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 Liberty91LTD/cti-skills --skill tlp-guidegit clone --depth 1 https://github.com/Liberty91LTD/cti-skillsWrote 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/liberty91ltd/cti-skills/tlp-guide)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/tlp-guide"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/tlp-guide/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/liberty91ltd/cti-skills/tlp-guide"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/tlp-guide.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.00985 |
| Opus 5 | $0.00030 | $0.00492 |
| Sonnet 5 | $0.00012 | $0.00197 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
tlp-guide 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Traffic Light Protocol (TLP) v2.0
Every intelligence output from this platform MUST have a TLP designation. This is enforced by platform rules and validated by hooks.
TLP Definitions
TLP:RED — Named Recipients Only
When to use: Information that would cause significant harm if shared beyond the named recipients. Sources may face risk.
- Share with: Only the named recipients, in person or via secure channels
- Do NOT share with: Anyone not explicitly named, even within the same organisation
- Examples: Active zero-day exploitation details shared to a specific CISO; source-identifying intelligence; ongoing law enforcement operation details
TLP:AMBER+STRICT — Organisation Only
When to use: Information that requires support to be effectively acted upon, limited to the recipient's organisation only.
- Share with: Members of the recipient's own organisation on a need-to-know basis
- Do NOT share with: External parties, clients, partners, or affiliated organisations
- Examples: Targeted threat intelligence specific to one organisation's infrastructure; internal investigation findings
TLP:AMBER — Organisation + Need-to-Know
When to use: Information that requires support to be effectively acted upon, and may be shared with clients/partners on a need-to-know basis.
- Share with: Members of the recipient's organisation AND their clients/partners who need the information to protect themselves
- Do NOT share with: The general public, social media, or parties without a clear need-to-know
- Examples: Sector-specific threat briefings shared with ISAC members; IOCs for active campaigns affecting a supply chain
TLP:GREEN — Community
When to use: Information useful for awareness within a broader community but not for public disclosure.
- Share with: The wider community (sector peers, security community) but not via publicly accessible channels
- Do NOT share with: The general public, social media, public blogs, or news outlets
- Examples: General threat landscape updates shared at closed conferences; new TTP descriptions shared within an ISAC
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.
- 8d ago First seen · 102 lines · 61 tokens per session scan A 2439420e960f
tlp-guide is a skill published in the GitHub repository Liberty91LTD/cti-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 985 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
ai-ad-copy-compliance-review
A risk-review assistant for advertising and sales copy. It examines provided material for possible concerns and suggests actions.
ai-contract-clause-risk-review-cn
A Chinese-language assistant for reviewing risks in contract clauses. It is intended for human resources, management, operations, and software-related work.
ai-financial-marketing-compliance-review
A financial marketing compliance review assistant for examining pricing or marketing material for financial concerns.
ai-insurance-policy-faq-explainer
A risk-review helper for explaining questions about insurance policies and their possible risks. It produces summaries, diagnoses, recommended actions, and reusable deliverables from supplied material.
ai-live-commerce-script-compliance-review
A risk review assistant for checking provided live-commerce scripts and producing findings, recommendations, and reusable review materials.
ai-medical-content-compliance-review
A risk review assistant for checking provided medical content and producing findings, recommendations, and reusable review materials.