypress E2E Testing
Cypress end-to-end testing with custom commands, intercepts, and component testing.