agent-discover-scanner: Command for Claude Code

.claude/commands/grow-scanner.md

grow-scanner is a command for Claude Code from Defend-AI-Tech-Inc/agent-discover-scanner. It costs 0 tokens per session (702 once invoked), scanned A, original, MIT.

An autonomous task for increasing real-world use of the AgentDiscover scanner, a tool that scans projects for agent-related information. It focuses on improving the product, documentation, first-run experience, output, and discoverability without fabricating results.

In plain words
What is it for?
Use it to improve installation, first scans, example output, troubleshooting guidance, actionable summaries, Markdown reports, and AIBOM or CycloneDX output.
Why use it?
It addresses setup friction and unclear scan results that can prevent security engineers and other users from adopting the scanner.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is Defend-AI-Tech-Inc/agent-discover-scanner's own configuration. It tells Claude Code how to work on agent-discover-scanner itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-discover-scanner configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Defend-AI-Tech-Inc/agent-discover-scanner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Defend-AI-Tech-Inc/agent-discover-scanner/main/.claude/commands/grow-scanner.md
Clone the repo
git clone --depth 1 https://github.com/Defend-AI-Tech-Inc/agent-discover-scanner

Made for: Claude Code.

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 grow-scanner

README.md
[![agentmods](https://agentmods.dev/badge/commands/defend-ai-tech-inc/agent-discover-scanner/grow-scanner/github.svg)](https://agentmods.dev/commands/defend-ai-tech-inc/agent-discover-scanner/grow-scanner)
Your own site
<a href="https://agentmods.dev/commands/defend-ai-tech-inc/agent-discover-scanner/grow-scanner"><img src="https://agentmods.dev/badge/commands/defend-ai-tech-inc/agent-discover-scanner/grow-scanner/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.

agentmods 80×15 button for grow-scanner

Your own site · 80×15
<a href="https://agentmods.dev/commands/defend-ai-tech-inc/agent-discover-scanner/grow-scanner"><img src="https://agentmods.dev/badge/commands/defend-ai-tech-inc/agent-discover-scanner/grow-scanner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 702 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00702
Opus 5 $0.00000 $0.00351
Sonnet 5 $0.00000 $0.00140
Haiku 4.5 $0.00000 $0.00070

Measured 10d ago against content hash a2d14901d831, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

grow-scanner 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 10d 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.

.claude/commands/grow-scanner.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grow AgentDiscover Scanner Traction

Autonomous task: increase real-world adoption of the AgentDiscover scanner.

Rules:

  • NEVER fake metrics (no artificial stars, downloads, or issues)
  • NEVER create fake user testimonials or reviews
  • ONLY improve the product, documentation, and discoverability
  • Every change must make the scanner genuinely more useful

Execute the following improvement categories in order:

1. First-Run Experience (highest impact)

  • Audit the README.md: Can a security engineer go from zero to first scan in under 3 minutes?
  • Ensure pipx install agentdiscover && agent-discover-scanner scan-all ~/projects --duration 30 works flawlessly
  • Add a "What You'll See" section with REAL example output (not mocked)
  • Add a "Common Issues" section addressing known friction points
  • Test the install path on a clean Python 3.10+ environment

2. Output Quality

  • Ensure scan output is immediately actionable (not just raw data)
  • Add a --summary flag that prints a human-readable executive summary
  • Add a --report flag that generates a markdown report suitable for sharing with management
  • Ensure AIBOM/CycloneDX output is valid and parseable by standard tools
  • Add --json output that's clean enough to pipe into jq

3. CI/CD Integration

  • Create a GitHub Action: defendai/agentdiscover-action
  • Usage: add to any repo's CI to scan for AI agents on every PR
  • Output: SARIF format for GitHub Security tab integration
  • Create the action.yml, Dockerfile, and documentation
  • Write a blog-post-ready tutorial: "Add AI Agent Discovery to Your CI Pipeline in 5 Minutes"

4. Comparison Content

  • Create docs/comparisons/ directory
  • Write honest comparisons: AgentDiscover vs Cisco DefenseClaw Skills Scanner
  • Write: AgentDiscover vs manual grep for AI frameworks
  • Write: AgentDiscover vs Nudge Security agent discovery
  • Be honest about limitations — credibility > marketing

5. Integration Guides

  • Create docs/integrations/ directory
  • Write: "Using AgentDiscover with Splunk" (forward JSONL audit to Splunk HEC)
  • Write: "Using AgentDiscover with Elastic/Kibana" (filebeat config for scan output)
  • Write: "Using AgentDiscover in a Kubernetes cluster" (DaemonSet + Tetragon setup)
  • Write: "Using AgentDiscover with GitHub Actions" (reference the action from #3)

Read the full file on GitHub · 59 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. 10d ago First seen · 59 lines · 0 tokens per session scan A a2d14901d831

Subscribe to this mod's changes

grow-scanner is a command published in the GitHub repository Defend-AI-Tech-Inc/agent-discover-scanner (21 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 702 tokens. 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 2026-08-30.