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.
npx agentmods add commands/logi-cmd/agent-guardrails/checkgit clone --depth 1 https://github.com/logi-cmd/agent-guardrailsWhat 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.
| Model | Per session | Once 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 |
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.
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
- Run: Execute
npx agent-guardrails check --base-ref HEAD~1 - Analyze: Review findings (scope-drift, missing-test, new-abstraction)
- Report: Show results in chat with severity levels
- 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:fixinstead) - Modify files without user approval
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.
- 2d ago First seen · 63 lines · 9 tokens per session scan A 2f1973a6bd7c
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.
Other commands, from other repositories
everme-help
Print a concise EverMe plugin status + reference card.
release
Walk the llmwiki release process step by step.
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
capture-feedback
Quick feedback capture with structured signals.
migrate
Command "migrate" from chohra-med/expo_boilerplate, covering invocation, steps and rule.
cost-tracker
Track session costs, understand token spend, and get optimization tips.