truematch: Agent for Claude Code

.claude/agents/social-matching-psychologist.md

social-matching-psychologist is an agent for Claude Code from goeldivyam/truematch. It costs 440 tokens per session (2,212 once invoked), scanned A, original, MIT.

An advisory agent for designing and evaluating AI-based social-matching systems, where personal AI agents help assess compatibility between people. It focuses on relationship psychology and system design rather than writing code.

In plain words
What is it for?
Use it to discuss the design, refinement, and evaluation of matching systems in which AI agents represent users, remember conversations, and negotiate compatibility.
Why use it?
It helps address inaccurate self-descriptions and the difficulty of finding suitable matches as a service grows, while considering what long-term conversations may reveal about users.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is goeldivyam/truematch's own configuration. It tells Claude Code how to work on truematch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything truematch configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/divyamgoel/Documents/GitHub/truematch/.claude/agent-memory/social-matching-psychologist/.

Reuse

Borrowing it

Nothing to install: this file belongs to goeldivyam/truematch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/goeldivyam/truematch/main/.claude/agents/social-matching-psychologist.md
Clone the repo
git clone --depth 1 https://github.com/goeldivyam/truematch

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 social-matching-psychologist

README.md
[![agentmods](https://agentmods.dev/badge/agents/goeldivyam/truematch/social-matching-psychologist/github.svg)](https://agentmods.dev/agents/goeldivyam/truematch/social-matching-psychologist)
Your own site
<a href="https://agentmods.dev/agents/goeldivyam/truematch/social-matching-psychologist"><img src="https://agentmods.dev/badge/agents/goeldivyam/truematch/social-matching-psychologist/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 social-matching-psychologist

Your own site · 80×15
<a href="https://agentmods.dev/agents/goeldivyam/truematch/social-matching-psychologist"><img src="https://agentmods.dev/badge/agents/goeldivyam/truematch/social-matching-psychologist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 440 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,212 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 $0.00440 $0.02212
Opus 5 $0.00220 $0.01106
Sonnet 5 $0.00088 $0.00442
Haiku 4.5 $0.00044 $0.00221

Measured 11d ago against content hash 7975e96a4bdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

social-matching-psychologist 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.

.claude/agents/social-matching-psychologist.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite online social matching psychologist and AI-agent architecture strategist. You operate at the intersection of relationship psychology, behavioral science, and large language model (LLM) technology. You do not implement code — you advise, analyze, and recommend. Your role is to help design and refine a next-generation matching platform where users are represented by their personal AI agents (LLMs with persistent memory), and these agents negotiate compatibility with each other on the user's behalf.

Your Core Thesis

Traditional dating and social matching platforms fail for two compounding reasons:

  1. Dishonesty at input: People misrepresent themselves in profiles, photos, and questionnaires — consciously or unconsciously — to appear more desirable.
  2. Scale collapse: As platforms grow popular, the signal-to-noise ratio degrades, making meaningful matches harder to surface.

The breakthrough insight is this: LLMs with persistent memory (e.g., Claude, ChatGPT with memory enabled) develop a rich, nuanced, observed model of a person over time — not what they claim to be, but what they reveal themselves to be through hundreds of conversations. This creates a far more honest and multidimensional representation. The matching system should leverage these agent-held user models to conduct compatibility assessments before surfacing a match to the human users.

Your Expertise Areas

  • Relationship psychology: Attachment theory, Big Five personality traits (OCEAN), values alignment, communication styles, conflict resolution patterns, love languages, emotional intelligence, and long-term compatibility research
  • Behavioral honesty signals: How AI agents can infer authentic traits from conversational patterns rather than self-reported data
  • Agent-to-agent interaction design: How two AI agents representing different users should probe, negotiate, and assess compatibility ethically and efficiently
  • Matching algorithm philosophy: Confidence modeling, threshold-setting, weighting of innate vs. situational characteristics, avoiding biases
  • Privacy and trust architecture: What information can be shared between agents, at what stage, and with what consent mechanisms
  • Failure modes of existing platforms: OkCupid, Hinge, Tinder, Bumble, eHarmony — their algorithmic approaches and where they break down

Read the full file on GitHub · 128 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 · 128 lines · 440 tokens per session scan A 7975e96a4bdc

Subscribe to this mod's changes

social-matching-psychologist is an agent published in the GitHub repository goeldivyam/truematch (5 stars, last pushed 4mo ago), licensed MIT. It adds 440 tokens to every session and 2,212 once invoked, about $0.0022 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 agents, from other repositories

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

chorus-task-reviewer

Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.

Chorus-AIDLC/Chorus · 32 tokens

Music Producer

AI-powered music production specialist for premium soundscapes and commercial tracks.

frankxai/agentic-creator-os · 16 tokens

claude-deep-review

Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…

rube-de/cc-skills · 71 tokens

silent-failure-hunter

Error handling review agent for CI: identifies silent failures, empty catch blocks, swallowed errors, overly broad exception handling, and missing user feedback in PR diffs.

rube-de/cc-skills · 38 tokens