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 campaign-trackinggit 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/campaign-tracking)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/campaign-tracking"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/campaign-tracking/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/campaign-tracking"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/campaign-tracking.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 | $0.02575 |
| Opus 5.5 | $0.00028 | $0.01030 |
| Sonnet 5.5 | $0.00014 | $0.00515 |
| Haiku 4.5 | $0.00007 | $0.00258 |
Grade A, and why
campaign-tracking 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Campaign Tracking
A campaign is a coordinated set of malicious activities carried out by a threat actor against specific targets over a defined period.
Sourcing Before Tracking
A campaign record is built from claims, and each claim belongs to the source that originated it. Before any report feeds the record:
- Resolve provenance. Run
/source-provenanceon every ingested report or article. Record the primary, the chain and theprovenance_basis(platform-resolved, script-resolved or model-judged). - Dedupe by primary, not by URL. Five outlets covering one vendor report are one source and produce one timeline row, not five. List the outlets as "via". Count corroboration by independent primaries with separate access only.
- Grade per claim. Run
/quality-of-information-checkon the primary (it calls/claim-extraction). The intrusion, the vector, the attribution and the actor's own figures carry different grades. - Store the grade with the entity. Every timeline row, attack chain row, attribution statement and victim count carries the primary that supports it and the grade of the supporting claim.
Actor claims about victim count or data volume are graded "adversary, unverified" until an independent primary corroborates them. Record them as actor-claimed, not as findings. Grades follow the fixed rubric in /quality-of-information-check (references/grading-rubric.md). The grade is two words, access level then claim support, for example "direct, firm". It is not an Admiralty rating. Your own telemetry and SOC alerts are primaries in their own right, name them as such.
Campaign Template
## Campaign: [Campaign ID / Name]
### Overview
| Field | Value |
|-------|-------|
| **Campaign ID** | CAMP-YYYY-MM-XXX |
| **Name** | [Descriptive name if known] |
| **Status** | Active / Dormant / Concluded |
| **First observed** | YYYY-MM-DD |
| **Last observed** | YYYY-MM-DD |
| **Attribution** | [Actor — with confidence level] |
| **Motivation** | [Espionage / Financial / Destruction / Hacktivism] |
| **Independent primaries** | [Count of originating sources with separate access, and basis] |
| **Provenance basis** | [platform-resolved / script-resolved / model-judged (worst of the sources used)] |
| **Alias source** | [user / liberty91 / none] |
### Timeline
| Date | Event | Primary | Access level | Claim support |
|------|-------|---------|--------------|---------------|
| YYYY-MM-DD | Initial delivery emails sent | Internal telemetry | direct | established |
| YYYY-MM-DD | First successful compromise | [Vendor, report title] | limited | firm |
| YYYY-MM-DD | Lateral movement detected | SOC alert | direct | established |
| YYYY-MM-DD | Data exfiltration observed | Network forensics | direct | established |
### Attribution
[Assessment of who is behind this campaign, with confidence level. Reference threat actor profile if available.]
| Attribution statement | Primary | Stated confidence (verbatim) | Access level | Claim support | Independent primaries |
|-----------------------|---------|------------------------------|--------------|---------------|-----------------------|
| [Campaign is linked to X] | [Org, report title, date] | ["moderate confidence" / not stated] | [e.g., limited] | [e.g., tentative] | [Count, and basis] |
### Victimology
- **Sectors targeted**: [List]
- **Geographies**: [Countries/regions]
- **Number of known victims**: [Count with confidence, primary and grade. Mark actor-claimed figures as such]
- **Selection criteria**: [How were targets chosen? Opportunistic vs targeted?]
- **Common characteristics**: [What do victims have in common?]
### Attack Chain (Kill Chain / ATT&CK)
| Phase | Technique (ATT&CK) | Details | Primary | Access level | Claim support |
|-------|-------------------|---------|---------|--------------|---------------|
| Reconnaissance | T1598 Phishing for Information | Targeted LinkedIn messages to identify employees | [Org, date] | [e.g., limited] | [e.g., firm] |
| Initial Access | T1566.001 Spearphishing Attachment | Malicious Word doc with macro | [Org, date] | [e.g., direct] | [e.g., firm] |
| Execution | T1059.001 PowerShell | Macro downloads PowerShell stager | [Org, date] | [e.g., direct] | [e.g., firm] |
| Persistence | T1547.001 Registry Run Keys | Run key added for backdoor | [Org, date] | [e.g., direct] | [e.g., firm] |
| C2 | T1071.001 Application Layer Protocol | HTTPS to legitimate cloud service | [Org, date] | [e.g., limited] | [e.g., firm] |
| Exfiltration | T1567.002 Exfiltration to Cloud Storage | Data uploaded to attacker-controlled cloud | [Org, date] | [e.g., limited] | [e.g., firm] |
### Diamond Model
| Vertex | Details |
|--------|---------|
| **Adversary** | [Threat actor / group — reference profile] |
| **Capability** | [Malware, exploits, tools, techniques used] |
| **Infrastructure** | [C2 servers, staging, delivery infrastructure, domains] |
| **Victim** | [Targeted organisations, sectors, systems] |
**Meta-features:**
- **Direction**: [Adversary-to-Victim / Victim-to-Adversary / Bidirectional]
- **Methodology**: [Attack phases and progression]
- **Resources**: [Level of investment observed]
- **Social-Political**: [Geopolitical context driving the campaign]
- **Technology**: [Technology landscape enabling the campaign]
### IOC Clusters
#### Delivery Infrastructure
| Type | Value | First Seen | Status |
|------|-------|-----------|--------|
| Domain | phishing.example.com | 2026-01-15 | Active |
| IP | 203.0.113.42 | 2026-01-15 | Active |
#### C2 Infrastructure
| Type | Value | First Seen | Status |
|------|-------|-----------|--------|
| Domain | c2.badactor.net | 2026-01-20 | Active |
| IP | 198.51.100.10 | 2026-01-20 | Active |
#### Malware
| Hash (SHA-256) | Name | Type | First Seen |
|----------------|------|------|-----------|
| abc123... | loader.dll | Loader | 2026-01-15 |
### TTP Evolution During Campaign
[How have the attackers adapted? Changed tools? Modified techniques? Responded to detection?]
### Detection Guidance
[Reference to SIGMA/YARA/KQL rules created for this campaign. Link to data/detection-rules/.]
### Intelligence Gaps
[What we still don't know about this campaign]
### Sources
One row per primary. Outlets that carried the primary go in "Via".
| Date | Primary source | Via | Access | Access level | Key Finding |
|------|----------------|-----|--------|--------------|-------------|
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 · +25 lines aa802aa6b583
- 2mo ago First seen · 129 lines · 69 tokens per session scan A 8e9408e0d387
campaign-tracking 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 2,575 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 2026-08-30.
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.