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 source-provenancegit 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/source-provenance)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/source-provenance"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/source-provenance/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/source-provenance"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/source-provenance.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 | $0.00125 | $0.02973 |
| Opus 5.5 | $0.00050 | $0.01189 |
| Sonnet 5.5 | $0.00025 | $0.00595 |
| Haiku 4.5 | $0.00013 | $0.00297 |
Grade A, and why
source-provenance 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 3d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
source-provenance
Most CTI reporting that reaches an analyst is derivative. An outlet rewrites another outlet, which summarised a vendor blog, which reported on the vendor's telemetry. Five outlets covering one vendor report look like five sources. They are one.
This skill resolves a URL to its originating source and returns the chain as data. It does not grade anything. Grading is /quality-of-information-check.
Composition. Invokes /lookup-liberty91 when a key is configured. Invoked by /quality-of-information-check, /claim-extraction (for the fetcher), /threat-actor-profiling, /campaign-tracking, /intelligence-writing and /cti-orchestrator.
The rule that matters
The chain comes from data, never from recollection. You may know that a story "was originally a Mandiant report". That knowledge does not go in the output. If the platform or the script did not resolve a hop, the hop is unresolved, and you say so.
Inputs
- One or more URLs (up to 50 per run).
- Optional: a Liberty91 event ID, in which case platform data is returned instead of resolving.
Pasted text with no URL cannot be resolved by this skill. Say so and hand it to /quality-of-information-check, which treats it as Tier 3.
Tiers
| Tier | When | Who resolves the chain | provenance_basis |
|---|---|---|---|
| 1 | LIBERTY91_API_KEY is set and the platform returns provenance fields for the event |
Liberty91 ingestion pipeline, across the whole deduplicated event | platform-resolved |
| 2 | No key, or the platform has no provenance for this URL | scripts/resolve_provenance.py, for the single article given |
script-resolved |
| 3 | The page cannot be fetched, or the input is pasted text | The model, from the text alone, every field marked unverified | model-judged |
Every output carries provenance_basis at the top. Downstream skills carry it through unchanged.
Procedure
1. Try the platform
If LIBERTY91_API_KEY is set, ask /lookup-liberty91 for the event that contains this URL and read its provenance fields (primaries[], independent_primaries, chains[], most_recent_observation, superseded_by). If they are present, return them with provenance_basis: platform-resolved and stop.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · -46 tokens per session cdc921c42e67
- 1mo ago First seen · 191 lines · 171 tokens per session scan A 695873a21ff6
source-provenance is a skill published in the GitHub repository Liberty91LTD/cti-skills (36 stars, last pushed 4d ago), licensed MIT. It adds 125 tokens to every session and 2,973 once invoked, about $0.0005 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 2026-10-01.
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.