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.
git clone --depth 1 https://github.com/logi-cmd/agent-guardrailsWrote 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.
[](https://agentmods.dev/rules/logi-cmd/agent-guardrails/agent-guardrails-enforce)<a href="https://agentmods.dev/rules/logi-cmd/agent-guardrails/agent-guardrails-enforce"><img src="https://agentmods.dev/badge/rules/logi-cmd/agent-guardrails/agent-guardrails-enforce.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00122 | $0.00122 |
| Opus 5 | $0.00061 | $0.00061 |
| Sonnet 5 | $0.00024 | $0.00024 |
| Haiku 4.5 | $0.00012 | $0.00012 |
Grade A, and why
agent-guardrails-enforce 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 7d 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
agent-guardrails: ALWAYS run before finishing
Before telling the user a task is done, you MUST:
- Run:
agent-guardrails check --base-ref HEAD~1 - If issues found → fix them first, do NOT say "done"
- If clean → include the check result in your summary
- If command not found → tell user to run
npx agent-guardrails setup
This is not optional. Skipping this check means the task is incomplete.
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.
- 7d ago First seen · 13 lines · 122 tokens per session scan A f29f7f14b37c
agent-guardrails-enforce is a cursor rule published in the GitHub repository logi-cmd/agent-guardrails (29 stars, last pushed 21d ago), licensed MIT. It adds 122 tokens to every session, about $0.0006 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 cursor rules, from other repositories
bootstrap-alwayson
Minimal always-required LLM fixes.
agents
Always-loaded project anchor. Read this first. Contains project identity, non-negotiables, commands, and pointer to ROUTER.md for full context.
reqforge-dev-build
Dev Builder — implementation execution. Build code phase by phase following DEV-PLAN, each Task goes through review → fix loop.
execution
Repository execution and verification commands.
mena-payment-guardian
Use when building or reviewing Arab/MENA payment or BNPL flows with Paymob, FawryPay, Geidea, PayTabs, Tap Payments, MyFatoorah, HyperPay, Moyasar, Amazon Payment Services, EasyKash, Kashier, PaySky, Tabby, Tamara, valU, Souhoola, callbacks, webhooks, HMAC, SecureHash, redirects, refunds, captures, or payment secrets.
no-tool-contributors
Never add AI coding tools as contributors or co-authors.