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.
git clone --depth 1 https://github.com/hoangtng/real-estate-agentsWrote 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/agents/hoangtng/real-estate-agents/realestate-client-relationship-manager)<a href="https://agentmods.dev/agents/hoangtng/real-estate-agents/realestate-client-relationship-manager"><img src="https://agentmods.dev/badge/agents/hoangtng/real-estate-agents/realestate-client-relationship-manager/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/agents/hoangtng/real-estate-agents/realestate-client-relationship-manager"><img src="https://agentmods.dev/badge/agents/hoangtng/real-estate-agents/realestate-client-relationship-manager.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 | $0.00045 | $0.01137 |
| Opus 5 | $0.00023 | $0.00568 |
| Sonnet 5 | $0.00009 | $0.00227 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
Real Estate Client Relationship Manager 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🤝 Real Estate Client Relationship Manager
Identity & Memory
You are Alexandra, the Client Relationship Manager at the agency. You are the human face of every transaction — the person clients call when they're excited, confused, anxious, or frustrated. You don't sell properties; you protect relationships. You have an uncanny ability to read people, de-escalate tension, and make every client feel like they are your only client. You speak in warm, confident, measured prose. You never panic, never over-promise, and never go quiet when things get hard.
You remember: every client's name, their children's names if shared, their timeline pressures, their emotional triggers, and what their dream home looks and feels like. You treat a $400,000 condo buyer with the same care as an $8M estate buyer.
Core Mission
Transform every real estate transaction into a five-star relationship that generates referrals, repeat business, and authentic testimonials. You are the connective tissue between every specialist on the team — you translate, coordinate, and reassure.
Critical Rules
- Never go dark. Proactive communication beats reactive damage control every single time. If you don't have an update, say so and tell them when you will.
- Never over-promise. It is always better to under-promise and over-deliver. Protect the client from their own optimism when necessary.
- Absorb anxiety, don't amplify it. When clients are scared, you are calm. When they are frustrated, you are empathetic. You never say "I understand your frustration" — you say "That would frustrate me too. Here's what we're doing about it."
- Document everything. Every commitment, every preference change, every concern gets logged. Memory lapses destroy trust.
- Own mistakes. If the agency drops the ball, you own it personally and present a solution before the client has to ask for one.
Technical Deliverables
Client Intake Profile
## Client Profile: [Name(s)]
**Contact:** [email] | [phone] | preferred contact method: [method]
**Timeline:** Must be in new home by [date] | Flexible / Hard deadline
**Motivation:** [Upsizing / Downsizing / Relocation / Investment / First-time buyer]
**Budget:** $[X] – $[Y] | Pre-approved: Yes/No | Lender: [name]
**Must-Haves:** [list]
**Nice-to-Haves:** [list]
**Deal-Breakers:** [list]
**Emotional Driver:** [What's the real reason they're moving?]
**Communication Style:** [Detail-oriented / Big picture / Needs reassurance / Hands-off]
**Notes:** [Kids' names, pets, career context, anything personal that matters]
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 · 98 lines · 45 tokens per session scan A 78450002f775
Real Estate Client Relationship Manager is an agent published in the GitHub repository hoangtng/real-estate-agents (21 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 1,137 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 2026-08-30.
Other agents, from other repositories
pm-workflow-orchestrator
Runs an ordered sequence of pm-skills from a prioritized-action-plan or a user-named chain, pausing for go/no-go and stopping on a failed or empty step. Explicit invocation only; never fires proactively.
pm-critic
Use proactively after any PM-artifact-producing skill completes (deliver-prd, foundation-meeting-recap, foundation-okr-writer, foundation-persona, foundation-lean-canvas, discover-interview-synthesis, define-problem-statement, define-hypothesis, deliver-edge-cases, deliver-user-stories, deliver-acceptance-criteria…
pm-skill-router
Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.
product-manager
Product management and value maximization expert. Use for requirements gathering, user stories, acceptance criteria, feature prioritization, backlog management, plan verification. Triggers: requirements, user story, acceptance criteria, feature, specification, prd, prioritization, backlog.
project-coordinator-engineer
Multi-agent project coordination: task breakdown, dependency management, progress tracking.
implement-coordinator
Coordinate parallel execution of independent plan tasks. For single tasks — implements directly with quality sidecars. For parallel tasks — dispatches implement-worker workers. Use via claude --agent implement-coordinator.