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 confidence-levelsgit 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/confidence-levels)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/confidence-levels"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/confidence-levels/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/confidence-levels"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/confidence-levels.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 | $0.00087 | $0.01290 |
| Opus 5.5 | $0.00035 | $0.00516 |
| Sonnet 5.5 | $0.00017 | $0.00258 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
confidence-levels 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confidence Levels
Every analytical judgment produced by this platform MUST carry a confidence level. Confidence reflects the quality and quantity of evidence supporting the judgment, NOT the probability that the event will occur (that's likelihood — see likelihood-language skill).
Primary Scale: Named Bands
Three levels, following ICD 203. Each band is tied to the claim support of the evidence underneath, as graded by /quality-of-information-check. On export, STIX confidence comes from claim support: established 90, firm 70, tentative 50, disputed 30, and unverified omits the property. These values are the pack's own mapping, chosen to sit inside the bands below, so a confidence level, a STIX confidence value and the grade of the evidence underneath all say the same thing.
| Band | Score Range | Meaning | Evidence it requires |
|---|---|---|---|
| High | 80-100 | Based on high-quality information from multiple independent sources. Well corroborated. High confidence does not mean the judgment is a fact. | Every load-bearing claim at claim support established, with access level direct or limited |
| Moderate | 60-79 | Based on credibly sourced and plausible information that is not corroborated enough to warrant higher confidence. Alternative interpretations exist. | Weakest load-bearing claim at claim support firm, or established with access level indirect |
| Low | 40-59 | Based on limited or fragmentary information, or on a judgment the source itself hedged. Several plausible alternative interpretations. | Weakest load-bearing claim at claim support tentative |
| No confidence level | none | The evidence cannot carry a judgment. Do not attach a label. State what is known, state the gap, and say what collection would close it. | Any load-bearing claim at claim support disputed or unverified |
Scores below 40 are not used. A judgment that would score there is not one the evidence supports, and it gets no confidence level.
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 · +13 lines · +24 tokens per session bb33d2ca2e7b
- 2mo ago First seen · 90 lines · 63 tokens per session scan A ec1eb92f5560
confidence-levels is a skill published in the GitHub repository Liberty91LTD/cti-skills (36 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 1,290 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.