rapport-building

rapport-building is a skill for Claude Code from sumitaich1998/OpenDate. It costs 27 tokens per session (551 once invoked), scanned A, original, MIT.

A conversation guide for building trust through thoughtful questions, active listening, and personal follow-up.

In plain words
What is it for?
It is for starting conversations, following someone’s interests, reflecting their feelings, and gradually making a connection deeper.
Why use it?
It helps replace shallow small talk with conversations where people feel heard and find genuine common ground.

Skill for Claude Code

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

Good fit It is for starting conversations, following someone’s interests, reflecting their feelings, and gradually making a connection deeper.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sumitaich1998/opendate/rapport-building
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 rapport-building
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 rapport-building

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sumitaich1998/opendate/rapport-building"><img src="https://agentmods.dev/badge/skills/sumitaich1998/opendate/rapport-building.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 551 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 $0.00027 $0.00551
Opus 5 $0.00014 $0.00275
Sonnet 5 $0.00005 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured 12d ago against content hash 1f5fbb7a0278, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

rapport-building 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/rapport-building/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rapport building

Chemistry needs jokes; connection needs rapport. This is where you turn surface chat into the feeling of "oh, I actually like talking to this person."

The loop

Ask → listen → reflect → relate → (gently) deepen.

  1. Ask an open, specific question about something they care about.
  2. Listen for what they emphasize or get animated about — that's the thread.
  3. Reflect it back so they feel heard ("so the move was leaving the safe job — that's a big swing").
  4. Relate with something true about yourself. Reciprocity builds trust.
  5. Deepen by one layer: from whatwhywhat it meant.

Great questions

  • Trade "what do you do?" for "what's something you're weirdly good at?"
  • Trade "do you travel?" for "what's a place that changed how you think?"
  • Ask about meaning and motivation, not résumés: "what got you into that?", "what part do you actually love?", "what's lighting you up lately?"
  • Follow energy, not your checklist. If they light up about their dog, stay there a while.

Active listening on text

  • Name the feeling, not just the fact: "that sounds like it was equal parts terrifying and freeing."
  • Callback to something they said earlier to show you retained it.
  • Match self-disclosure depth. Go one layer deeper than they did, never ten.
  • Validate before pivoting. Acknowledge what they shared before adding yours.

Calibration

  • Keep it warm and curious, not clinical. One good question per message.
  • Balance depth with lightness so it never feels like therapy. A little humor keeps it human.
  • Watch the give/take ratio — aim for roughly 50/50 sharing.

Do / Don't

  • Do reflect feelings and motivations, not just facts.
  • Do share something real about yourself in return.
  • Don't rapid-fire questions; it feels like a form.
  • Don't one-up their stories — relate, then hand it back.

Output

A warm message that makes them feel heard, shares something true in return, and opens one genuine door to go a layer deeper.

Read the full file on GitHub · 60 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 · 60 lines · 27 tokens per session scan A 1f5fbb7a0278

Subscribe to this mod's changes

rapport-building is a skill published in the GitHub repository sumitaich1998/OpenDate (2 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 551 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

build-bot-funnel

A workflow that turns a written conversation plan into a validated chatbot flow for Telegram, MAX, or Instagram.

skiddgoddamn/zaytsv-mcp · 137 tokens

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…

aden-hive/hive · 133 tokens

make-a-deck

Slide presentation in HTML.

asgeirtj/system_prompts_leaks · 9 tokens

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.

aden-hive/hive · 40 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

subscription-manager

Create and manage scheduled subscription tasks. Use when the user wants to set up recurring reminders, periodic reports, scheduled checks, or any automated tasks that run on a schedule. Supports cron expressions, fixed intervals, and one-time executions.

wecode-ai/Wegent · 49 tokens