verify

verify is a command for coding agents from JeongJaeSoon/agent-guard. It costs 40 tokens per session (316 once invoked), scanned C, original, MIT.

A command that scans the current project for exposed secrets, including staged, unstaged, and untracked files. It uses Gitleaks, a tool that detects passwords, tokens, and other secret-looking text.

In plain words
What is it for?
Use it before committing changes to find leaked credentials and identify the affected file paths and detection rules.
Why use it?
It checks whether the current files are safe to commit without relying on Git hooks, which are automatic checks that run during certain Git actions.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the agent-guard plugin — 2 skills, 2 commands, 5 hooks 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/jeongjaesoon/agent-guard/verify
Clone the repo
git clone --depth 1 https://github.com/JeongJaeSoon/agent-guard

Or install agent-guard, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 5 hooks.

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 verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/jeongjaesoon/agent-guard/verify.svg)](https://agentmods.dev/commands/jeongjaesoon/agent-guard/verify)
Your own site
<a href="https://agentmods.dev/commands/jeongjaesoon/agent-guard/verify"><img src="https://agentmods.dev/badge/commands/jeongjaesoon/agent-guard/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 316 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 $0.00040 $0.00316
Opus 5 $0.00020 $0.00158
Sonnet 5 $0.00008 $0.00063
Haiku 4.5 $0.00004 $0.00032

Measured 5d ago against content hash e8fc8187d928, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

verify 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 5d 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.

- **`gitleaks config not found`** → the plugin install is incomplete; suggest reinstalling via `curl -fsSL https://github.com/JeongJaeSoon/agent-guard/releases/latest/download/bootstrap.sh | sh`.

Makes network callslowCapability

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

- **`gitleaks config not found`** → the plugin install is incomplete; suggest reinstalling via `curl -fsSL https://github.com/JeongJaeSoon/agent-guard/releases/latest/download/bootstrap.sh | sh`.
plugins/agent-guard/commands/verify.md · 22 lines

What it actually says

/agent-guard:verify

One-shot secret scan over everything currently on disk: staged changes, unstaged changes, and untracked files. Backed by the bundled gitleaks rule set the agent-guard hooks already use, so a clean verify here implies the same thing the hooks would say at commit time.

Run

!"${CLAUDE_PLUGIN_ROOT}/bin/agent-guard" scan-working-tree

Interpretation

  • Exit 0, no output beyond the gitleaks summary → no secrets detected. Tell the user the working tree is clean and stop.
  • Non-zero exit with agent-guard: lines → leaks were flagged. Report the exact file paths and rule names gitleaks emitted, verbatim. Do not propose fixes unless the user asks.
  • required command not found: gitleaks → suggest agent-guard setup --install --gitleaks-checksum <SHA> and stop.
  • gitleaks config not found → the plugin install is incomplete; suggest reinstalling via curl -fsSL https://github.com/JeongJaeSoon/agent-guard/releases/latest/download/bootstrap.sh | sh.

Stay terse: the scan output is the answer. Avoid restating what gitleaks already printed.

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. 5d ago First seen · 22 lines · 40 tokens per session scan C e8fc8187d928

Subscribe to this mod's changes

verify is a command published in the GitHub repository JeongJaeSoon/agent-guard (25 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 316 once invoked, about $0.0002 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 2026-08-30.