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/eliornl/rolemule/rolemule-coregit clone --depth 1 https://github.com/eliornl/rolemuleWhat 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 | $0.02609 | $0.02609 |
| Opus 5 | $0.01305 | $0.01305 |
| Sonnet 5 | $0.00522 | $0.00522 |
| Haiku 4.5 | $0.00261 | $0.00261 |
Grade A, and why
rolemule-core 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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RoleMule Core Conventions
App Name
The product name is RoleMule. Use settings.app_name in templates. The repo/folder name is rolemule.
Standardized Error System
Never raise bare HTTPException — always use APIError or the factory functions from utils/error_responses.py.
from utils.error_responses import APIError, ErrorCode, create_error_response
from utils.error_responses import unauthorized_error, forbidden_error, not_found_error, validation_error, rate_limit_error, internal_error, no_api_key_error
# Raise typed errors
raise APIError(ErrorCode.AUTH_INVALID_CREDENTIALS, "Invalid email or password", status_code=401)
# Or use convenience constructors
raise not_found_error("Workflow session")
raise unauthorized_error()
raise rate_limit_error(retry_after=3600)
raise no_api_key_error() # when neither user key nor server key is configured
Error codes follow a namespace pattern:
AUTH_1xxx— authentication/authorizationVAL_2xxx— validationRES_3xxx— resource not found/conflictRATE_4xxx— rate limitingEXT_5xxx— external service errorsCFG_6xxx— configuration errors (e.g. missing API key)INT_9xxx— internal server errors
Personal access tokens (PAT)
Long-lived CLI/automation auth (rm_pat_ prefix). Implementation: utils/personal_access_tokens.py, migration 20260708_024, API POST/GET/DELETE /api/v1/auth/tokens. get_current_user and WebSocket auth check PAT before JWT. Plaintext shown once on create; SHA-256 hash stored. Revoke all user PATs on password change, password reset, and account delete (with JWT invalidation).
CFG_6001 — No API Key (no_api_key_error())
Use no_api_key_error() (HTTP 422, error_code: "CFG_6001") whenever an LLM-backed endpoint is called but the user is not ready to run LLM. Never use validation_error() for this case — the dedicated code lets the frontend detect it and render a targeted "Add your API key → Settings" prompt instead of a generic error toast.
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.
- 2d ago First seen · 135 lines · 2,609 tokens per session scan A 3feb334cbd82
rolemule-core is a cursor rule published in the GitHub repository eliornl/rolemule (37 stars, last pushed 3d ago), licensed MIT. It adds 2,609 tokens to every session, about $0.0130 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
project-main-rules
You are an expert in building production-ready AI agent applications using Python, FastAPI, LangGraph, and LangChain.
dev-process
Cursor rule "dev-process" from Lawofall/AgentCore, covering 开发工作流, 新会话冷启动, 决策权限, 设计纪律 and 补丁绊线.
multitask
Multitask 模式下主 Agent 与子代理的分工、委派规范、模型约束.
intercept-discipline
硬/软拦截纪律——禁默认加闸;误伤优先;提拦截须走人确认.
langchain-workflow-provider-agnostic
Langchain workflow changes must work regardless of model/provider choice.
cursorrules
Cursor rule "cursorrules" from sseshachala/conductai, covering conductguard policy and agent booster — context-efficient reads.