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/security-pythongit 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 | $0.00000 | $0.02128 |
| Opus 5 | $0.00000 | $0.01064 |
| Sonnet 5 | $0.00000 | $0.00426 |
| Haiku 4.5 | $0.00000 | $0.00213 |
Grade A, and why
security-python scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
from urllib.parse import urlparse How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Security Patterns
XSS Sanitization (always sanitize LLM and user content)
from utils.security import sanitize_text, sanitize_html, sanitize_llm_output
clean = sanitize_text(user_input) # strips all HTML
clean = sanitize_html(html_content) # allows safe tags only
clean = sanitize_llm_output(llm_response) # recursive sanitize for LLM dicts
Always call sanitize_llm_output() before returning agent results to the client.
File Upload MIME Validation
Never trust the file extension — always check magic bytes.
Two main upload paths (do not mix limits):
| Path | Where | Max size | Magic / constants |
|---|---|---|---|
| Profile resume | POST /api/v1/profile/parse-resume, resume upload in profile setup / settings |
10 MB | _RESUME_MAGIC in api/profile.py |
| Workflow job description | POST /api/v1/workflow/start (job_file), New Application → Upload File |
5 MB | _JOB_FILE_MAGIC in api/workflow.py |
Both allow .pdf, .txt, .docx (ZIP signature for DOCX). Workflow job uploads do not support legacy binary .doc.
Use APIError / validation_error() from utils/error_responses.py in app code — never bare HTTPException (the snippet below illustrates the magic-bytes pattern only):
MAX_UPLOAD_SIZE_BYTES = 10 * 1024 * 1024 # 10 MB — profile resume; workflow `job_file` uses 5 MB in api/workflow.py
_FILE_MAGIC = { "pdf": b"%PDF", "docx": b"PK\x03\x04", "txt": None }
content = await upload_file.read()
if len(content) > MAX_UPLOAD_SIZE_BYTES:
raise HTTPException(status_code=413, detail="File too large.")
magic = _FILE_MAGIC.get(ext)
if magic is not None and not content.startswith(magic):
raise HTTPException(status_code=400, detail="File content does not match declared type.")
if ext == "txt":
try: content.decode("utf-8")
except UnicodeDecodeError:
raise HTTPException(status_code=400, detail="TXT files must be UTF-8 encoded.")
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 · 183 lines · 2,128 tokens per session scan A 26ea027a92f5
security-python is a cursor rule published in the GitHub repository eliornl/rolemule (37 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,128 tokens. A static security scan graded it A with 1 finding (makes network calls). 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
cursorrules
Agent2 is a framework for building production AI agents with typed HTTP APIs. PydanticAI handles the agent loop. Agent2 handles everything else: API, auth, pause/resume, approvals, provider routing, knowledge search.
product-manager
Holistic product leader who owns the full product lifecycle — from discovery and strategy through roadmap, stakeholder alignment, go-to-market, and outcome measurement. Bridges business goals, user needs, and technical reality to ship the right thing at the right time.
api-tester
Expert API testing specialist focused on comprehensive API validation, performance testing, and quality assurance across all systems and third-party integrations.
developer-advocate
Expert developer advocate specializing in building developer communities, creating compelling technical content, optimizing developer experience (DX), and driving platform adoption through authentic engineering engagement. Bridges product and engineering teams with external developers.
architectural-and-structural-rules
The project follows a layered architecture with clear separation of concerns.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.