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 inklate/social-skills --skill social-contextgit clone --depth 1 https://github.com/inklate/social-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/skills/inklate/social-skills/social-context)<a href="https://agentmods.dev/skills/inklate/social-skills/social-context"><img src="https://agentmods.dev/badge/skills/inklate/social-skills/social-context/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/inklate/social-skills/social-context"><img src="https://agentmods.dev/badge/skills/inklate/social-skills/social-context.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 | $0.00147 | $0.01509 |
| Opus 5 | $0.00073 | $0.00754 |
| Sonnet 5 | $0.00029 | $0.00302 |
| Haiku 4.5 | $0.00015 | $0.00151 |
Grade A, and why
social-context 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview the user, then write a social-context.md at the project root that every other
social skill can read.
Context
Check for an existing social-context.md at the project root, then .agents/social-context.md.
If one exists, this run is an update: read it fully before asking anything, skip questions
it already answers well, and confirm only what looks stale. If neither exists, this is a fresh
interview — say so and start immediately.
Workflow
- Set expectations in one line: "Up to 10 quick questions, multiple choice where I can — say 'skip' to any." Then ask the first question in the same message. Do not wait for permission to begin.
- Who are you and what do you sell? One open question, captured as the
## Positioningsection. If the answer is vague ("a startup"), push once for the one-sentence version a stranger would understand: product, category, and who pays. - Audience. Ask who they most need to reach, offering choices:
- (a) buyers/customers
- (b) peers in their field
- (c) potential hires
- (d) investors
- (e) a niche community Follow with one sharpening question: "Describe one real person in that audience — job title, what they scroll past, what stops them." Capture that person, not a demographic.
- Platforms. Ask which platforms they're active on — LinkedIn, X, Instagram, Threads, TikTok, YouTube etc. — and, for each chosen one, why (where the audience is vs. where they're comfortable). If they pick more than three, warn once that two done consistently beats five done sporadically, and ask them to rank. Record a primary and a secondary.
- Pillars. Ask for 3–5 recurring themes they can post about for a year without running dry. If they stall, propose pillars derived from their answers so far — build-in-public progress, opinions on their industry, teaching their craft, customer stories, behind-the-scenes — and let them pick and edit. Each pillar gets a name and a one-line description.
- Tone sliders. Present three sliders as multiple choice (1–5), all in one message:
- funny ↔ serious
- spicy ↔ safe
- personal ↔ brand Then ask for one account they admire and one they'd hate to sound like — those two anchors are worth more than the sliders.
- Cadence reality check. Ask how many posts per week they will actually ship, not aspire to. If they say daily, ask what they shipped last month. Record the honest number per platform.
- Goals. Ask what a win looks like in 90 days, offering: reach/awareness, inbound leads, hiring pipeline, community, or personal brand. Force a single primary goal; secondary goals are allowed but labeled.
- Red lines. Ask what they will never post: competitors they won't name, topics that are off-limits (politics, salaries, client names), formats they hate (dance trends, engagement bait), words they'd never use. Get at least three concrete items.
- Write the file. Assemble
social-context.mdusing the sections in the Quality bar table below, in that order, with those exact headings — other skills locate sections by these headings, so never rename or reorder them. - Fresh run: write the whole file. Update run: regenerate section by section, diff
each against the existing file, and where the existing text contains detail you didn't
collect this session (manual edits, rules added by the
social-voiceskill), show the old and new versions side by side and ask which to keep. Never silently drop a line the user wrote by hand. - Before showing the file, check every section against the Quality bar; fix any that fail its "Must contain" bar, and turn any section you can only fill with an invented answer into a placeholder instead. Then show the file and ask for one correction pass on the highest-stakes sections: "Read the Never and Voice sections — anything wrong?" Apply fixes and finish.
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 · 115 lines · 147 tokens per session scan A 4a9221005de9
social-context is a skill published in the GitHub repository inklate/social-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 147 tokens to every session and 1,509 once invoked, about $0.0007 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 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…