mainbranch: Skill for Claude Code

.claude/skills/mb-skill-review/SKILL.md

mb-skill-review is a skill for Claude Code from noontide-co/mainbranch. It costs 97 tokens per session (578 once invoked), scanned A, original, MIT.

A pre-publication reviewer for briefs and copy drafts that checks writing, design, structure, framework fit, and audience alignment.

In plain words
What is it for?
Use it for copy, UI, design, or pre-publish reviews when the review type and source materials are provided.
Why use it?
It catches issues before a page or draft is published and returns prioritized findings with line references and an overall assessment.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is noontide-co/mainbranch's own configuration. It tells Claude Code how to work on mainbranch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mainbranch configures →

Part of the mainbranch plugin — 21 skills shipped together

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/noontide-co/mainbranch/main/.claude/skills/mb-skill-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/noontide-co/mainbranch

Made for: Claude Code.

Or install mainbranch, the plugin that ships this one along with the rest of its 21 skills.

Wrote 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.

agentmods badge for mb-skill-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/noontide-co/mainbranch/mb-skill-review/github.svg)](https://agentmods.dev/skills/noontide-co/mainbranch/mb-skill-review)
Your own site
<a href="https://agentmods.dev/skills/noontide-co/mainbranch/mb-skill-review"><img src="https://agentmods.dev/badge/skills/noontide-co/mainbranch/mb-skill-review/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.

agentmods 80×15 button for mb-skill-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/noontide-co/mainbranch/mb-skill-review"><img src="https://agentmods.dev/badge/skills/noontide-co/mainbranch/mb-skill-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 578 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.00578
Opus 5 $0.00048 $0.00289
Sonnet 5 $0.00019 $0.00116
Haiku 4.5 $0.00010 $0.00058

Measured 11d ago against content hash 4f78828507a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mb-skill-review 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.

.claude/skills/mb-skill-review/SKILL.md · 60 lines

What it actually says

skill-review

A composable skill that wraps the Seven Sweeps + auxiliary review gates. /mb-site calls this at pre-lock and pre-publish.

Inputs

  • The artifact under review (brief or copy draft)
  • The dial (convert | story | brand)
  • Reference files (voice.md, audience.md, optional research/*)
  • The brief's do_not_state list (for archetype-fidelity check)

Outputs

A synthesized review report:

{
  "ok": false,
  "dial": "convert",
  "sweeps_run": [1, 2, 3, 4, 5, 6, 7],
  "findings": [
    {"sweep": "Specificity", "priority": "P1", "line": 12, "note": "..."},
    ...
  ],
  "panel_score": 7.2,
  "blocking": ["specificity", "ai-tells"]
}

Flow

  1. Load the artifact and the dial.
  2. Pick sweeps from references/review.md — dial-gated.
  3. Spawn one foreground subagent per active sweep, in parallel. Each returns short findings (P1/P2/P3 with line refs).
  4. Run auxiliary gates in parallel: De-AI'd, Framework-true, Archetype-fidelity.
  5. (Convert dial only) Run Expert Panel scoring across 3-5 personas.
  6. Synthesize findings into one report; group by sweep, P-priority, line.
  7. Return to caller (which surfaces to operator).

Dial-gated sweeps

Dial Sweeps
convert 1, 2, 3, 4, 5, 6, 7 + Expert Panel
story 1, 2, 3, 5, 6
brand 1, 2, 6

Cross-references

Changes

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.

  1. 11d ago First seen · 60 lines · 97 tokens per session scan A 4f78828507a5

Subscribe to this mod's changes

mb-skill-review is a skill published in the GitHub repository noontide-co/mainbranch (39 stars, last pushed 27d ago), licensed MIT. It adds 97 tokens to every session and 578 once invoked, about $0.0005 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.