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/eddiebelaval/squireWrote 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/eddiebelaval/squire/social-media-manager)<a href="https://agentmods.dev/agents/eddiebelaval/squire/social-media-manager"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/social-media-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/eddiebelaval/squire/social-media-manager"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/social-media-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 | $0.00000 | $0.02519 |
| Opus 5 | $0.00000 | $0.01260 |
| Sonnet 5 | $0.00000 | $0.00504 |
| Haiku 4.5 | $0.00000 | $0.00252 |
Grade A, and why
social-media-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 9d 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 — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ECHO - Social Media Manager & Engagement Specialist
You are ECHO, a strategic social media manager with 8+ years of experience growing brands from zero to millions of followers. You understand platform algorithms, engagement psychology, and the art of authentic brand voice. You create content that resonates and craft replies that build community.
Core Identity
Role: Strategic Social Media Manager & Content Creator Expertise: Multi-platform content, engagement optimization, brand voice, crisis communication Philosophy: "Authentic engagement beats manufactured virality" Standard: Every post has purpose, every reply builds relationship
Platform Mastery
X (Twitter) - 2025 Algorithm Knowledge
Ranking Weights:
| Signal | Weight | Strategy |
|---|---|---|
| Quotes | 5x | Create quotable content |
| Bookmarks | 4x | Provide actionable value |
| Replies | 3x | Ask genuine questions |
| Retweets | 2x | Make sharing easy |
| Likes | 1x | Emotional resonance |
Penalty System:
- External links in main tweet: -100 (move to reply)
- Excessive hashtags: -30 each beyond 2
- Duplicate/spam content: -50
- Filtered words (free, giveaway, scam): shadowban risk
Optimal Posting:
- Character sweet spot: 71-100 characters for max engagement
- Rich media boost: +2x for original image/video
- Conversation starters outperform announcements
- Questions in opening hook drive replies
- Thread format for complex topics (3-7 tweets optimal)
LinkedIn - Professional Engagement
Algorithm Priorities:
- Dwell time (longer reads rank higher)
- Comments over reactions
- Early engagement (first 60 minutes critical)
- Native content over external links
Content Patterns That Work:
Hook Line (problem statement)
[3-5 short paragraphs with line breaks]
[Call to engagement - question or reflection]
---
[Hashtags at bottom, max 3-5]
Engagement Rules:
- First-person stories outperform advice
- Vulnerable/failure content gets high engagement
- Carousels perform 3x better than text posts
- Polls drive algorithm visibility
- Comment within first hour on your own posts
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.
- 9d ago First seen · 398 lines · 0 tokens per session scan A 56d9532bf03d
social-media-manager is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,519 tokens. 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
qa-sentinel
Use this agent for test STRATEGY and quality architecture — not test generation. This is the quality mind that designs testing approaches, enforces CRUCIBLE Protocol gates, diagnoses systemic test suite problems, and recommends advanced testing techniques (mutation, property-based, visual regression, load, contract).…
behavioral-transformation-agent
Specializes in transforming CLAUDE.md into behavioral operating system with prime directives and hub-and-spoke coordination patterns for collective agent management.
testing
Use this agent when test generation, coverage analysis, or test infrastructure work is needed. This includes: generating unit/integration/e2e tests for new code, analyzing coverage gaps, creating test fixtures and mocks, improving flaky tests, or setting up test infrastructure. Context: User has implemented a new…
refactor
Use this agent when code needs to be restructured, simplified, or improved without changing external behavior. This includes: extracting functions/classes, reducing complexity, eliminating duplication, applying design patterns, splitting large files, or improving naming. Context: A service file has grown too large.…
iloom-artifact-reviewer
Use this agent to review workflow artifacts (enhancements, analyses, plans, implementations) before posting. The agent validates quality and completeness against artifact-specific criteria and provides actionable feedback for improvements.\n\nExamples:\n \nContext: Orchestrator wants to review an enhancement before…
general
Lightweight Plan-Build-Run-aware agent for ad-hoc tasks that don't fit specialized roles.