secure-agent

A security setup for an AI agent that limits which commands it can run and which web addresses its templates can contact.

In plain words
What is it for?
Use it after setting up Earl to block selected commands such as curl, gh, or stripe-cli and to restrict network access. It supports Claude Code, Cursor, and Windsurf with different levels of enforcement.
Why use it?
It makes the agent's security rules enforceable at the platform level instead of relying only on instructions in a configuration file. It also helps prevent the agent from reaching unauthorized services, although command restrictions can have workarounds.

Skill for Claude CodeCodex

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 skills/mathematic-inc/earl/secure-agent
Any agent
npx skills add mathematic-inc/earl --skill secure-agent
Clone the repo
git clone --depth 1 https://github.com/mathematic-inc/earl

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,851 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.01851
Opus 5 $0.00024 $0.00925
Sonnet 5 $0.00010 $0.00370
Haiku 4.5 $0.00005 $0.00185

Measured 2d ago against content hash ee9871116fb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

secure-agent 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **`deniedTools`**: Blocks specific bash commands (curl, gh, stripe-cli, etc.) at the
skills/development/secure-agent/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Secure Agent

After Earl is set up and working, this skill restricts the agent's ability to bypass Earl and make raw API/CLI calls directly. Without this step, CLAUDE.md is just a suggestion.

What This Does

  1. deniedTools: Blocks specific bash commands (curl, gh, stripe-cli, etc.) at the platform level for Claude Code. Agents cannot run these commands at all.
  2. Egress rules: Restricts which URLs Earl templates can contact, preventing Earl itself from being used as an open proxy.

Important Limitation

deniedTools pattern matching can be bypassed via alternative tools (python3 -c "import urllib...", node -e "fetch(...)", etc.). This blocks accidental or habitual CLI use — the common case. For stronger containment, pair with OS-level firewall rules or a network proxy.

Platform Support

Platform Mechanism Hard restriction?
Claude Code deniedTools in .claude/settings.json Yes — platform enforced
Cursor .cursor/mcp.json or Cursor settings UI Partial — check Cursor docs for per-tool restrictions
Windsurf .windsurf/mcp.json or Windsurf settings UI Partial — check Windsurf docs for per-tool restrictions
Claude Desktop No bash access N/A
Non-MCP CLI agents CLAUDE.md instructions only No — advisory only

This skill primarily targets Claude Code. Instructions for other platforms are best-effort.


Step 1: Check Coverage

Only deny tools for services that have Earl templates. Denying a tool for a service with no Earl template would leave the agent unable to interact with that service at all.

Read the full file on GitHub · 196 lines

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.

  1. 2d ago First seen · 196 lines · 48 tokens per session scan A ee9871116fb0

Subscribe to this mod's changes

secure-agent is a skill published in the GitHub repository mathematic-inc/earl (113 stars, last pushed 5d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,851 once invoked, about $0.0002 per session on Opus 5. 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.

Related

Other skills, from other repositories

api-design-patterns

Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices.

aAAaqwq/AGI-Super-Team · 29 tokens

api-design

Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error envelope, pagination, idempotency — emitted as OpenAPI 3.1. NOT implementing the endpoints (that is fastapi/nestjs/go/nodejs), NOT auth hardening (that is secure-coding), NOT…

ericrisco/rsc-harness · 105 tokens

api-designer

Designs production-grade APIs — REST, GraphQL, gRPC, and AsyncAPI patterns including pagination, versioning, error handling, rate limiting, and API governance. Use when the user asks to design APIs, create endpoints, build an API layer, write OpenAPI specs, or needs help with REST/GraphQL/gRPC service design.

buiphucminhtam/forgewright · 73 tokens

api-design

Design and implement RESTful APIs with proper routing, validation, error handling, and documentation. Use when building new API endpoints, designing API architecture, or improving existing APIs.

asgarovf/locusai · 37 tokens

api-design

RESTful, GraphQL, gRPC, and API best practices.

miles990/claude-software-skills · 16 tokens

api-design-first

Design-first API development skill. Generates OpenAPI 3.1 specifications, enforces REST design best practices, validates endpoints, handles versioning, pagination, error formatting, authentication patterns, rate limiting, and idempotency. Activates when users say "design an API", "create OpenAPI spec", "API endpoint"…

JPeetz/agent-skills · 117 tokens