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 quality-of-information-checkgit 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/quality-of-information-check)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/quality-of-information-check"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/quality-of-information-check/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/quality-of-information-check"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/quality-of-information-check.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 | $0.00124 | $0.03772 |
| Opus 5.5 | $0.00050 | $0.01509 |
| Sonnet 5.5 | $0.00025 | $0.00754 |
| Haiku 4.5 | $0.00012 | $0.00377 |
Grade A, and why
quality-of-information-check 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
quality-of-information-check
Grade the evidence before you reason about it.
A structured analytic technique run by prompt alone produces output that has the shape of the technique and none of its discipline. An ACH matrix built on whatever the model felt like trusting is worse than no matrix, because it looks rigorous. This skill is the step that comes first: it establishes what the evidence is, where it came from, and how much weight each claim can bear.
Composition. Invokes /source-provenance, then /claim-extraction, then applies the rubric, then hands to /quality-control. Optionally invokes /lookup-* skills for corroboration and /lookup-liberty91 for platform data. Its output is the preferred input of /ach, /threat-assessment and /writing-assessments, and is consumed by /key-assumptions-check, /intelligence-writing, /stix-bundle and /ioc-export.
Three principles
- Grade provenance chains, not outlets. The grade belongs to this claim arriving by this chain. The same outlet carries a vendor's own telemetry finding and an attacker's boast in the same week.
- Grade claims, not events. One report contains observations, attributions and assessments of very different standing. One grade for all of them is meaningless.
- Data does the research, the model applies the rubric. The chain is resolved by the platform or by a script. Corroboration is counted from data. What is left for the model is labelled as model judgement.
Inputs
- One or more URLs, pasted text, or Liberty91 event IDs.
- First-party observations: hits from
/lookup-sentinelor the user's own EDR. These enter the claim table directly, graded direct and established (rubric rule R12), withprovenance_basis: first-party. Steps 1 to 4 do not apply to them. - Optional, and worth asking for: the question or hypothesis the evidence is meant to serve. With it, the skill can mark which claims are load-bearing.
What the model may and may not do
| Allowed (model judgement, labelled as such) | Not allowed |
|---|---|
| Judge transmission fidelity | Assert a primary the script or platform did not resolve |
| Judge claim type | Assert corroboration not established by data or lookups |
| Apply the rubric | Infer access type from an organisation's reputation |
| Write the rationale | Invent or paraphrase vendor confidence language |
| Analyse gaps | Assign a grade above a cap |
| Run the deception screen | Apply a track record modifier outside Tier 1 |
What ships with it
7 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 · -87 tokens per session 4c1cbc6f9ac5
- 1mo ago First seen · 257 lines · 211 tokens per session scan A f9605d054110
quality-of-information-check is a skill published in the GitHub repository Liberty91LTD/cti-skills (36 stars, last pushed 4d ago), licensed MIT. It adds 124 tokens to every session and 3,772 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.