check

A command for checking recent code changes against guardrails such as scope drift, missing tests, and duplicate abstractions.

In plain words
What is it for?
Running the guardrail check with a base revision, reviewing severity levels, and optionally recording test or lint commands.
Why use it?
It helps identify problems in a change before committing or presenting it as complete.

Command

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/logi-cmd/agent-guardrails/check
Clone the repo
git clone --depth 1 https://github.com/logi-cmd/agent-guardrails
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 425 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00009 $0.00425
Opus 5 $0.00005 $0.00212
Sonnet 5 $0.00002 $0.00085
Haiku 4.5 $0.00001 $0.00042

Measured 2d ago against content hash 2f1973a6bd7c, 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 2d 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.

templates/commands/check.md · 63 lines

What it actually says

/ag:check - Guardrail Check

Triggers

  • User wants to validate recent changes before commit
  • User wants to check scope drift, test coverage, or drift detection
  • User types /ag:check

Context Trigger Pattern

/ag:check [--base-ref <ref>] [--commands-run "<cmd1>, <cmd2>"]

Default behavior: npx agent-guardrails check --base-ref HEAD~1

Behavioral Flow

  1. Run: Execute npx agent-guardrails check --base-ref HEAD~1
  2. Analyze: Review findings (scope-drift, missing-test, new-abstraction)
  3. Report: Show results in chat with severity levels
  4. Fix: If issues found, suggest fixes or run /ag:fix

Key Patterns

  • Scope check: Verify only intended files were modified
  • Test validation: Ensure tests run or are updated
  • Drift detection: Flag parallel abstractions or interface changes

Examples

Basic check

/ag:check
# Runs: npx agent-guardrails check --base-ref HEAD~1

Check with commands run

/ag:check --commands-run "npm test, npm run lint"
# Runs: npx agent-guardrails check --base-ref HEAD~1 --commands-run "npm test, npm run lint"

Check specific base

/ag:check --base-ref origin/main
# Runs: npx agent-guardrails check --base-ref origin/main

Boundaries

Will:

  • Run check and report findings
  • Suggest fixes for found issues
  • Show confidence level of the check

Will Not:

  • Automatically fix issues (use /ag:fix instead)
  • Modify files without user approval
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. 2d ago First seen · 63 lines · 9 tokens per session scan A 2f1973a6bd7c

Subscribe to this mod's changes

check is a command published in the GitHub repository logi-cmd/agent-guardrails (29 stars, last pushed 16d ago), licensed MIT. It adds 9 tokens to every session and 425 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 2026-08-30.