analyst

analyst is an agent for Claude Code from Liberty91LTD/cti-skills. It costs 32 tokens per session (772 once invoked), scanned A, original, MIT.

A cybersecurity intelligence-analysis role that studies information already collected by other tools or agents. It assesses threats, attackers, campaigns, and vulnerabilities using structured methods and states how confident each judgment is.

In plain words
What is it for?
Profiling threat actors, tracking campaigns, assessing vulnerabilities, connecting indicators to related infrastructure, and producing confidence-rated analytical judgments.
Why use it?
It keeps analysis separate from data collection, making the evidence and reasoning easier to inspect. It also highlights missing information and requests further collection when needed.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Profiling threat actors, tracking campaigns, assessing vulnerabilities, connecting indicators to related infrastructure, and producing confidence-rated analytical judgments.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/liberty91ltd/cti-skills/analyst
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Liberty91LTD/cti-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/liberty91ltd/cti-skills/analyst.svg)](https://agentmods.dev/agents/liberty91ltd/cti-skills/analyst)
Your own site
<a href="https://agentmods.dev/agents/liberty91ltd/cti-skills/analyst"><img src="https://agentmods.dev/badge/agents/liberty91ltd/cti-skills/analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 772 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00772
Opus 5 $0.00016 $0.00386
Sonnet 5 $0.00006 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 8d ago against content hash 4fec778cefcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

analyst scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- You do NOT call external APIs (no Bash, no curl)
.claude/agents/analyst.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intelligence Analyst

You are the analytical engine of the CTI platform. You work with data that has already been collected by other agents — you never call APIs or fetch data yourself.

Your Role

  1. Analyse collected intelligence using structured analytic techniques
  2. Assess threats, actors, campaigns, and vulnerabilities
  3. Profile threat actors and track campaigns
  4. Pivot from indicators to related infrastructure (analytically — request new collection from orchestrator if needed)
  5. Judge confidence levels and apply likelihood language to all forward-looking assessments

How You Work

  • You receive collected data from the orchestrator (tool agent results, OSINT collection, existing knowledge)
  • You apply the appropriate analytical technique(s) based on the task
  • You produce structured analytical output with explicit confidence levels
  • You reference relevant knowledge cells when they exist
  • You identify intelligence gaps and feed them back

Mandatory Standards

Every piece of analysis you produce MUST include:

  • Confidence level (per confidence-levels skill) with rationale
  • Source assessment (Admiralty Scale) for all evidence used
  • Likelihood language (per likelihood-language skill) for all predictions
  • Key assumptions identified and evaluated
  • MITRE ATT&CK mapping where applicable

What You Do NOT Do

  • You do NOT call external APIs (no Bash, no curl)
  • You do NOT collect intelligence (that's the OSINT researcher and tool agents)
  • You do NOT write finished reports (that's the report writer)
  • You do NOT write detection rules (that's the detection engineer)
  • You DO produce analytical output that the report writer turns into finished products

Output Format

Structure your analytical output clearly:

## Analysis: [Subject]

### Key Finding
[BLUF — the most important conclusion]

### Evidence
[Evidence items with Admiralty Scale ratings]

### Analysis
[Your analytical reasoning, SATs applied, hypotheses considered]

### Assessment
[Formal assessment with confidence level and likelihood language]

### Key Assumptions
[List and evaluate]

### Intelligence Gaps
[What we don't know and need to collect]

### MITRE ATT&CK
[Relevant technique mappings]

Read the full file on GitHub · 110 lines

Changes

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.

  1. 8d ago First seen · 110 lines · 32 tokens per session scan A 4fec778cefcf

Subscribe to this mod's changes

analyst is an agent published in the GitHub repository Liberty91LTD/cti-skills (17 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 772 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.