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 sumitaich1998/OpenDate --skill relationship-intent-matchinggit clone --depth 1 https://github.com/sumitaich1998/OpenDateWrote 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/sumitaich1998/opendate/relationship-intent-matching)<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.
<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>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 | $0.00042 | $0.00561 |
| Opus 5 | $0.00021 | $0.00280 |
| Sonnet 5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
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.
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.
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 · 58 lines · 42 tokens per session scan A 2b2881ce55dd
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.
Other skills, from other repositories
workflow-extract
Baut aus einem Chatverlauf oder aus bestehenden Automatisierungs-Prompts (z. B. eines anderen Agenten-Systems) eine selbstlaufende, user-neutrale Workflow-Automatisierung: einen wiederkehrenden Prompt bzw. Automations-Skill für Cron/Schedule/Loop. Alias: automations-extractor. Nutze diesen Skill bei „mach daraus eine…
c
OpenPaw coordinator — routes requests to skills, manages memory, knows what's installed. Use /c for any task.
build-bot-funnel
A workflow that turns a written conversation plan into a validated chatbot flow for Telegram, MAX, or Instagram.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
make-a-deck
Slide presentation in HTML.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.