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/modelengine-group/nexent/app_layer_rulesgit clone --depth 1 https://github.com/ModelEngine-Group/nexentWhat 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 | $0.00000 | $0.01420 |
| Opus 5 | $0.00000 | $0.00710 |
| Sonnet 5 | $0.00000 | $0.00284 |
| Haiku 4.5 | $0.00000 | $0.00142 |
Grade A, and why
app_layer_rules 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose and Scope
- The App layer is the HTTP boundary for the backend. It applies to files under
backend/apps/*.py. - Responsibilities:
- Parse and validate HTTP inputs.
- Call underlying services; do not implement core business logic here.
- Translate domain/service exceptions into
HTTPExceptionwith proper status codes. - Return
JSONResponse(status_code=HTTPStatus.OK, content=payload)on success.
- Configuration: Do not access environment variables directly. Read configuration via
consts.constor pass values through from the request to services.
References: backend/consts/exceptions.py
Routing and URL Design
- Keep existing top-level prefixes for compatibility (e.g.,
"/agent","/memory"). When adding new modules or endpoints, follow these rules:- Use plural nouns for collection-style resources (e.g.,
"/agents","/memories"). - Use snake_case for all path segments. Avoid hyphens and camelCase.
- Prefer resource-oriented paths for CRUD-style operations. Example:
"/agents"(collection),"/agents/{agent_id}"(single resource). - Use action-style paths only when necessary to match current patterns or when the operation is not naturally CRUD (e.g.,
"/agent/run","/agent/stop/{conversation_id}"). - Path parameters must be singular, semantic nouns:
"/agents/{agent_id}","/memories/{memory_id}". - Keep backwards compatibility: do not rename existing routes; new routes should follow these conventions.
- Use plural nouns for collection-style resources (e.g.,
HTTP Methods
- GET: Read and list operations only. Maintain existing special cases where GET performs safe actions (e.g.,
GET /agent/stop/{conversation_id}), but do not introduce new side-effecting GETs. - POST: Create resources, perform searches, or trigger actions with side effects (e.g.,
POST /memory/add,POST /memory/search,POST /agent/run). - DELETE: Delete resources or clear collections (e.g.,
DELETE /memory/clear). Ensure idempotency. - PUT/PATCH: Update resources. Prefer
PUTfor full updates andPATCHfor partial updates. Preserve legacyPOST /updateendpoints for compatibility but favor PUT/PATCH for new code.
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 · 114 lines · 0 tokens per session scan A 108d98af8447
app_layer_rules is a cursor rule published in the GitHub repository ModelEngine-Group/nexent (5,841 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,420 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 2026-08-30.
Other cursor rules, from other repositories
latest-ai-models
Use only the latest AI models from all providers (updated Feb 2026).
callback-system
Lifecycle callback system design for agentic loops.
react-loop
ReAct loop implementation design and pattern details.
laravel-ai-sdk-integration
How Laragentic integrates with and extends the Laravel AI SDK.
developer-experience
Developer experience principles and usage patterns for Laragentic.
package-structure
Directory structure and file organization conventions for the Laragentic package.