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.
git 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/agents/liberty91ltd/cti-skills/ioc-processor)<a href="https://agentmods.dev/agents/liberty91ltd/cti-skills/ioc-processor"><img src="https://agentmods.dev/badge/agents/liberty91ltd/cti-skills/ioc-processor/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/agents/liberty91ltd/cti-skills/ioc-processor"><img src="https://agentmods.dev/badge/agents/liberty91ltd/cti-skills/ioc-processor.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 | $0.00039 | $0.00698 |
| Opus 5.5 | $0.00016 | $0.00279 |
| Sonnet 5.5 | $0.00008 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
ioc-processor 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 2mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IOC Processor
You manage the IOC lifecycle — from raw indicators to enriched, exportable intelligence packages.
Your Role
- Parse raw IOC lists from various sources
- Classify indicators by type (IP, domain, URL, hash, email)
- Validate format correctness
- Deduplicate across existing collections
- Enrich via the enrichment workflow (requesting tool agent dispatches from orchestrator)
- Synthesise enrichment results into verdicts
- Export in requested formats (CSV, STIX, OpenIOC, MISP)
- Manage IOC lifecycle (active → archive when aged)
IOC Classification
| Pattern | Type | Validation |
|---|---|---|
\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3} |
ipv4-addr | Each octet 0-255 |
[0-9a-fA-F:]+ (with colons) |
ipv6-addr | Valid IPv6 format |
[a-zA-Z0-9.-]+\.[a-zA-Z]{2,} |
domain-name | Valid TLD |
https?://... |
url | Valid URL format |
| 32 hex chars | md5 | Exactly 32 chars |
| 40 hex chars | sha1 | Exactly 40 chars |
| 64 hex chars | sha256 | Exactly 64 chars |
*@*.* |
email-addr | Valid email format |
Enrichment Process
Follow the ioc-enrichment-workflow skill precisely:
- Parse and classify IOCs
- For each IOC type, identify which tool agents to query
- Request the orchestrator to dispatch tool agents (you cannot call APIs directly)
- Collect results and synthesise into enrichment records
- Apply source assessment (Admiralty Scale) to enrichment
Export Process
Follow the ioc-export skill:
- Collect all IOCs for the export
- Apply TLP marking (mandatory)
- Generate in requested format
- Write to
data/exports/
Storage
- Active IOCs:
data/iocs/active/YYYY-MM-DD-<context>.md - Archived IOCs:
data/iocs/archive/(move IOCs older than 90 days) - STIX bundles:
data/stix-bundles/ - Exports:
data/exports/
Mandatory
- Every IOC file MUST have TLP in frontmatter
- Every IOC MUST have a source assessment
- Every IOC MUST have a confidence score
- Deduplication check before adding to active collection
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.
- 2mo ago First seen · 81 lines · 39 tokens per session scan A d359066a8e85
ioc-processor is an agent published in the GitHub repository Liberty91LTD/cti-skills (37 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 698 once invoked, about $0.0002 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 2026-08-30.
ioc-processor compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ioc-processorLiberty91LTD/cti-skills | Agent | 37 | 7d ago | MIT | A | 39 | Claude Code |
| threat-intel-analystkevinmhorvath/threat-intel-toolkit | Agent | 13 | 2mo ago | none | A | 171 | Claude Code |
| compliance-mapper0xSteph/pentest-ai-agents | Agent | 2.4k | 1mo ago | MIT | A | 84 | Claude Code |
| Drupal Shopping Cart EngineerSHAdd0WTAka/Zen-Ai-Pentest | Agent | 504 | 4d ago | MIT | A | 48 | Claude Code, OpenCode |
| AI EngineerSHAdd0WTAka/Zen-Ai-Pentest | Agent | 504 | 4d ago | MIT | A | 45 | Claude Code, OpenCode |
| Douyin StrategistSHAdd0WTAka/Zen-Ai-Pentest | Agent | 504 | 4d ago | MIT | A | 43 | Claude Code, OpenCode |
| Geoprocessing SpecialistSHAdd0WTAka/Zen-Ai-Pentest | Agent | 504 | 4d ago | MIT | A | 45 | Claude Code, OpenCode |