lenserfight: Skill for Claude Code

.claude/agents/lenserfight-profile-access-team/05-feed-ranking-relationship-engineer/SKILL.md

social-ranking-relationship-engineer is a skill for Claude Code from conectlens/lenserfight. It costs 37 tokens per session (552 once invoked), scanned A, original, MIT.

Guidance for designing ranking rules in social feeds, discovery tools, recommendations, and social graphs. It covers follows, mutual connections, interactions, freshness, privacy, and account status.

In plain words
What is it for?
Use it to design feed ranking, recommendation, and discovery systems with privacy checks and relationship-based signals.
Why use it?
It provides a structured way to decide who can see content and how eligible content should be ordered.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is conectlens/lenserfight's own configuration. It tells Claude Code how to work on lenserfight 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 lenserfight configures →

Reuse

Borrowing it

Nothing to install: this file belongs to conectlens/lenserfight. 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/conectlens/lenserfight/main/.claude/agents/lenserfight-profile-access-team/05-feed-ranking-relationship-engineer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/conectlens/lenserfight

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-ranking-relationship-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/conectlens/lenserfight/05-feed-ranking-relationship-engineer/github.svg)](https://agentmods.dev/skills/conectlens/lenserfight/05-feed-ranking-relationship-engineer)
Your own site
<a href="https://agentmods.dev/skills/conectlens/lenserfight/05-feed-ranking-relationship-engineer"><img src="https://agentmods.dev/badge/skills/conectlens/lenserfight/05-feed-ranking-relationship-engineer/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-ranking-relationship-engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/conectlens/lenserfight/05-feed-ranking-relationship-engineer"><img src="https://agentmods.dev/badge/skills/conectlens/lenserfight/05-feed-ranking-relationship-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 552 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 $0.00037 $0.00552
Opus 5 $0.00018 $0.00276
Sonnet 5 $0.00007 $0.00110
Haiku 4.5 $0.00004 $0.00055

Measured 12d ago against content hash 1972868fcba5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

social-ranking-relationship-engineer 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.

.claude/agents/lenserfight-profile-access-team/05-feed-ranking-relationship-engineer/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feed Ranking + Relationship Engineer

Mission

Upgrade LenserFight's social graph beyond a bare follower system.

Principle

Do not copy Instagram/X ranking blindly. Extract the primitives that matter:

  • explicit follow edges
  • reciprocal follow strength
  • interaction intensity
  • freshness
  • creator quality / trust
  • viewer eligibility under privacy policy

Ranking primitives

Graph signals

  • viewer follows author
  • author follows viewer
  • mutual follow
  • accepted follow age
  • recent profile visits
  • recent replies/comments/votes
  • repeated prompt execution interactions
  • shared communities / shared battles

Content signals

  • recency
  • engagement velocity
  • completion rate
  • save/reuse/remix rate
  • battle win rate / trust score
  • moderation risk penalties

Visibility gates

Before ranking anything, check eligibility:

  • author account must be active
  • if author is private, viewer must be owner or approved follower for full private content
  • restricted-shell eligible viewers may discover profile identity, not gated content bodies
  • deactivated / pending_deletion / deleted authors are excluded

Minimum algorithm v1

Feed candidate generation

  1. accepted follows
  2. mutual follows boost
  3. second-degree neighbors with shared communities
  4. popular public content fallback

Scoring formula example

score = recency_weight + relationship_weight + interaction_weight + quality_weight - risk_penalty

Where:

  • relationship_weight is highest for mutual follows and accepted follows
  • private content gets no ranking attempt for unauthorized viewers

Private account discovery rules

Recommended:

  • active private accounts may appear in people search and suggested follows
  • private content does not appear in public feed bodies
  • follower count and trust markers can still power follow conversion

Friendship interpretation

Implement friendship as tiers:

  • Tier 0: no edge
  • Tier 1: pending request
  • Tier 2: accepted one-way follow
  • Tier 3: mutual follow (friend)
  • Tier 4: trusted circle / close circle later

Read the full file on GitHub · 95 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 · 95 lines · 37 tokens per session scan A 1972868fcba5

Subscribe to this mod's changes

social-ranking-relationship-engineer is a skill published in the GitHub repository conectlens/lenserfight (18 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 552 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.

Related

Other skills, from other repositories

potpie-infra-architecture

Use for project infra and architecture context: environments, adapters, runtime configuration, deployments, service dependencies, datastores, API contracts, ownership, incidents, and dependency blast radius.

potpie-ai/potpie · 43 tokens

potpie-project-preferences

Use before writing, modifying, reviewing, refactoring, or testing code so repo/project preferences surface: error handling, file structure, frameworks, logging, dependency choices, testing, security, API style, and naming. Also use after code work when a reusable project preference should be recorded.

potpie-ai/potpie · 63 tokens

api-debugging

Systematic approach to debugging REST APIs, HTTP errors, authentication issues, and network problems. Use when the user has API errors, status code issues, timeout problems, or needs help troubleshooting HTTP requests.

ownpilot/OwnPilot · 44 tokens

authentication-patterns

OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.

travisjneuman/.claude · 28 tokens

email-systems

Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.

travisjneuman/.claude · 55 tokens

devex-sdk-design

Developer experience (DX) engineering, SDK design patterns, API ergonomics, CLI tooling design, documentation-driven development, and developer onboarding. Use when designing SDKs, improving API ergonomics, building developer tools, or creating developer documentation.

travisjneuman/.claude · 52 tokens