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 guia-matthieu/clawfu-skills --skill terms-analyzergit clone --depth 1 https://github.com/guia-matthieu/clawfu-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/guia-matthieu/clawfu-skills/terms-analyzer)<a href="https://agentmods.dev/skills/guia-matthieu/clawfu-skills/terms-analyzer"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/terms-analyzer/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/guia-matthieu/clawfu-skills/terms-analyzer"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/terms-analyzer.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 | $0.00023 | $0.02639 |
| Opus 5 | $0.00012 | $0.01319 |
| Sonnet 5 | $0.00005 | $0.00528 |
| Haiku 4.5 | $0.00002 | $0.00264 |
Grade A, and why
terms-analyzer 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terms of Service Analyzer
Decode complex terms of service and privacy policies to identify concerning clauses, hidden permissions, and implications for users.
When to Use This Skill
- Evaluating new SaaS tools
- Assessing platform policies
- Comparing competitor terms
- Due diligence on acquisitions
- Consumer protection analysis
Methodology Foundation
Based on consumer protection frameworks and EFF/ToS;DR guidelines, analyzing:
- Data usage and ownership
- Liability limitations
- Arbitration clauses
- Change provisions
- Termination rights
What Claude Does vs What You Decide
| Claude Does | You Decide |
|---|---|
| Identifies key clauses | Risk tolerance |
| Flags concerning terms | Whether to accept |
| Compares to standards | Alternative tools |
| Summarizes rights | Business necessity |
| Rates overall fairness | Action to take |
Instructions
Step 1: Document Overview
Initial Assessment:
| Element | What to Capture |
|---|---|
| Service | What the product does |
| Provider | Company and jurisdiction |
| Last Updated | Currency of terms |
| Length | Complexity indicator |
| Readability | Plain language or legalese |
Step 2: Key Clause Categories
Critical Clauses to Analyze:
| Category | What to Find | Risk Signal |
|---|---|---|
| Data Ownership | Who owns your content | "Perpetual, irrevocable license" |
| Data Usage | How they use your data | "Any purpose", "train AI" |
| Data Sharing | Third-party access | "Partners", "affiliates" |
| Termination | Can they cancel you | "At sole discretion" |
| Changes | Can they modify terms | "Without notice" |
| Liability | What they're liable for | "In no event" disclaimers |
| Disputes | How conflicts resolve | Mandatory arbitration |
| Account Data | What happens on deletion | No deletion guarantee |
Step 3: Rights Assessment
User Rights Checklist:
| Right | Status | Clause |
|---|---|---|
| Data portability | Yes/No/Limited | § reference |
| Account deletion | Yes/No/Limited | § reference |
| Content ownership | Yes/No/Limited | § reference |
| Privacy controls | Yes/No/Limited | § reference |
| Opt-out options | Yes/No/Limited | § reference |
| Refund rights | Yes/No/Limited | § reference |
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 · 429 lines · 23 tokens per session scan A c106d1c11f2f
terms-analyzer is a skill published in the GitHub repository guia-matthieu/clawfu-skills (149 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 2,639 once invoked, about $0.0001 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
faktura-paminnelse-svensk
Hanterar fakturapåminnelser och inkasso enligt svensk lagstiftning. Identifierar förfallna fakturor i Bokio, beräknar korrekt påminnelseavgift (max 60 kr) och dröjsmålsränta (referensränta + 8 procentenheter), upprättar tröskel innan inkassoärende, och genererar utkast till påminnelsemejl, andra påminnelse…
agi-arbetsgivardeklaration
Förbereder och sammanställer arbetsgivardeklaration på individnivå (AGI) för månatlig inlämning till Skatteverket. Hämtar löneunderlag från Bokio, kontrollerar att arbetsgivaravgifter, skatteavdrag, förmåner och ersättningar är korrekt bokförda per anställd, och producerar både totalsumman för betalning och…
f-skatt-bolagskontroll
Verifierar nya leverantörer, kunder eller samarbetspartners genom att kontrollera F-skattestatus hos Skatteverket, registreringsdata hos Bolagsverket, och eventuella betalningsanmärkningar via tillgängliga källor. Skydd mot att betala till bolag som tappat F-skatt (vilket gör dig skyldig för deras skatter och…
periodisk-sammanstallning
Sammanställer kvartalsvis periodisk sammanställning för EU-försäljning (varor och tjänster), validerar köparnas VAT-nummer mot VIES, och förbereder underlag för inlämning till Skatteverket. Använd skillen när användaren nämner "periodisk sammanställning", "EU-försäljning", "VIES", "moms EU", "kvartalsrapport EU"…
semester-berakning
Beräknar semesterlön, semesterersättning och sparade semesterdagar enligt svenska Semesterlagen (1977:480). Hanterar både 12 %-regeln (vanlig för månadslön) och sammalöneprincipen. Använd skillen när användaren nämner "semester", "semesterlön", "semesterersättning", "sparade semesterdagar", "semesterlönegrundande"…
beweislast-und-zugang-309
Für Beweislast und Zugang 309: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Beweislast- und Substantiierungsmatrix.