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 threat-assessmentgit 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/threat-assessment)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/threat-assessment"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/threat-assessment/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/threat-assessment"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/threat-assessment.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 | $0.00069 | $0.02469 |
| Opus 5.5 | $0.00028 | $0.00988 |
| Sonnet 5.5 | $0.00014 | $0.00494 |
| Haiku 4.5 | $0.00007 | $0.00247 |
Grade A, and why
threat-assessment 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 1mo 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Assessment Methodology
A threat assessment evaluates the threat posed by a specific actor or scenario to a specific target. It combines Intent, Capability, and Opportunity into an overall Threat Level.
Formula
Threat = Intent + Capability + Opportunity
All three must be present for a credible threat. A highly capable actor with no intent poses minimal threat. A motivated actor with no capability poses minimal threat.
Evidence: Graded Preferred, Ungraded Allowed
An assessment is best built on graded evidence items, one per claim, as produced by /quality-of-information-check (the QoI JSON or its claim table). The schema is in skills/quality-of-information-check/references/evidence-item-schema.md. Grading is the default. It is not a condition for writing the assessment.
- Handed a QoI output: proceed.
- Handed raw URLs, articles, vendor reports or pasted text: invoke
/quality-of-information-checkfirst, passing the assessment question so it can mark which claims are load-bearing. Build the assessment from its output. This is the default and needs no permission. - Handed a mix: grade what can be graded and carry the rest as ungraded.
- The user asks to skip grading, or
/quality-of-information-checkcannot be run: write the assessment in ungraded mode. Say once what that costs, then proceed. Do not ask again.
Ungraded mode
Any assessment that uses at least one ungraded item from reporting follows these rules:
- Label it. The header carries
Evidence basis: ungradedwhen nothing is graded,mixedwhen some items are, andgradedwhen all are. - Do not invent grades. An ungraded item is listed in Sources as
ungraded. Where the analyst supplied a rating through/source-assessment, show it asAdmiralty B2 (analyst). An Admiralty rating applies to a lookup result or a single item, the evidence grade applies to a claim from a document, and neither is converted into the other. - Confidence is capped at Moderate when any item the conclusion depends on is ungraded. High is reserved for conclusions whose load-bearing claims are all graded and independently confirmed. Weak logic or a single unverified source lowers it further, as always.
- Name the ungraded items in the confidence rationale, and say that running
/quality-of-information-checkon them may raise or lower the level:
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.
- 1mo ago Changed · +65 lines · +43 tokens per session 424e144b25e1
- 2mo ago First seen · 104 lines · 26 tokens per session scan A b888479fd7a5
threat-assessment is a skill published in the GitHub repository Liberty91LTD/cti-skills (36 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 2,469 once invoked, about $0.0003 per session on Opus 5.5. 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
analyzing-campaign-attribution-evidence
Systematically evaluate cyber-campaign evidence to attribute an operation to a threat actor, using the Diamond Model and Analysis of Competing Hypotheses (ACH) to weigh infrastructure overlaps, TTP consistency, malware code similarity, and timing/language artifacts into confidence-weighted attribution assessments. Use…
analyzing-threat-actor-ttps-with-mitre-attack
MITRE ATT&CK is a globally-accessible knowledge base of adversary tactics, techniques, and procedures (TTPs) based on real-world observations. This skill covers systematically mapping threat actor beh.
analyzing-threat-landscape-with-misp
Analyze the threat landscape using MISP (Malware Information Sharing Platform) by querying event statistics, attribute distributions, threat actor galaxy clusters, and tag trends over time. Uses PyMISP to pull event data, compute IOC type breakdowns, identify top threat actors and malware families, and generate threat…
analyzing-campaign-attribution-evidence
Use when campaign attribution analysis involves systematically evaluating evidence to determine which threat actor or group is responsible for a cyber operation. This skill covers collecting and weighting attr.
prompt-injection-auditor
Security audit of LLM system prompts, agent instruction files (SKILL.md, AGENTS.md, CLAUDE.md), and agent configurations against prompt injection attacks. Use when the user wants to (1) audit or harden a system prompt or agent instructions against prompt injection, (2) review an agent skill or system prompt for…
analyzing-campaign-attribution-evidence
Campaign attribution analysis involves systematically evaluating evidence to determine which threat actor or group is responsible for a cyber operation. This skill covers collecting and weighting attr.