Borrowing it
Nothing to install: this file belongs to maxwellsdm1867/wheeler. 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/maxwellsdm1867/wheeler/main/.claude/skills/wheeler-brief/SKILL.mdgit clone --depth 1 https://github.com/maxwellsdm1867/wheelerWrote 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/maxwellsdm1867/wheeler/wheeler-brief)<a href="https://agentmods.dev/skills/maxwellsdm1867/wheeler/wheeler-brief"><img src="https://agentmods.dev/badge/skills/maxwellsdm1867/wheeler/wheeler-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/maxwellsdm1867/wheeler/wheeler-brief"><img src="https://agentmods.dev/badge/skills/maxwellsdm1867/wheeler/wheeler-brief.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 | $0.00342 | $0.02235 |
| Opus 5 | $0.00171 | $0.01118 |
| Sonnet 5 | $0.00068 | $0.00447 |
| Haiku 4.5 | $0.00034 | $0.00224 |
Grade A, and why
wheeler-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 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wheeler research brief
Turn a Wheeler plan (and later its execution) into one self-contained HTML page a scientist can read top to bottom: the question, a bulleted game plan, and figure mockups that pre-register what will be plotted. The HTML embeds everything (figures as base64 or inline SVG), so it opens offline from any location.
The brief is a thinking aid, not a report (read this first)
The whole point is to sharpen thinking and decision-making at a glance. If it turns into a wall of text, the scientist will not read it, and it has failed. Be ruthless about what goes on the visible page:
- The visible page holds only what drives a decision: the question, the open or settled decisions, the figures (and how each hypothesis would look different in them), the next steps, the success criteria. Everything is scannable in well under a minute.
- Captions are one line. Decision text and its resolution are short phrases, not paragraphs. Step titles are a handful of words. Success criteria are terse.
- Detail, nuance, and full rationale go in the collapsed Background section or stay in the plan markdown, not on the visible page. When in doubt, cut it from the brief; the plan file is the system of record, the brief is the lens.
- Prefer fewer, load-bearing items: the 3 to 5 steps that matter, not all 9 sub-tasks; the 2 to 3 real decisions, not every minor choice. A brief that lists everything helps no one decide anything.
You do two jobs at once:
- Elicit the high-level content the brief needs, if the plan does not already contain it. This is where you genuinely help planning: a scientist often has the question and the analysis steps but has not said out loud what the key figure will look like or which decision is the load-bearing one. Drawing that out is the point.
- Render the brief deterministically from a spec JSON via the bundled script.
How it works
You compose a spec JSON; scripts/render_brief.py turns it into HTML. You never write
HTML by hand. The full spec contract is in references/spec-schema.md (read it before
composing). Figure styling guidance is in references/figure-style-guide.md and
references/mockup-svg-guide.md (read whichever applies to the figures you are
drawing).
What ships with it
7 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.
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 · 164 lines · 342 tokens per session scan A ae2ff5d160d0
wheeler-brief is a skill published in the GitHub repository maxwellsdm1867/wheeler (11 stars, last pushed 8d ago), licensed MIT. It adds 342 tokens to every session and 2,235 once invoked, about $0.0017 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
comps-analysis
Build comparable-company valuation workbooks in Excel.
wowerpoint
Turn one document into a kawaii NotebookLM slide-deck PDF. Use for "wowerpoint this", "make a deck about ", "turn this report into slides", or any request to render a single document as shareable narrative slides.
save-as-pdf
Reformat the current HTML design into a paginated, paper-ready PDF. The "Instant" export already gives the user a PDF at the design's native pixel size — this path is for when they want real pages.
treatment-plans
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
venue-templates
Prepare journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Use when selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF.
xlsx
Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm, .xltx) where the workbook file is the primary deliverable. Use for formulas, formatting, financial models, multi-sheet workbooks, and tabular cleanup exported to Excel. Also applies to .csv/.tsv when the user wants spreadsheet output. Do NOT use for…