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 skills add sp3ak/safenode-mcp-gateway --skill safenode-policiesgit clone --depth 1 https://github.com/sp3ak/safenode-mcp-gatewayWrote 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.
[](https://agentmods.dev/skills/sp3ak/safenode-mcp-gateway/safenode-policies)<a href="https://agentmods.dev/skills/sp3ak/safenode-mcp-gateway/safenode-policies"><img src="https://agentmods.dev/badge/skills/sp3ak/safenode-mcp-gateway/safenode-policies/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sp3ak/safenode-mcp-gateway/safenode-policies"><img src="https://agentmods.dev/badge/skills/sp3ak/safenode-mcp-gateway/safenode-policies.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00112 | $0.02109 |
| Opus 5.5 | $0.00045 | $0.00844 |
| Sonnet 5.5 | $0.00022 | $0.00422 |
| Haiku 4.5 | $0.00011 | $0.00211 |
Grade A, and why
safenode-policies 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 17d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing SafeNode policies
SafeNode evaluates each proposed action and returns allow, warn, review or deny. A policy
is a JSON definition with hard rules (any failure denies) and soft rules (each one adds
risk, and the total score is banded into a decision). The user edits policies in the SafeNode
dashboard under Policy: each policy has versions, and Set active on a version makes it the
one evaluations use.
Your job: turn "what should my agent be allowed to do" into rules, explain each one in plain words, and hand the user JSON they can paste.
Step 1: Inventory the actions
List what the agent can actually do, then sort it into tiers with the user:
| Tier | Examples | Usual decision |
|---|---|---|
| Read-only | read_file, list_*, search_*, get_* |
allow |
| Reversible writes | create a task, write inside the project folder | allow or warn |
| Costly or external | send email, create invoice, open a PR, payment | review |
| Destructive | delete_*, drop table, force push, rm |
deny |
Ask which tier any unclear tool belongs in. Don't guess for anything that costs money or can't be undone.
Step 2: Know what the policy can see
Every evaluation carries an action_type, a payload (the arguments) and a context.
Through the MCP gateway, every call has action_type: "mcp_tool_call". The tool is identified
in context, not in the action type:
| Context key | Value |
|---|---|
tool_name |
The tool's name on the downstream server |
exposed_tool_name |
The name the agent sees (with a <server>__ prefix if names collided) |
server_name |
The gateway's name for the downstream server |
session_id |
One per gateway process |
| anything you add | From context in the gateway config: globally, per server or per tool (they merge) |
So rules like action_type_match on delete_* do nothing behind the gateway. Target tools with
context: either an allowlist on tool_name, or a tag you attach per tool in the gateway config
(see the patterns below).
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.
- 17d ago First seen · 161 lines · 112 tokens per session scan A 1647d185e51e
safenode-policies is a skill published in the GitHub repository sp3ak/safenode-mcp-gateway (0 stars, last pushed 17d ago), licensed MIT. It adds 112 tokens to every session and 2,109 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-19.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…