A set of security rules for coding-agent work, backed by an MCP server named aegis. MCP is a way for an agent to use external tools or data during a session.

Use it when changing endpoints, permissions, authentication, input validation, security settings, secrets, deployment pipelines, or error handling exposed outside the application.

It makes the agent check security requirements before handling sensitive changes such as authentication, database queries, file uploads, secrets, or external requests. It also requires the agent to follow the returned security policies.

cursorrules — Cursor rule for Cursor by bgigurtsis: A set of security rules for coding-agent work, backed…

Install

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.

agentmods

npx agentmods add rules/bgigurtsis/aegis-mcp/cursorrules

Clone the repo

git clone --depth 1 https://github.com/bgigurtsis/aegis-mcp

Made for: Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/bgigurtsis/aegis-mcp/cursorrules.svg)](https://agentmods.dev/rules/bgigurtsis/aegis-mcp/cursorrules)

Your own site

<a href="https://agentmods.dev/rules/bgigurtsis/aegis-mcp/cursorrules"><img src="https://agentmods.dev/badge/rules/bgigurtsis/aegis-mcp/cursorrules.svg" alt="Measured on agentmods" height="20"></a>

Per session 315 This file is loaded in full into every session.

When invoked 315 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00315	$0.00315
Opus 5	$0.00158	$0.00158
Sonnet 5	$0.00063	$0.00063
Haiku 4.5	$0.00032	$0.00032

Measured 3d ago against content hash ecd164adfaf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 3d 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.

agent-templates/cursor/.cursorrules · 33 lines

What it actually says

You have an MCP server named "aegis".

At session start, read aegis://summary once and use canonical IDs plus known_actions from that resource.

Call aegis_assess before generating code whenever tasks involve:

create-endpoint
database-query
auth-flow-change
external-api-call
file-upload
processing classified data
permission or role-logic changes
untrusted input validation (request body, URL/query params)
security configuration changes (cors, headers, cookies, tls)
secrets handling or credential flow updates
CI/CD pipeline or release automation changes
externally reachable error-handling paths

When calling aegis_assess:

Use canonical IDs from security-context.yaml
Include services, data_types, boundary_crossing, auth_scope, input_sources, and action
Set action using a value from aegis://summary.known_actions

Enforce all returned requirements in generated code. Prefer approved_patterns and avoid anti_patterns. Apply returned security_configs, secrets_management, pipeline_policies, and error_handling policies when present. If no_match=true or warnings mention unknown IDs, tell the user schema updates may be required.

After generating security-relevant code, call aegis_review:

Send requirements from the previous aegis_assess response
Send mappings with { requirement_id, satisfied_by } entries
If pass=false or missing is non-empty, revise the code before final output

Changes

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.

3d ago First seen · 33 lines · 315 tokens per session scan A ecd164adfaf0

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository bgigurtsis/aegis-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 315 tokens to every session, about $0.0016 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 2026-08-31.

Security

cursorrules

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

cli-error-handling

prefer-direct-imports-over-module-mocks

control-plane-descriptors

family-instance-domain-actions