guard

guard is a command for coding agents from open-covenant/covenant. It costs 17 tokens per session (202 once invoked), scanned C, original, Apache-2.0.

A command for checking the latest covguard result. Covguard runs coding agents under a spending limit and sandbox, then creates a signed record of the run.

In plain words
What is it for?
Viewing the latest run, verifying its receipt, or checking whether covguard is installed and healthy.
Why use it?
It gives you the run outcome, spending, and receipt status without running an agent outside those safeguards.

Command

Part of the covenant-guard plugin — 1 command, 1 hook shipped together

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 commands/open-covenant/covenant/guard
Clone the repo
git clone --depth 1 https://github.com/open-covenant/covenant

Or install covenant-guard, the plugin that ships this one along with the rest of its 1 command, 1 hook.

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.

agentmods badge for guard

README.md
[![agentmods](https://agentmods.dev/badge/commands/open-covenant/covenant/guard.svg)](https://agentmods.dev/commands/open-covenant/covenant/guard)
Your own site
<a href="https://agentmods.dev/commands/open-covenant/covenant/guard"><img src="https://agentmods.dev/badge/commands/open-covenant/covenant/guard.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 202 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00202
Opus 5 $0.00009 $0.00101
Sonnet 5 $0.00003 $0.00040
Haiku 4.5 $0.00002 $0.00020

Measured 3d ago against content hash 92182f7e5958, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

guard scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

(`curl -fsSL https://opencovenant.org/guard/install.sh | sh`) and stop. Do not

Makes network callslowCapability

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

(`curl -fsSL https://opencovenant.org/guard/install.sh | sh`) and stop. Do not
plugins/covenant-guard/commands/guard.md · 21 lines

What it actually says

The user is asking about covguard, the local guard that runs coding agents under a spend cap, a sandbox, and a signed receipt. Run the matching command and report the result plainly. Lead with the outcome and the spend against the cap.

Argument: $ARGUMENTS

  • (empty) or status → run covguard receipts show last
  • verify → run covguard receipts show last to find the receipt path, then covguard verify <that receipt.json>
  • doctor → run covguard doctor

If covguard is not installed, tell the user to install it (curl -fsSL https://opencovenant.org/guard/install.sh | sh) and stop. Do not attempt to run agents unguarded on their behalf.

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. 3d ago First seen · 21 lines · 17 tokens per session scan C 92182f7e5958

Subscribe to this mod's changes

guard is a command published in the GitHub repository open-covenant/covenant (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 17 tokens to every session and 202 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.