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 moses607/socialforge --skill onboarding-brand-briefgit clone --depth 1 https://github.com/moses607/socialforgeWrote 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/moses607/socialforge/onboarding-brand-brief)<a href="https://agentmods.dev/skills/moses607/socialforge/onboarding-brand-brief"><img src="https://agentmods.dev/badge/skills/moses607/socialforge/onboarding-brand-brief/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/moses607/socialforge/onboarding-brand-brief"><img src="https://agentmods.dev/badge/skills/moses607/socialforge/onboarding-brand-brief.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 | $0.00128 | $0.01108 |
| Opus 5 | $0.00064 | $0.00554 |
| Sonnet 5 | $0.00026 | $0.00222 |
| Haiku 4.5 | $0.00013 | $0.00111 |
Grade A, and why
onboarding-brand-brief 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding Brand Brief
Everything downstream — hooks, personas, calendars, captions — degrades to generic mush without a foundation the model can anchor on. A brand brief is not branding fluff; it is a compression of five decisions (who you serve, why you, what you sell, where, and how you sound) into a block short enough to prepend to every generation. Extract it once, reuse it forever. The single highest-leverage step is voice training: a model that has read five of the creator's real posts stops writing "in today's fast-paced world" and starts writing like them.
Method: interrogate the five pillars
Ask these in order. One question at a time. Push back on vague answers — "fitness" is not a niche, "busy moms who want to lift heavy without a gym" is.
- Niche + sub-niche. Force specificity. Broad niche = the room; sub-niche = the corner they own. Reject anything you could put on a billboard for a competitor.
- Positioning / unique angle. Finish this sentence with them: "Unlike everyone else in [niche], I ___." If they can't, probe their contrarian take, origin story, or unfair advantage.
- Offer + primary goal. What is the money or growth event? Followers, email leads, product sales, bookings? Name ONE primary goal and the metric that proves it. Secondary goals get logged but never drive the strategy.
- Platforms. Where do they post now and where do they want to. Rank them. Downstream skills adapt format per platform.
- Voice attributes. Pull 3 adjectives, but make them earn it — "professional" is banned. Push for tension pairs like "blunt but warm" or "nerdy but irreverent".
Method: voice training from real posts
- Ask for 3-5 of their best-performing or favorite posts — their own, or admired creators they want to sound like (flag which).
- Extract three layers explicitly: tone (emotional default — deadpan, hyped, tender), lexicon (recurring words, slang, jargon, signature phrases, emoji habits), rhythm (sentence length, one-liners vs paragraphs, use of line breaks, punctuation quirks).
- Derive a do-words / don't-words list: words that sound like them, and words that would break the illusion (corporate filler, hashtag-speak, AI tells like "delve", "elevate", "unlock").
- Write one 2-sentence sample in their voice and ask "does this sound like you?" Iterate until yes. Do not finalize the brief on an unconfirmed voice.
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 · 52 lines · 128 tokens per session scan A d74a8873ad09
onboarding-brand-brief is a skill published in the GitHub repository moses607/socialforge (2 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 1,108 once invoked, about $0.0006 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
self-media-content-workflow
A general workflow for planning, creating, adapting, reviewing, and archiving social-media content.
self-media-short-video
A planning and production guide for vertical short videos on platforms such as TikTok, Xiaohongshu, and WeChat Channels.
self-media-content-delivery
A file-based process for saving, versioning, checking, and packaging completed social-media content.
self-media-trend-radar
A research guide for tracking public trends, search terms, popular content, competitors, and audience questions. It turns that research into original content ideas supported by evidence.
x-marketing
Plan, draft, audit, and publish posts and threads for X (Twitter). Use when the user wants to write a single tweet or an auto-numbered thread, build a long-form tweetstorm, remove AI tells from a draft, reverse-engineer the hook from a viral tweet, draft a reply or quote tweet, or plan a week of X content. Tweets and…
smart-illustrator
An image-generation tool for adding illustrations to articles, creating slide presentations and infographics, or making cover images and thumbnails. It can also create prompts without generating the images.