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.
npx skills add tahirraufkeeyu/software-development-agent-stack--sdas --skill social-mediagit clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasWrote 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/skills/tahirraufkeeyu/software-development-agent-stack--sdas/social-media)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/social-media"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/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/skills/tahirraufkeeyu/software-development-agent-stack--sdas/social-media"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/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 | $0.00059 | $0.02128 |
| Opus 5 | $0.00030 | $0.01064 |
| Sonnet 5 | $0.00012 | $0.00426 |
| Haiku 4.5 | $0.00006 | $0.00213 |
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 11d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Trigger this skill when the request includes any of:
- "Turn this blog post into a LinkedIn post and a Twitter thread"
- "Draft social copy for the launch"
- "Write a newsletter snippet for the new case study"
- "We need three posts promoting the whitepaper"
Do not use for paid ad copy (different constraints), customer support replies, or crisis comms.
Inputs
Required:
- Source content — URL, draft, or summary of the pillar piece being atomized.
- Primary audience — role and platform context (e.g., "platform leads, mostly on LinkedIn; engineers, mostly on X").
- Goal — one of: drive traffic, drive replies/engagement, capture subscribers, announce.
Optional:
- Author voice (if posting from a personal account vs brand account).
- Target CTA URL.
- Any must-include numbers, quotes, or visuals.
Outputs
Three deliverables (unless the brief limits to specific platforms):
- LinkedIn post — hook in first 2-3 lines, 150-300 words total, one CTA, posting-time note.
- X/Twitter thread — 7-10 tweets, each ≤280 chars, strong lead tweet, payoff tweet, reply CTA.
- Newsletter snippet — subject line (4-7 words), preview text, 80-120 word body, single CTA.
Plus a posting plan note: platform-by-platform recommended send time and any cross-posting rules.
Tool dependencies
- Read access to
references/platform-best-practices.md(required — load before drafting). - Optional: web-fetch to pull the source piece if only a URL is given.
Procedure
- Load the platform reference. Read
references/platform-best-practices.md. Note length targets, hook rules, and posting times. - Extract the "one thing." Every atomization comes from a single claim in the source. Identify it before writing a single post. If the source has more than one claim, pick the sharpest one and ignore the rest.
- Draft LinkedIn first. LinkedIn tolerates the most depth and is usually the primary channel for B2B. Hook in the first 3 lines before the "see more" cutoff (roughly 210 chars). End with a question or a concrete next step, not a hashtag stack.
- Draft the X/Twitter thread. Lead tweet must stand alone if nothing else gets read. Structure: hook → 5-8 substance tweets → payoff → optional "follow for more / reply with X" tweet. No "1/" numbering unless the client prefers it.
- Draft the newsletter snippet. Subject line 4-7 words, preview text extends the subject rather than repeating it. Body pays off the subject in sentence one.
- Write the posting plan. Note optimal send time per platform based on the reference. Flag any platform where the piece is a bad fit (e.g., skip X if the post is a long executive reflection).
- Run quality checks. Fix before returning.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 218 lines · 59 tokens per session scan A 82d5fa4ae298
social-media is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 2,128 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…