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 90le/worker-rights-cn --skill agreement-reviewgit clone --depth 1 https://github.com/90le/worker-rights-cnWrote 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/90le/worker-rights-cn/agreement-review)<a href="https://agentmods.dev/skills/90le/worker-rights-cn/agreement-review"><img src="https://agentmods.dev/badge/skills/90le/worker-rights-cn/agreement-review/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/90le/worker-rights-cn/agreement-review"><img src="https://agentmods.dev/badge/skills/90le/worker-rights-cn/agreement-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 15 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00057 | $0.00684 |
| Opus 5 | $0.00028 | $0.00342 |
| Sonnet 5 | $0.00011 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
agreement-review 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 12d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agreement Review
Overview
Review labor documents from the worker side. Identify risky clauses, missing payment terms, rights waivers, non-compete exposure, illegal penalties, evidence effects, and negotiation edits.
Workflow
- Identify the document type: separation agreement, resignation form, termination notice, non-compete agreement, confidentiality agreement, service-period agreement, settlement receipt, or mixed document.
- Accept only normalized input supplied by the orchestrator and return only this skill's documented output. Do not ask the user to select or chain internal skills. Report missing intake or termination fields to the orchestrator instead of invoking another skill.
- Read
references/clause-risk-matrix.jsonand match clauses by document type, clause type, and plain-language triggers. - For each clause, output risk level, worker-side impact, source anchors, evidence impact, and proposed revision or negotiation point.
- Separate
must_fix_before_signing,negotiate,verify_amounts, andlawyer_checkitems. - If the user already signed, switch from signing advice to validity, revocation, enforcement, payment, and evidence-preservation analysis.
Risk Levels
critical: likely waives major rights, creates high penalty exposure, changes termination characterization, or blocks later claims.high: materially weakens bargaining position or creates uncertain but serious liability.medium: should be clarified or narrowed before signing.low: administrative or wording issue, still worth tracking.lawyer_check: local practice, large amount, executive/non-compete/stock option/foreign worker, or disputed validity.
Output Format
Return:
document_type: detected type and confidence.signing_status: not signed, signed, partly signed, or unknown.top_risks: 3 to 7 highest-risk clauses.clause_review: clause-by-clause findings with risk level, source anchors, reason, evidence impact, and recommended edit.missing_terms: payment date, amount, tax, social insurance month, certificate wording, handover scope, non-compete compensation, dispute release carve-outs, or proof of employer proposal.do_not_sign_until: blocking items that should be resolved before signing.negotiation_edits: worker-side replacement wording or negotiation points.evidence_to_preserve: documents and communications to preserve before negotiation.next_skill: usuallycompensation-calculator,evidence-builder,layoff-defense, orarbitration-drafter.
What ships with it
4 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.
- 12d ago First seen · 50 lines · 57 tokens per session scan A 9aa1cc7db4d0
agreement-review is a skill published in the GitHub repository 90le/worker-rights-cn (94 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 684 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
compliance
Compliance expert for SOC 2, GDPR, HIPAA, PCI-DSS, and security frameworks.
dependency-audit
Audits direct and transitive dependencies for license compliance, maintenance health, CVEs, abandoned packages, and bloat. Triggers on: "audit dependencies", "license check", "dependency health", "abandoned packages", "unused dependencies", "license compliance", "supply chain", "dependency risk".
commercial-legal-pl
Skill do analizy i tworzenia umów według polskiego prawa, ze szczególnym uwzględnieniem umów B2B, IP i IT (body leasing, NDA, wdrożenia, SaaS, przeniesienie praw autorskich, ugody). Powstał w Kancelarii Radców Prawnych Żurawska Piotrowski i Wspólnicy (ktzr.pl). Używaj zawsze gdy użytkownik prosi o przeanalizowanie…
anvil-adsense-audit
A pre-submission audit for websites applying to Google AdSense, Google's advertising programme. It checks policy, content, crawling, privacy, and site-readiness items and records each as Pass, Fail, Unknown, or Not applicable.
counterparty-guard
A Russian business-counterparty check based on an identification number called an INN. It gathers public records about a company or sole proprietor and presents deal-risk signals.
contract-review
A contract-checking tool for Russian law, aimed at small businesses without an in-house lawyer. It reviews supply, service, contractor, NDA, and SaaS agreements and explains risky or missing terms in plain language.