What is cti-skills CLAUDE.md?

A set of instructions for using the cti-skills cybersecurity threat-intelligence pack with Claude Code and compatible agent tools. It includes skills, optional agents, integration guides, and command-line tools for analysing collected security information.

Orienting agents in the pack, analysing threats and campaigns, processing indicators, coordinating intelligence work, and using the included lookup and reporting workflows.

It gives a project a shared structure and vocabulary for handling threat intelligence. The pack separates collecting information from analysing it and from producing security detections.

How Liberty91LTD/cti-skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Liberty91LTD/cti-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Liberty91LTD/cti-skills/main/CLAUDE.md

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/liberty91ltd/cti-skills/claude-md/github.svg)](https://agentmods.dev/instructions/liberty91ltd/cti-skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/liberty91ltd/cti-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/liberty91ltd/cti-skills/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/liberty91ltd/cti-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/liberty91ltd/cti-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 883 This file is loaded in full into every session.

When invoked 883 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00883	$0.00883
Opus 5	$0.00441	$0.00441
Sonnet 5	$0.00177	$0.00177
Haiku 4.5	$0.00088	$0.00088

Measured 10d ago against content hash 3706e9261cc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cti-skills CLAUDE.md 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 10d 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.

CLAUDE.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cti-skills — Claude Code orientation

Cyber Threat Intelligence skills pack for Claude Code and other agentic IDEs. See AGENTS.md for the platform-neutral orientation — this file adds Claude-Code-specific notes.

What's here

skills/ — 75 composable CTI skills flat at the repo root per Agent Skills spec. Each is a directory with a SKILL.md. Canonical user-invokable interface. Works in any Agent-Skills-compatible IDE.
.claude-plugin/marketplace.json — plugin manifest, install via /plugin marketplace add Liberty91LTD/cti-skills.
.claude/agents/ — optional Claude-Code-specific subagents (analyst, report-writer, quality-reviewer, osint-researcher, ioc-processor, detection-engineer). These wrap skills with model routing (Opus for deep reasoning, Sonnet for structured work) and tool permissions. The new cti-orchestrator lives as a skill now — the old agent was archived.
.claude/settings.json — baseline permissions.
tools/ — REGISTRY + per-API integration guides + zero-dep CLIs. Used by lookup-* skills.
archive/agents/ — the 7 tool-API agents and old cti-orchestrator — moved here after being superseded by lookup-* skills and the orchestrator skill.
data/ — sample IOCs, reports, PIRs for users to model after.
mitre-attack/ — bundled MITRE ATT&CK Enterprise dataset.
VERSIONS.md — per-skill semver + changelog.
validate-skills.sh — run before committing.

How to use the pack

Orchestrator-routed requests (the default): the user says "investigate 8.8.8.8" or "profile APT28" — route to /cti-orchestrator, which picks the right investigation/analysis skill and auto-applies rigor skills (TLP, source rating, confidence, likelihood) on the output.
Direct skill invocations: when the user types /ach, /iran-cyber-espionage, /pir-management etc., invoke the named skill directly, bypassing the orchestrator.
Composition: skills can invoke other skills. Investigation skills chain lookups; analytical skills can prioritize IOCs and dispatch further investigation. Composition is documented at the top of each skill body.
Claude-Code subagent specialists (optional): for deep analytical work, Claude Code can dispatch to analyst (Opus), report-writer (Opus), quality-reviewer (Opus), osint-researcher (Sonnet), ioc-processor (Sonnet), or detection-engineer (Sonnet). These agents load the same skills but offer model routing and tighter tool permissions. They are a Claude-Code-only optimization — skills alone work everywhere.

Read the full file on GitHub · 47 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.

10d ago First seen · 47 lines · 883 tokens per session scan A 3706e9261cc4

Subscribe to this mod's changes

cti-skills CLAUDE.md is an instructions file published in the GitHub repository Liberty91LTD/cti-skills (17 stars, last pushed 1mo ago), licensed MIT. It adds 883 tokens to every session, about $0.0044 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.

Research Security agent-skills agentic agentic-workflow agents agentskil agentskill

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

cti-skills: Instructions file for Claude Code