Borrowing it
Nothing to install: this file belongs to noontide-co/mainbranch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/noontide-co/mainbranch/main/.claude/skills/mb-skill-brief-draft/SKILL.mdgit clone --depth 1 https://github.com/noontide-co/mainbranchWrote 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/noontide-co/mainbranch/mb-skill-brief-draft)<a href="https://agentmods.dev/skills/noontide-co/mainbranch/mb-skill-brief-draft"><img src="https://agentmods.dev/badge/skills/noontide-co/mainbranch/mb-skill-brief-draft/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/noontide-co/mainbranch/mb-skill-brief-draft"><img src="https://agentmods.dev/badge/skills/noontide-co/mainbranch/mb-skill-brief-draft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.00821 |
| Opus 5 | $0.00037 | $0.00411 |
| Sonnet 5 | $0.00015 | $0.00164 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
mb-skill-brief-draft 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 10d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-brief-draft
A composable skill for drafting a site / campaign brief. /mb-site calls this in Step 2 of the minisite flow. /mb-ads, /mb-organic, or sales-video workflows may call it later; for now it is only used by /mb-site.
Inputs
offer.md,audience.md,voice.md(resolved viamb resolve)research/*.mdproduced earlier in the flow- Operator picks:
dial,archetype(optional),audience_current_archetype(optional) - Picked headline formulas (2-3 from
references/headline-formulas.md)
Outputs
A single markdown artifact: decisions/YYYY-MM-DD-minisite-brief-<slug>.md with the v0.1 schema:
---
type: brief
date: YYYY-MM-DD
slug: <offer-slug>
status: proposed
dial: convert | story | brand
conversion_mechanism: lead_form | book_call | purchase | other
takes_calls: true | false
archetype: ...
audience_current_archetype: ...
copy_framework_tag: ...
headline_formulas_picked: [...]
do_not_state: [...]
four_forces: {push, pull, habit, anxiety}
voice_anchor_lines: {use: [...], avoid: [...]}
---
conversion_mechanism and takes_calls are operator-stated facts, not guesses — see the gate in Flow step 0.
Plus the body sections: headline + subhead, value prop, mechanism summary, picked supporting pages, conversion endpoint, adjacency map.
Flow
- Conversion-mechanism gate (before any copy). Pin what the visitor does
to convert — submit a lead form, book a call, buy — and specifically whether
the operator takes calls. This is an operator-stated fact: if it is not
already recorded (in
offer.md, a prior decision, or the operator's own words this session), STOP and ask before drafting. Never assume a model — the headline, value prop, and mechanism summary are all shaped by it, so a wrong guess rewrites the whole brief. A real business we built lost a full day when an agent invented a call-booking flow the operator never chose. Record the answer inconversion_mechanism+takes_calls. - Read inputs. Resolve offer/audience/voice; load picked archetype detail file.
- Compose schema header. Fill in fields from operator picks, including the
gated
conversion_mechanism+takes_calls. - Draft headline + subhead. Apply one of the picked formulas. Aim for ≤ 2 lines.
- Draft value prop. 3 short reasons OR one extended argument. Match the dial.
- Draft mechanism summary. For the how-it-works page.
- Pick supporting pages. 2-4 from proof / pricing / faq / about.
- Build adjacency map. Per Hughes paired-imagery rule, name two images per section.
- Hand off to skill-review with the dial.
What ships with it
11 files 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.
- references/archetypes.md 3.5 KB
- references/archetypes/broken-hero.md 2.0 KB
- references/archetypes/dark-hero.md 6.2 KB
- references/archetypes/david-goliath.md 2.1 KB
- references/archetypes/redemption.md 6.7 KB
- references/archetypes/savior.md 1.9 KB
- references/archetypes/tragedy-mindset.md 6.2 KB
- references/archetypes/tragic-comedy.md 7.3 KB
- references/archetypes/victim.md 5.3 KB
- references/archetypes/wounded-healer.md 2.6 KB
- references/headline-formulas.md 3.1 KB
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.
- 10d ago First seen · 73 lines · 74 tokens per session scan A 293b14574926
mb-skill-brief-draft is a skill published in the GitHub repository noontide-co/mainbranch (39 stars, last pushed 26d ago), licensed MIT. It adds 74 tokens to every session and 821 once invoked, about $0.0004 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
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
processing-markdown
Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.
web-scraping
Fetches web pages and extracts structured data using mq's toolchain (mq-crawl for fetching/crawling/JS rendering, mq for HTML-to-Markdown selector-based extraction, http() for in-query requests). Use when the user wants to scrape a URL, pull structured data out of a webpage, crawl a site, or turn HTML into…
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
larksnap-fetch
A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.
suiko
A Japanese writing and review workflow for checking whether text sounds uniform, translated, unnatural, or difficult to read. It supports writing and editing documents such as reports, guides, meeting notes, proposals, and emails.