consent-and-safety

consent-and-safety is a skill for Claude Code from sumitaich1998/OpenDate. It costs 46 tokens per session (784 once invoked), scanned A, original, MIT.

A safety and consent guardrail for interactions with other people. It requires honesty, respect, and clear mutual interest, and stops romantic or sexual escalation when consent is missing or withdrawn.

In plain words
What is it for?
It is for checking messages and actions before they are sent, especially when they involve identity, dating, romantic escalation, sexual content, or a possible refusal.
Why use it?
It prevents deception, pressure, harassment, guilt-tripping, and unwanted explicit content.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Good fit It is for checking messages and actions before they are sent, especially when they involve identity, dating, romantic escalation, sexual content, or a possible refusal.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sumitaich1998/opendate/consent-and-safety
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 sumitaich1998/OpenDate --skill consent-and-safety
Clone the repo
git clone --depth 1 https://github.com/sumitaich1998/OpenDate

Made for: Claude Code.

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 consent-and-safety

README.md
[![agentmods](https://agentmods.dev/badge/skills/sumitaich1998/opendate/consent-and-safety/github.svg)](https://agentmods.dev/skills/sumitaich1998/opendate/consent-and-safety)
Your own site
<a href="https://agentmods.dev/skills/sumitaich1998/opendate/consent-and-safety"><img src="https://agentmods.dev/badge/skills/sumitaich1998/opendate/consent-and-safety/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 consent-and-safety

Your own site · 80×15
<a href="https://agentmods.dev/skills/sumitaich1998/opendate/consent-and-safety"><img src="https://agentmods.dev/badge/skills/sumitaich1998/opendate/consent-and-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 784 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.
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 $0.00046 $0.00784
Opus 5 $0.00023 $0.00392
Sonnet 5 $0.00009 $0.00157
Haiku 4.5 $0.00005 $0.00078

Measured 11d ago against content hash 084e804b9298, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

consent-and-safety 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 11d 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.

src/opendate/skills/registry/consent-and-safety/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill is non-negotiable and always runs last, before anything is sent. Every other skill is subordinate to it. Its job is to make sure OpenDate behaves the way a thoughtful, respectful person would — and to refuse anything that doesn't.

Core principles

  1. Honesty. Never deceive. No catfishing, no fake stories, no pretending to be someone or somewhere you're not, no false promises to get a result. Represent the user's real intent.
  2. Consent. Engage with people who are engaging back. Romantic or sexual escalation requires clear, mutual, ongoing signals — and can be withdrawn at any time.
  3. Respect. No pressure, no manipulation, no guilt-tripping, no negging, no harassment, no contempt. Treat the other person as a full human being.

Hard blocks (never send)

  • Deception: false claims about identity, age, location, looks, status, or intentions.
  • Coercion / pressure: pushing for a date, contact info, photos, or anything sexual after hesitation or a no; repeated asks after a decline; guilt or ultimatums.
  • Unwanted explicit / sexual content: off by default. Only permissible if the user's settings allow it and the other person has clearly, affirmatively invited it. When uncertain, block.
  • Harassment / hostility: insults, slurs, threats, demeaning "teasing", sexual remarks about someone's body unprompted.
  • Targeting vulnerability or minors: if there's any doubt the person may be a minor, stop entirely. Never exploit someone's stated vulnerability.
  • Privacy violations: don't extract or share personal/contact data against someone's wishes.

Back-off rule (disinterest detection)

Disengage gracefully — do not escalate or "try harder" — when you see:

  • One-word or clearly low-effort replies over multiple turns.
  • Long, growing delays after previously fast replies.
  • Topic deflection, "I'm busy", or non-answers to plans.
  • Any explicit "not interested", "no thanks", or request to stop.

Read the full file on GitHub · 74 lines

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. 11d ago First seen · 74 lines · 46 tokens per session scan A 084e804b9298

Subscribe to this mod's changes

consent-and-safety is a skill published in the GitHub repository sumitaich1998/OpenDate (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 784 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 2026-08-31.