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 key-assumptions-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/key-assumptions-check)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/key-assumptions-check"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/key-assumptions-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/key-assumptions-check"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/key-assumptions-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 | $0.00049 | $0.01155 |
| Opus 5.5 | $0.00020 | $0.00462 |
| Sonnet 5.5 | $0.00010 | $0.00231 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade A, and why
key-assumptions-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 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Key Assumptions Check
Every analytical judgment rests on assumptions — often unstated. This technique surfaces them and evaluates whether the analysis holds if assumptions are wrong.
Procedure
Step 1: State the Analytical Line
Write the current assessment or conclusion in one clear sentence.
Step 2: List All Assumptions
Brainstorm every assumption underlying the assessment. Include:
- Assumptions about threat actor intent or capability
- Assumptions about data completeness or accuracy
- Assumptions about the relevance of historical patterns
- Assumptions about the target environment
- Assumptions about timing or sequencing
Step 3: Walk the Claim Table (when one exists)
If the assessment was built on graded evidence items from /quality-of-information-check, go through the claim table row by row. Assumptions are usually hiding in judgements that the analysis treats as observations. If there is no claim table, skip this step and leave the Claim column as "n/a".
For each claim, compare its claim_type with how the analytical line uses it:
| In the claim table | How the analysis uses it | Assumption to record |
|---|---|---|
assessment |
Stated as fact, or as a premise for a further judgement | That the source's judgement about intent, capability or future behaviour is correct |
attribution |
Actor named without the source's hedge | That the attribution holds. Quote stated_confidence verbatim |
actor_claim |
Scale, victim or data figures repeated as fact | That the actor is telling the truth |
Any type, flagged caveats_dropped_in_chain |
Outlet's stronger wording used | That the claim is as strong as the outlet made it, not as the primary wrote it |
Any type, flagged single_source or with corroboration unchecked |
Relied on without qualification | That the one primary is right |
Any type, flagged stale or superseded |
Used as current | That nothing has changed since publication |
Rules:
- Every
assessmentandattributionclaim withload_bearing: truegets a row in the matrix, even when the assumption looks safe. - Carry the
claim_idinto the matrix. One claim can produce more than one assumption, and an assumption can rest on several claims. - Do not regrade claims here. The grade informs the Confidence column: claim support tentative or worse on a claim used as fact is Low or Medium confidence, never High.
- Assumptions from Step 2 that trace to no claim are kept, with "none" in the Claim column. These have no evidence behind them at all, which is worth stating.
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 · +20 lines d32d2c94dd2f
- 2mo ago First seen · 77 lines · 49 tokens per session scan A 442ae4158486
key-assumptions-check is a skill published in the GitHub repository Liberty91LTD/cti-skills (36 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 1,155 once invoked, about $0.0002 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.