evidence-builder

evidence-builder is a skill for Claude Code, Codex from 90le/worker-rights-cn. It costs 76 tokens per session (695 once invoked), scanned A, original, Apache-2.0.

A checklist builder for collecting and preserving evidence in China labor disputes. It labels each item by whether it is available, missing, controlled by the employer, held by another party, or possible to create now.

In plain words
What is it for?
Use it after the case facts and type of termination have been organized, especially for layoffs, dismissal, forced resignation, unpaid wages, salary cuts, contract expiry, or arbitration preparation.
Why use it?
It helps show what supports a claim, prioritize urgent evidence work, and request employer-controlled documents without suggesting unlawful access or fabricated records.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the worker-rights-cn plugin — 11 skills, 5 hooks, 1 MCP server shipped together

Good fit Use it after the case facts and type of termination have been organized, especially for layoffs, dismissal, forced resignation, unpaid wages, salary cuts, contract expiry, or arbitration preparation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/90le/worker-rights-cn/evidence-builder
Install

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.

Any agent
npx skills add 90le/worker-rights-cn --skill evidence-builder
Clone the repo
git clone --depth 1 https://github.com/90le/worker-rights-cn

Made for: Claude Code, Codex.

Or install worker-rights-cn, the plugin that ships this one along with the rest of its 11 skills, 5 hooks, 1 MCP server.

Wrote 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.

agentmods badge for evidence-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/90le/worker-rights-cn/evidence-builder/github.svg)](https://agentmods.dev/skills/90le/worker-rights-cn/evidence-builder)
Your own site
<a href="https://agentmods.dev/skills/90le/worker-rights-cn/evidence-builder"><img src="https://agentmods.dev/badge/skills/90le/worker-rights-cn/evidence-builder/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.

agentmods 80×15 button for evidence-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/90le/worker-rights-cn/evidence-builder"><img src="https://agentmods.dev/badge/skills/90le/worker-rights-cn/evidence-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 695 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 14
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.00695
Opus 5 $0.00038 $0.00347
Sonnet 5 $0.00015 $0.00139
Haiku 4.5 $0.00008 $0.00069

Measured 10d ago against content hash b38e667de2b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

evidence-builder 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run_evidence_cases.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/worker-rights-cn/skills/evidence-builder/SKILL.md · 50 lines

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.

Evidence Builder

Overview

Turn labor dispute facts into an evidence plan. Use source-card anchors and termination maps from layoff-defense when available, and label evidence strength without inventing facts.

Workflow

  1. 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 facts to the orchestrator.
  2. Consume the orchestrator-provided termination classification; if it is absent, return the missing input instead of invoking another skill.
  3. Read references/evidence-matrix.json and select evidence bundles by termination_map, claim type, and source anchors.
  4. Classify each evidence item as available, missing, employer_controlled, third_party, or create_now.
  5. Prioritize collection as P0_immediate, P1_core, P2_supporting, or P3_local_verify.
  6. Output lawful preservation steps and request language; do not suggest illegal data access or fabricated records.

Evidence Status Rules

  • available: the worker already has the item or can lawfully access it.
  • missing: the item is needed but not yet located.
  • employer_controlled: the employer likely controls the item; ask for it in writing or request production during arbitration.
  • third_party: bank, tax, social insurance, housing fund, hospital, delivery platform, or government system may provide it.
  • create_now: the worker should create a truthful timeline, written objection, preservation memo, or request based on existing facts.

Output Format

Return:

  • case_evidence_summary: short summary of what the evidence must prove.
  • termination_maps_used: mapped categories such as economic_layoff or constructive_dismissal.
  • source_anchors: source-card anchors supporting the evidence plan.
  • evidence_checklist: grouped items with status, priority, purpose, lawful source, and collection note.
  • evidence_gaps: missing or employer-controlled items that affect claim strength.
  • preservation_steps_24h: immediate lawful steps for the next 24 hours.
  • request_to_employer: concise wording for requesting documents or written reasons.
  • risk_flags: signing risk, limitation risk, protected status, confidential data, group layoff, high-value claim, or lawyer review.
  • next_skill: usually compensation-calculator, agreement-review, arbitration-drafter, or layoff-defense.

Read the full file on GitHub · 50 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 50 lines · 76 tokens per session scan A b38e667de2b5

Subscribe to this mod's changes

evidence-builder is a skill published in the GitHub repository 90le/worker-rights-cn (93 stars, last pushed 29d ago), licensed Apache-2.0. It adds 76 tokens to every session and 695 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

compliance

Compliance expert for SOC 2, GDPR, HIPAA, PCI-DSS, and security frameworks.

RightNow-AI/openfang · 22 tokens

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".

Mathews-Tom/armory · 66 tokens

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…

apiotrowski-afk/commercial-legal-pl · 231 tokens

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.

PNGTRID/AnvilWiki · 136 tokens

brazil-vat

> Use esta skill sempre que perguntarem sobre tributos indiretos brasileiros, IVA, tributos sobre o consumo, PIS, Cofins, ICMS, ISS, IPI, CBS, IBS, Imposto Seletivo, NF-e (Nota Fiscal Eletronica), NFS-e, Simples Nacional, registro de CNPJ, reforma tributaria (EC 132/2023, LC 214/2025, LC 227/2026) ou qualquer questao…

openaccountants/openaccountants · 213 tokens

bulgaria-vat-return

Use this skill whenever asked to prepare, review, or classify transactions for a Bulgarian VAT return (Spravka-deklaratsiya po DDS) for any client. Trigger on phrases like "prepare VAT return", "do the DDS", "fill in DDS return", "create the return", "Bulgarian VAT", or any request involving Bulgaria VAT filing. Also…

openaccountants/openaccountants · 158 tokens