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 writing-assessmentsgit 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/writing-assessments)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/writing-assessments"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/writing-assessments/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/writing-assessments"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/writing-assessments.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 | $0.00039 | $0.01352 |
| Opus 5 | $0.00019 | $0.00676 |
| Sonnet 5 | $0.00008 | $0.00270 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
writing-assessments 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 9d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Assessments
Three types of assessments, each with distinct purpose and structure. Do not conflate them.
Threat Assessment
Purpose: Evaluate a threat actor or threat scenario against a specific target.
Formula: Threat = Intent + Capability + Opportunity
Structure
1. Intent — What does the adversary want?
- Stated objectives (if known)
- Historical targeting patterns
- Geopolitical/economic motivations
- Assessment of intent with confidence level
2. Capability — What can the adversary do?
- Technical sophistication
- Resources (financial, human, infrastructure)
- Known tooling and TTPs
- Track record of successful operations
- Assessment of capability with confidence level
3. Opportunity — What attack surface exists?
- Target's exposure (internet-facing services, supply chain)
- Known vulnerabilities relevant to the adversary's TTPs
- Access pathways (initial access vectors)
- Defensive posture gaps
- Assessment of opportunity with confidence level
4. Combined Threat Level
| Level | Criteria |
|---|---|
| Critical | Demonstrated intent, advanced capability, and clear opportunity. Attack is imminent or ongoing. |
| High | Strong intent indicators, significant capability, and exploitable opportunity. Attack is highly likely in assessment period. |
| Moderate | Some intent indicators, moderate capability, and some opportunity. Attack is a realistic possibility. |
| Low | Limited intent indicators, basic capability, or minimal opportunity. Attack is unlikely. |
| Negligible | No credible intent, minimal capability, or no meaningful opportunity. |
Example assessment statement
"We assess the threat level from APT41 to European pharmaceutical companies as HIGH (confidence: high). APT41 has demonstrated intent through active reconnaissance (observed since November 2025), possesses advanced capability including zero-day exploitation, and the sector presents significant opportunity due to widespread legacy VPN infrastructure."
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.
- 9d ago First seen · 144 lines · 39 tokens per session scan A 025a71e500c9
writing-assessments is a skill published in the GitHub repository Liberty91LTD/cti-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,352 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
ai-ad-copy-compliance-review
A risk-review assistant for advertising and sales copy. It examines provided material for possible concerns and suggests actions.
ai-agent-browser
A business-diagnosis assistant for marketing, operations, product, and sales questions. It breaks down a goal and produces a summary, findings, action suggestions, and reusable deliverables.
ai-article
A Chinese-language assistant for turning source material into article and content-operation deliverables. It is aimed at creators, marketers, technical teams, and media publishers.
ai-brand-voice-review
A business-diagnosis assistant for marketing, operations, services, and sales questions.
ai-browser-use
A business-diagnosis assistant for marketing, operations, product, and sales questions about how to approach a task.
ai-content-material-audit
A Chinese-language copy-review assistant for creators, marketers, operators, and media teams.