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 skills add gnt-ai/gnt --skill gnt-check-actiongit clone --depth 1 https://github.com/gnt-ai/gntWrote 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/skills/gnt-ai/gnt/gnt-check-action)<a href="https://agentmods.dev/skills/gnt-ai/gnt/gnt-check-action"><img src="https://agentmods.dev/badge/skills/gnt-ai/gnt/gnt-check-action/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.
<a href="https://agentmods.dev/skills/gnt-ai/gnt/gnt-check-action"><img src="https://agentmods.dev/badge/skills/gnt-ai/gnt/gnt-check-action.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00349 |
| Opus 5 | $0.00016 | $0.00175 |
| Sonnet 5 | $0.00007 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
gnt-check-action 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 12d 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
Check actions with gnt-brain
Cline has gnt-brain available as an MCP server named gnt-brain. It exposes check_action,
search_rules, get_rule, list_skill_packs, and get_skill_pack.
Before taking an action
Before sending a message, moving money, deleting data, or taking another action that is hard to
undo, call check_action with a plain-English description of the exact action.
The client or executor must require an allowed verdict for the same recipient, amount, target,
and scope. Run a new check if any detail changes.
- If the verdict is
allowed, proceed. - If the verdict is
blocked, stop. Explain why and cite the returned rule. - If the verdict is
needs_human, stop and ask a human to approve the action.
A missing, failed, expired, or unclear verdict is not permission to continue.
Before answering a policy question
Use search_rules to find approved rules and get_rule to retrieve the full text of a rule. Use
list_skill_packs and get_skill_pack for compiled company context. Do not infer policy from
drafts, rules in review, rejected rules, or deprecated rules.
When a human is needed
Do not retry with a softer description, route around the check, or decide for the human. Show the proposed action and gnt-brain's reason, then wait for the human's decision.
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.
- 12d ago First seen · 35 lines · 33 tokens per session scan A d307766487f5
gnt-check-action is a skill published in the GitHub repository gnt-ai/gnt (30 stars, last pushed 4d ago), licensed Apache-2.0. It adds 33 tokens to every session and 349 once invoked, about $0.0002 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 skills, from other repositories
achieving-cmmc-level-2-compliance
Prepare a defense-contractor environment for CMMC Level 2 certification: scope CUI and FCI, implement the 110 NIST SP 800-171 Rev 2 security requirements across 14 families, compute the SPRS score with the DoD Assessment Methodology, manage a compliant POA&M, and ready the organization for a C3PAO assessment. Use when…
implementing-gdpr-data-protection-controls
The General Data Protection Regulation (EU) 2016/679 (GDPR) is the EU's comprehensive data protection law governing the collection, processing, storage, and transfer of personal data. This skill cover.
implementing-pci-dss-compliance-controls
PCI DSS 4.0.1 establishes 12 requirements across 6 control objectives for organizations that store, process, or transmit cardholder data. With PCI DSS 3.2.1 retiring April 2024 and 51 new requirements.
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
iso-24495-2
Sector-specific Plain Language standard for legal communication (ISO 24495-2:2025). Applied during contract drafting, license review, and legal/compliance writing.
compliance
Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (that is gdpr-privacy, terms-conditions)…