check

Run validation command from README and report all issues.

Command for Claude Code

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/jnarowski/agentcmd/check
Clone the repo
git clone --depth 1 https://github.com/jnarowski/agentcmd

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00009 $0.00575
Opus 5 $0.00005 $0.00287
Sonnet 5 $0.00002 $0.00115
Haiku 4.5 $0.00001 $0.00057

Measured today against content hash 716cd5e5a27a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check 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 today.

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/check.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Check

Reads the ## Validation section from README.md, runs the validation command, and reports all issues including errors and warnings. Does not make any fixes.

Variables

  • $format: $1 (optional) - Output format: "text" or "json" (defaults to "text" if not provided)

Workflow

  1. Read README.md

    • Locate the ## Validation section (search for exact header text)
    • Extract the command shown in the code block under this section
    • If no command is found, report error and stop
  2. Run Validation

    • Execute the validation command using the Bash tool
    • Capture the full output including errors, warnings, and info messages
    • Do not attempt to fix any issues
  3. Parse and Categorize Issues

    • Analyze the output to identify all issues
    • Group issues by type:
      • Errors: Critical issues that prevent builds/tests from passing
      • Warnings: Non-critical issues that should be addressed
      • Info: Informational messages
    • Count issues in each category
  4. Report Results

    • Display the validation command that was executed
    • Show total counts by category (e.g., "5 errors, 3 warnings")
    • Display the full validation output
    • Summarize the validation status (pass/fail)
    • If there are issues, suggest running /fix to automatically resolve them

Report

JSON

IMPORTANT: If $format is "json", return raw JSON output (no ```json code fences, no markdown):

{
  "success": true,
  "validation_command": "bun run build && bun test",
  "issues": {
    "errors": 5,
    "warnings": 3,
    "info": 2
  }
}

JSON Field Descriptions:

  • success: Always true if check command completed (even if validation failed)
  • validation_command: The command that was executed from README
  • issues.errors: Number of errors found
  • issues.warnings: Number of warnings found
  • issues.info: Number of info messages found

Text

Otherwise, provide this human-readable information to the user:

Read the full file on GitHub · 83 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. today First seen · 83 lines · 9 tokens per session scan A 716cd5e5a27a

Subscribe to this mod's changes

check is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 9 tokens to every session and 575 once invoked, about $0.0000 per session on Opus 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 2026-09-01.