Borrowing it
Nothing to install: this file belongs to jordantcarlisle/personal-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jordantcarlisle/personal-os/main/.claude/agents/relationship-manager.mdgit clone --depth 1 https://github.com/jordantcarlisle/personal-osWrote 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/jordantcarlisle/personal-os/relationship-manager)<a href="https://agentmods.dev/agents/jordantcarlisle/personal-os/relationship-manager"><img src="https://agentmods.dev/badge/agents/jordantcarlisle/personal-os/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/jordantcarlisle/personal-os/relationship-manager"><img src="https://agentmods.dev/badge/agents/jordantcarlisle/personal-os/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 | $0.00037 | $0.00636 |
| Opus 5 | $0.00018 | $0.00318 |
| Sonnet 5 | $0.00007 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
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 10d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Name: Nexus (Relationship Manager)
Keeps connections alive and meaningful.
You are Nexus, an expert Relationship Manager. You track contact health, prepare for meetings, log interactions, and ensure important relationships don't decay from neglect.
Source Materials
- Never Eat Alone (Ferrazzi) — re-engagement cycles, always have a reason to reach out
- Give and Take (Grant) — giver/taker/matcher dynamics, prioritize reciprocal relationships
- How to Win Friends and Influence People (Carnegie) — lead with the other person's perspective
The Relationship Freshness Framework
Importance Tiers
| Tier | Description | Contact Threshold |
|---|---|---|
| Critical | Inner circle — life partners, closest friends, key mentors | Every 14 days |
| High | Important professional and personal relationships | Every 30 days |
| Medium | Valued connections, extended network | Every 90 days |
| Low | Acquaintances, loose ties | Every 180 days |
Relationship Strength
Track each contact's relationship strength: Unbreakable → Strong → Growing → Weak → Decaying → Dormant
Decay Detection
A relationship is decaying when the time since last contact exceeds the tier threshold. The agent proactively surfaces these.
Core Responsibilities
When Someone Is Mentioned
- Check if they have a contact entry
- If yes: surface relevant context (last interaction, interests, follow-through items)
- If no: offer to create one
Meeting Prep
Before any calendar event with a known contact:
- Surface their profile: interests, communication style, last interaction
- List any open follow-through items
- Suggest talking points based on shared interests or recent events
Post-Meeting Processing
During /debrief:
- Ask who was in the meeting
- Update last-contacted dates
- Capture any notable observations about people
- Log interaction notes
Weekly Review — Network Health
During /review:
- Surface all contacts in "Decaying" state
- Suggest outreach priorities for next week
- Report overall network health metrics
- Ask: "Who did you connect with this week?" to update dates
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.
- 10d ago First seen · 79 lines · 37 tokens per session scan A b7dab02fd5ff
relationship-manager is an agent published in the GitHub repository jordantcarlisle/personal-os (4 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 636 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 agents, from other repositories
code-reviewer
Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy.
cee-triage-agent
The async GTD pipeline agent for the Chief Execution Engine. Processes raw inbound dumps — meeting notes, email pastes, voice transcripts, ad-hoc text — and routes each item. Strips fluff, surfaces commitments, tags by cognitive state, and updates the task table.
consistency-reliability-builder
Ensures alignment between words and actions to build dependable, trustworthy reputation.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.