Selfish Reputation — Development agent for Claude Code
Measure whether the body of work is increasing qualified trust, recognition, referrals, repeat engagement, and durable authority.
How to install Selfish Reputation
Installs to ~/.claude/agents/wbrown-dev-selfish.ai-selfish-reputation.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/wbrown-dev/selfish.ai/HEAD/.claude/agents/selfish-reputation.md -o ~/.claude/agents/wbrown-dev-selfish.ai-selfish-reputation.md Restart Claude Code, or start a new session, for it to be picked up.
What Selfish Reputation does
name: selfish-reputation description: Measure whether the body of work is increasing qualified trust, recognition, referrals, repeat engagement, and durable authority. model: inherit
You are the selfish.ai Reputation specialist.
Before doing substantive work, read `agents/10-reputation.md` and follow it as the canonical specification. Read only the workspace files necessary for the delegated task.
Return a concise specialist result to the parent agent, including evidence gaps, uncerta
Alternatives in Development
- Executioner — Optional Sanhedrin fallback verifier 632 ★
- Performance Monitor — Monitor agent execution, track token usage, measure response quality, and optimize workflows 93 ★
- Measure Response Time For Varying Prefix Match Lengths — import time from statistics import mean def time_compare(guess, iterations=1000): times = [] for _ in range(it 78 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Selfish Integrity Contradiction
Protect reputation by detecting unsupported claims, contradictions, plagiarism risk, privacy breaches, inflate
Footprint Hunter
Collects external digital-footprint OSINT for a domain ingested as a huella_digital engagement — DNS surface (
Webinar Prospect Finder
Identifies qualified contacts from [User]'s network who would be interested in attending specific webinars. Us
Selfish Asset Builder
Detect when repeated useful work is mature enough to become a durable intellectual asset.
Findings DB Synthesizer
Closes the DB flywheel — turns an engagement's judge-confirmed findings into durable DB entries, hunt cards, a
Slash Command Auditor Dtd
DTD-aware slash command auditor. Use when auditing, reviewing or evaluating a -dtd command file: checks the DO
Related Skills
God Of The Void
A Claude Code skill with a BODY: persistent memory across sessions, ~0-token semantic search, an errarium that
Author Authority Builder
Turns authors from byline strings into entities Google's quality systems trust and AI engines cite. Builds the
Token Consumer
Measure and shrink the token cost of Claude Code skills, tier by tier: the always-on system-prompt tax, the pe
