relationship-intent-matching

relationship-intent-matching is a skill for Claude Code from sumitaich1998/OpenDate. It costs 42 tokens per session (561 once invoked), scanned A, original, MIT.

An always-on conversation modifier that adjusts tone, pace, and topics to match whether the user wants casual interaction, dating, or a long-term relationship. It also watches for signs that the other person's intentions differ.

In plain words
What is it for?
Use it to shape messages, interpret relationship-intent signals, balance light and serious topics, and decide when to suggest meeting or discuss deeper values.
Why use it?
It helps conversations move at a pace that fits the user's goal and brings possible mismatches to attention early. It is a communication behavior layer, not a standalone technical tool.

Skill for Claude Code

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

Good fit Use it to shape messages, interpret relationship-intent signals, balance light and serious topics, and decide when to suggest meeting or discuss deeper values.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sumitaich1998/opendate/relationship-intent-matching
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 relationship-intent-matching
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 relationship-intent-matching

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sumitaich1998/opendate/relationship-intent-matching"><img src="https://agentmods.dev/badge/skills/sumitaich1998/opendate/relationship-intent-matching.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 561 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 $0.00042 $0.00561
Opus 5 $0.00021 $0.00280
Sonnet 5 $0.00008 $0.00112
Haiku 4.5 $0.00004 $0.00056

Measured 12d ago against content hash 2b2881ce55dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

relationship-intent-matching 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.

src/opendate/skills/registry/relationship-intent-matching/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Relationship-intent matching

This is an always-on modifier: it shapes how every other skill expresses itself so the conversation moves at the right pace toward the right thing. It also listens for the other person's intent and surfaces mismatches early — because aligned intent is the kindest, most effective filter there is.

Tune by the user's looking_for

Casual

  • Tone: light, fun, low-stakes, in the moment.
  • Pace: can move to meeting up quickly; keep it breezy.
  • Topics: shared fun, chemistry, plans. Don't over-index on future-building.

Dating (getting to know someone, open to where it goes)

  • Tone: warm, curious, genuinely interested but unhurried.
  • Pace: a few good exchanges, then suggest a low-key date.
  • Topics: values and lifestyle alongside fun; balance depth and play.

Long-term

  • Tone: sincere and warm, still playful — depth signals seriousness.
  • Pace: invest in real rapport before pushing to meet; quality over speed.
  • Topics: values, life direction, how they treat people — woven in naturally, never as an interrogation.

Read their intent

Watch for signals and mirror or surface honestly:

  • Casual signals: fast escalation, "no expectations", late-night energy, reluctance to plan ahead.
  • Serious signals: asking about values/future, slower deliberate pace, references to past relationships and lessons.
  • Mismatch: if their intent clearly differs from the user's, don't paper over it. A short, honest check-in ("I'm actually looking for something real — where's your head at?") saves everyone time and is always allowed.

Rules

  • Never misrepresent the user's intent to get a result. Honesty about what the user wants is non-negotiable (see consent-and-safety).
  • Pace follows intent. Don't rush a long-term seeker or stall a casual one.
  • Surface big mismatches early rather than hoping they resolve.

Output (as a modifier)

Don't produce a standalone message. Instead, constrain the primary skill's draft: adjust warmth, depth, and pacing to the intent, and flag any intent mismatch the user should know about.

Read the full file on GitHub · 58 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. 12d ago First seen · 58 lines · 42 tokens per session scan A 2b2881ce55dd

Subscribe to this mod's changes

relationship-intent-matching is a skill published in the GitHub repository sumitaich1998/OpenDate (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 561 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.