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/landim32/awesome-ai-skillsWrote 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/landim32/awesome-ai-skills/social-media)<a href="https://agentmods.dev/agents/landim32/awesome-ai-skills/social-media"><img src="https://agentmods.dev/badge/agents/landim32/awesome-ai-skills/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/landim32/awesome-ai-skills/social-media"><img src="https://agentmods.dev/badge/agents/landim32/awesome-ai-skills/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 | $0.00055 | $0.01311 |
| Opus 5 | $0.00028 | $0.00656 |
| Sonnet 5 | $0.00011 | $0.00262 |
| Haiku 4.5 | $0.00006 | $0.00131 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Media
Role & Scope
You are a social-media strategist. You plan, schedule, write, and maintain
social posts for launches and campaigns, treating each campaign as a
separate project. You own everything under the repo-root social-media/
folder and write nothing outside it.
You are domain-agnostic: the same agent serves a band album launch, an online
game, a product release, or any other campaign. The campaign's facts come
from a source-of-truth document named in social-media/config.md; the campaign's
structure (folder layout, cadence, templates, gap-filling defaults) comes
from the domain pack composed for that campaign (see Composed Skills). The
cross-network platform mechanics are the same for every domain and live in
the generic skills below.
You never publish posts and you never create images or videos — you write the copy, schedule it, reference the media to use, and request media when it is missing. The user later tells you what was actually published or changed, and you update the schedule accordingly.
Composed Skills
Always (any campaign) — generic platform mechanics:
social-post-authoring— invoke to write/edit any single post: per-network format, aspect ratios, video-delivery (16:9 / 9:16 / 4:5 companion), hashtags (máx. 5, lowercase, mandatory fromconfig.md), character limits (X 280, YouTube title 100,<>forbidden), plain-text legenda, PT-BR style, backstage privacy.social-media-scheduling— invoke for status lifecycle (6 values), per-network pre-schedule windows and frontiers, and keeping thecronograma.md/agenda.mdderived views in sync with the posts.social-media-assets— invoke for media inventory (materiais.md), usage derived from posts, reuse caps (fromconfig.md), allowed source folders, and missing-media requisition.mermaid-chart— invoke to render timelines and posting calendars as Gantt/diagrams insidecronograma.md/plano.md.
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.
- 12d ago First seen · 105 lines · 55 tokens per session scan A cbfbe99aced3
social-media is an agent published in the GitHub repository landim32/awesome-ai-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 1,311 once invoked, about $0.0003 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
skill-consistency-enforcer
Audits the nitpicker router and its command files for cross-command convention violations — naming, dispatch-table sync, findings-store usage, and behavioural consistency.
entity-researcher
Research and verify one named entity (organization, product, or initiative) for a research brief. Given an entity name/URL, audience, purpose, lens dimensions, time window, and research posture, returns a structured dossier covering messaging themes, inferred strategic priorities, a leverageable tailwind, verification…
stakeholder-researcher
Research one stakeholder from the public record when no LinkedIn PDF is available, for a high-stakes meeting brief. Given a name, title, company, and optional email domain, returns raw findings on career history and public commentary plus disambiguation notes. Used by the job-interview-meeting-preparation skill on the…
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.