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 sopsgit 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/sops)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/sops"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/sops/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/sops"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/sops.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 | $0.00044 | $0.01052 |
| Opus 5 | $0.00022 | $0.00526 |
| Sonnet 5 | $0.00009 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
sops 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 7d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standard Operating Procedures
SOP-001: Daily Intelligence Triage
Frequency: Daily Owner: Orchestrator
- Review overnight intelligence feeds and alerts
- Check active PIRs — any new information relevant to Critical/High PIRs?
- Triage new indicators:
- Discard noise (known benign, low confidence, duplicate)
- Fast-track critical indicators (active exploitation, direct relevance)
- Queue remaining for standard processing
- Dispatch OSINT researcher for any trending threats relevant to PIRs
- Update relevant knowledge cells with new significant intelligence
- Produce daily intelligence brief if significant developments occurred
SOP-002: IOC Processing
Trigger: New IOC list received (from internal detection, external sharing, or OSINT collection) Owner: IOC Processor
- Parse and classify all indicators
- Validate format (reject malformed)
- Deduplicate against existing active IOC collections
- Enrich via enrichment workflow (dispatch tool agents)
- Apply source assessment to enrichment results
- Synthesise verdict (malicious/suspicious/benign/unknown)
- Store in
data/iocs/active/ - If actionable: request detection rule creation from detection engineer
- If significant: flag to orchestrator for flash report consideration
- Export in relevant formats if sharing is appropriate
SOP-003: Flash Report Creation
Trigger: Time-critical intelligence requiring immediate stakeholder action Owner: Orchestrator → Analyst → Report Writer → Quality Reviewer
- Orchestrator identifies time-critical situation
- Dispatch analyst for rapid assessment (30-minute time box)
- Dispatch report writer with flash report template
- Quality reviewer performs expedited review (critical checks only):
- TLP correct?
- Key finding supported?
- IOCs validated?
- Actions clear?
- Disseminate via appropriate TLP channel
- Link to relevant PIRs
- Schedule follow-up analysis if warranted
Expedited review: For flash reports, quality review focuses on CRITICAL issues only. MAJOR and MINOR issues are noted but don't block publication. Speed matters.
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.
- 7d ago First seen · 131 lines · 44 tokens per session scan A db86e2e67afc
sops is a skill published in the GitHub repository Liberty91LTD/cti-skills (17 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,052 once invoked, about $0.0002 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-just-scrape
A business diagnosis assistant for marketing, operations, product, and sales questions. It uses supplied material to produce summaries, findings, action suggestions, and reusable deliverables.
ai-lark-approval
A business diagnosis assistant for operations, product, technical, and sales work. It uses supplied material to produce summaries, findings, action suggestions, and reusable deliverables.
ai-lark-calendar
A business-diagnosis assistant for turning an unclear business question into a structured plan.
ai-lark-task
A business-diagnosis assistant for breaking down unclear tasks and deciding what should happen next.
ai-polish
A business diagnosis assistant that examines supplied material and helps decide what to do next.
ai-resume-screening-consistency-review
A business-diagnosis assistant for reviewing whether resume screening is consistent.