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 alelaguard/agentguards-plugins --skill guardrailsgit clone --depth 1 https://github.com/alelaguard/agentguards-pluginsWrote 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/alelaguard/agentguards-plugins/guardrails)<a href="https://agentmods.dev/skills/alelaguard/agentguards-plugins/guardrails"><img src="https://agentmods.dev/badge/skills/alelaguard/agentguards-plugins/guardrails.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00471 |
| Opus 5 | $0.00026 | $0.00235 |
| Sonnet 5 | $0.00010 | $0.00094 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
guardrails 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 7d 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.
command that invokes `curl`/`wget`/`http`/`fetch`/`aria2c` — redacting or What it actually says
AgentGuards — self-hosted, hooks-only
This variant bundles no MCP server, so there is no check_input/authorize_action
to reach for — do not ToolSearch for them, they are not installed here.
That is not reduced protection. The three hooks in hooks/hooks.json enforce
deterministically, on every request, regardless of anything the model does:
UserPromptSubmitscreens every prompt before you see it. A block or escalate exits non-zero and you never receive the message.PreToolUseauthorizes everyBashcommand before it runs.PostToolUsescans content fromWebFetch,WebSearch, and anyBashcommand that invokescurl/wget/http/fetch/aria2c— redacting or withholding it before you read it.
Nothing here requires you to call a tool, check a decision, or format a block message — the hook has already acted by the time you see (or don't see) the result. If a hook blocks something, its message appears as the tool result or the reason a prompt was rejected; reply with that message rather than composing your own.
Why no MCP server: Claude Code's plugin .mcp.json cannot substitute an
environment variable into its url field, so a URL baked in at publish time
cannot be made to point at each installer's own appliance — it would either be
fixed to one instance or, worse, silently fall back to AgentGuards' hosted
service. Rather than ship that, this variant relies entirely on the hooks,
which read AGENTGUARDS_URL correctly per installation because they are a
subprocess, not a static config file. If you're on the hosted product instead
of a self-hosted appliance, install agentguards-claude, which does bundle the
MCP server.
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.
- 7d ago First seen · 35 lines · 52 tokens per session scan A d2ef61a5a374
guardrails is a skill published in the GitHub repository alelaguard/agentguards-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 52 tokens to every session and 471 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
clawmoat
Real-time AI agent security scanner. Detects prompt injection, jailbreak attempts, credential/secret leaks, PII exposure, and dangerous tool calls. Activate when: (1) scanning inbound messages or tool outputs for prompt injection, (2) checking outbound content for credential leaks or PII, (3) auditing agent session…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-langchain
Integrate Arcjet security into a LangChain JS createAgent using @arcjet/guard — wrap tool() / StructuredTool, put guardMiddleware on createAgent({ middleware }) for MCP / unwrapped tools, and read configurable.threadid for correlation. Use when asked to add Arcjet to langchain createAgent, rate limit its tools, screen…
integrate-arcjet-guard-google-adk
Integrate Arcjet security into a Google ADK JS app using @arcjet/guard — put guardPlugin first on Runner({ plugins }) so beforeToolCallback gates tools, and read a caller-owned id from helper options or context. Use when asked to add Arcjet to Google ADK, @google/adk, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-langgraph
Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…
integrate-arcjet-guard-mastra
Integrate Arcjet security into a Mastra agent using @arcjet/guard — wrap createTool execute, screen input/output with a Processor tripwire, and gate unwrapped MCP/workspace tools with hooks. Use when asked to add Arcjet to a Mastra agent, rate limit its tools, screen inbound messages, or block prompt injection / PII.