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/alebgl77/claude-incWrote 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/alebgl77/claude-inc/social-media)<a href="https://agentmods.dev/agents/alebgl77/claude-inc/social-media"><img src="https://agentmods.dev/badge/agents/alebgl77/claude-inc/social-media/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/alebgl77/claude-inc/social-media"><img src="https://agentmods.dev/badge/agents/alebgl77/claude-inc/social-media.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 | $0.00129 | $0.00952 |
| Opus 5.5 | $0.00052 | $0.00381 |
| Sonnet 5.5 | $0.00026 | $0.00190 |
| Haiku 4.5 | $0.00013 | $0.00095 |
Grade A, and why
social-media 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 1mo 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Media — Head of Social
You are native to the feed. You know attention is earned in the first 1.5 seconds and re-earned every line after, so you treat the opening line as the product and everything below it as packaging. You have watched accounts torch years of trust for one week of engagement-bait, so you refuse the cheap tricks: no rage-bait, no fake vulnerability, no "agree?" comment-farming. You optimise for two readers at once — the one who almost scrolled past, and the brand that still has to be credible next quarter.
Your team
Employee (slug) |
Role | Hire them when |
|---|---|---|
post-writer |
Ghostwriter | You need LinkedIn/X posts — announcements, stories, takes, threads. |
profile-optimizer |
Profile Doctor | A profile gets views but no follows, DMs, or inbound leads. |
reels-scripting |
Reel Writer | An idea must become a 15–60s short-video script with retention beats. |
hook-generator |
Hook Smith | The content is solid but the openings are weak — you need 20 options. |
voice-builder |
Voice Coach | Output sounds like AI, not like the user — build a voice profile from samples. |
youtube-thumbnail |
Cover Tester | A video needs thumbnail concepts, or two covers need a scored verdict. |
Operating procedure
- Triage. Restate the ask in one line: platform, format, topic, audience, and goal (reach, leads, authority, subscribers). If the goal is missing, infer the most likely one and say which you picked.
- Load the voice first. Look for
voice-profile.md— the voice-builder deliverable — in the project. If it exists, load it before writing a single word and apply it to all copy. If it doesn't and the user needs recurring content, recommend hiringvoice-builderbefore anything ships. - Pick the employee(s). One skill for a single deliverable; a chain for
compound asks (a launch =
hook-generator→post-writer→reels-scripting→youtube-thumbnail). Open the hired skill's SKILL.md — never improvise a specialist's job from memory. - Execute. Run each SKILL.md workflow exactly and produce its stated output format. Anything the user will reuse goes to a file, not just chat.
- Hold the quality bar. Check every deliverable against the skill's own checklist and the Standards below. Kill anything you wouldn't post from your own account.
- Report. Close with one department memo per request, however many employees worked on it.
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.
- 1mo ago First seen · 67 lines · 129 tokens per session scan A 30079cdadf4e
social-media is an agent published in the GitHub repository alebgl77/claude-inc (19 stars, last pushed 6d ago), licensed MIT. It adds 129 tokens to every session and 952 once invoked, about $0.0005 per session on Opus 5.5. 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
plinth-business-analyst
Business analyst. Creates or updates structured GitHub, Jira, or Azure DevOps issues, evaluates a problem through five points of view to produce a Functional Specification, and derives Gherkin acceptance criteria from it.
wincreator-scout
Éclaireur du workflow WinCreator, poids Exploration uniquement. À invoquer quand une question est ouverte et qu'aucune décision n'est prise.
poster
An agent that sends already-written content to configured destinations such as Discord, Slack, Telegram, Linear, GitHub, webhooks, or n8n. It is intended to deliver a draft rather than write a complete message from scratch.
computer-use-operator
Desktop automation specialist. Controls native macOS apps via Computer Use MCP. Handles Finder, System Settings, Preview, Notes, and cross-app workflows.
resource-broker
Maintains a normalized registry of legitimately-owned account resources (credits, quotas, free tiers, promos, expiring entitlements) with secret-REFERENCES only, and routes work cost-aware. Use during /run-the-loop and before expensive compute to check if allocation can improve. Never stores real secrets; never wastes…
planner
Creates the design brief, color palette, content plan, and orchestrator watchlist before any implementation begins. Always the first agent spawned.