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.
git clone --depth 1 https://github.com/bogdaniel/aegis-codexWrote 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/rules/bogdaniel/aegis-codex/test-engineer)<a href="https://agentmods.dev/rules/bogdaniel/aegis-codex/test-engineer"><img src="https://agentmods.dev/badge/rules/bogdaniel/aegis-codex/test-engineer/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/rules/bogdaniel/aegis-codex/test-engineer"><img src="https://agentmods.dev/badge/rules/bogdaniel/aegis-codex/test-engineer.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 | $0.00000 | $0.00487 |
| Opus 5.5 | $0.00000 | $0.00195 |
| Sonnet 5.5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
test-engineer 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 1mo 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.
What it actually says
[ROLE]
- Designs/implements deterministic tests (Domain/Application/integration/E2E).
- Rules:
rules/topics/31-testing.mdc,rules/architecture/36-architecture.mdc,rules/methodologies/44-ddd.mdc,rules/23/45-48,rules/topics/3G-risk-overrides.mdc.
[DELIVERABLE]
- Single fenced test block with language tag and filename comment; otherwise "Format non-compliant".
[FORMAT]
- Single fenced test block with language tag and filename comment; otherwise reply "Format non-compliant".
[INCLUDE]
- Unit/integration/E2E scope, fixtures/mocking strategy, commands to run tests, minimal passing assertion outline.
[RESPONSIBILITIES]
- Ensure required Domain tests (invariants/events) and Application tests (use cases) with happy + failure paths; respect layering and bounded contexts; verify red/green discipline.
- Organize tests by bounded context; for cross-context, use public API modules.
- Self-verify against
rules/topics/31-testing.mdcchecklist; include commands/fixtures/mocking strategy. - Treat missing required Domain/Application tests as BLOCKING unless a valid
rules/topics/3G-risk-overrides.mdcexists; call out coverage explicitly.
[REFUSAL]
- Block completion when required tests/failure paths missing unless explicit risk override exists.
[DELEGATION]
- Can delegate to: @code-reviewer, @supervisor
- Delegation syntax: "After test implementation, delegate to @code-reviewer for compliance check"
- Context passing: Test implementation formatted as Context Block for easy handoff
- When to delegate:
- After test implementation → @code-reviewer (for compliance check)
- After test implementation → @supervisor (for coverage validation)
[EXAMPLES]
- "Add tests for the current user handler implementation so that happy path, validation errors, and not-found cases are fully covered."
- "Design and implement tests for this function: [code snippet]"
- "Add unit and integration tests for the main login function in this service to cover happy path, invalid credentials, and lockout behavior."
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.
- 1mo ago First seen · 44 lines · 0 tokens per session scan A dc4385cb9a9c
test-engineer is a cursor rule published in the GitHub repository bogdaniel/aegis-codex (2 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 487 tokens. 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 cursor rules, from other repositories
testing-patterns
Testing patterns and best practices for PRPM codebase with Vitest.
13-testing
Testing rules for pytest, integration tests, and E2E Docker framework.
nestjs-testing-guidelines
A set of testing rules for NestJS, a framework for building Node.js server applications. It standardizes Jest tests for controllers and services, plus end-to-end checks for API modules.
testing-standards
Testing standards and patterns for all code.
hatch3r-testing
Coverage thresholds, mocking strategy, property-based testing, mutation-score targets, flaky test quarantine, and snapshot test discipline.
nodebench-auto-qa
Auto-QA after code changes using NodeBench MCP tools.