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 rules/synaptic-ai-consulting/aamad/adapter-crewaigit clone --depth 1 https://github.com/synaptic-ai-consulting/AAMADWrote 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/synaptic-ai-consulting/aamad/adapter-crewai)<a href="https://agentmods.dev/rules/synaptic-ai-consulting/aamad/adapter-crewai"><img src="https://agentmods.dev/badge/rules/synaptic-ai-consulting/aamad/adapter-crewai.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 | $0.00685 | $0.00685 |
| Opus 5 | $0.00342 | $0.00342 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
adapter-crewai 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrewAI Adapter Rules
Purpose
- Define runtime-specific guidance when
AAMAD_TARGET_RUNTIME=crewai. - This adapter governs how implementation personas scaffold and validate the generated MVP runtime.
Setup
- Install CrewAI and dependencies in the generated backend environment.
- Required runtime files should include:
config/agents.yamlconfig/tasks.yamlcrew.py(or equivalent runtime entrypoint)
- Load secrets from environment variables and provide names in
.env.example. - Record resolved
llm, temperature, and max token controls in Audit.
Mapping
- All CrewAI agent and task definitions MUST be externalized to YAML files under a config/ directory (e.g., config/agents.yaml, config/tasks.yaml).
- Use explicit task context chaining (
Task.context) for deterministic dependency flow. - Define
expected_outputwith required headings and target artifact paths. - Prefer
allow_delegation=falseunless the SAD justifies delegated manager patterns.
Execution
- Prefer sequential process mode for reproducible MVP builds.
- Use hierarchical process mode only when justified in SAD and documented in Audit.
- Baseline controls:
max_iter <= 12for MVP tasks unless explicitly justified.max_execution_timetuned per epic.max_retry_limit >= 2.max_rpmset at crew level for budget stability.
- If using function-calling agents, do not switch mode mid-run; record chosen mode in Audit.
- Use
kickoff_for_eachonly for truly independent batch items and document deterministic merge keys.
Tools
- Bind only the minimum required tool set per agent/task.
- Validate YAML-referenced tools before kickoff to avoid runtime binding errors.
- Keep tool configs JSON-serializable; load secret parameters via env vars.
- Permit web/API tools only where explicitly justified by persona scope.
Logging
- Capture rendered system/user prompts in Prompt Trace before execution.
- Record lifecycle events (task start/stop, retries, guardrail outcomes) in Trace Log.
- Keep Prompt Trace and Trace Log in project-context artifacts, not inline with generated code.
- If using step callbacks/event listeners, redact secrets and persist logs under
project-context/2.build/logs.
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 · 64 lines · 685 tokens per session scan A 42408d72156d
adapter-crewai is a cursor rule published in the GitHub repository synaptic-ai-consulting/AAMAD (80 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 685 tokens to every session, about $0.0034 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.