Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/DaizeDong/buy-me-a-carnpx agentmods add skills/daizedong/buy-me-a-car/dossier-builderWrote 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/daizedong/buy-me-a-car/dossier-builder)<a href="https://agentmods.dev/skills/daizedong/buy-me-a-car/dossier-builder"><img src="https://agentmods.dev/badge/skills/daizedong/buy-me-a-car/dossier-builder/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/daizedong/buy-me-a-car/dossier-builder"><img src="https://agentmods.dev/badge/skills/daizedong/buy-me-a-car/dossier-builder.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 | $0.00100 | $0.02465 |
| Opus 5.5 | $0.00040 | $0.00986 |
| Sonnet 5.5 | $0.00020 | $0.00493 |
| Haiku 4.5 | $0.00010 | $0.00247 |
Grade A, and why
dossier-builder 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 15d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Dossier Builder
Deliver the buying report from the evidence already collected. A broad buying workflow includes this artifact without a separate request for detail or a PDF. The agent prepares the config; do not ask the buyer to populate schema fields.
Choose the document purpose first
| Purpose | Generator | Evidence needed |
|---|---|---|
| Buyer research and shortlisting | generate_research_report.py |
Dated source coverage, candidate listings, analysis and explicit unknowns. Zero written dealer quotes is allowed. |
| Dealer-facing purchase proposal | generate_dossier.py |
Complete competing written OTD quotes, supported facts and an itemized authorized proposal. |
The first is the default during market research. The second is a later outward document. Do not make the proposal's two-quote or complete-fee requirement block useful research. Both have separate demo/live privacy modes; research versus proposal is not the same choice as synthetic versus real data.
Generate the buyer research packet
Follow report delivery. Reuse the current private cycle, criteria and captured evidence. Produce substantive comparisons, configuration tradeoffs, delivered-cost uncertainties, suitability, ownership risks, shortlist rationale and next actions, rather than a long intake questionnaire or validation log. Use the research schema to assemble structured input.
python skills/orchestrator/scripts/generate_research_report.py --mode live --config cycles/session/research_config.json --output cycles/session/buyer_research.html --to-pdf cycles/session/buyer_research.pdf
Live relative paths resolve under private DATA. Keep
master_comparison.md alongside the report. When a scenario has fictional buyer
criteria but real source observations, use live private storage and label every
fictional criterion as an assumption; never turn observed inventory into public
demo fixtures. List asking prices as asking prices, leave missing fees unknown,
and explain what evidence would change the shortlist.
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.
- 15d ago Changed f800228e14ab
- 1mo ago Changed · +30 lines · -6 tokens per session 5a53a981e371
- 1mo ago First seen · 178 lines · 106 tokens per session scan A 84a2d75a69da
dossier-builder is a skill published in the GitHub repository DaizeDong/buy-me-a-car (11 stars, last pushed 11d ago), licensed MIT. It adds 100 tokens to every session and 2,465 once invoked, about $0.0004 per session on Opus 5.5. 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
pdf-report
Generate a branded PDF report: executive summary, campaign or channel review. "export this as a branded PDF".
album-report
Turn an album or a selection into a PDF report: metadata per photo, frames per video, and Claude's own description of what is in each one. Use when the user says "PDF of the album", "album report", "export to PDF", "make a document with these photos", "catalog the album", "identify what is in each video and put it in…
doc-intel-contract-pl
Normalizuje wyjscie darmowego RODO-safe stacku OCR/PDF (opendataloader-pdf, pdftotext, Chandra OCR, LiteParse - OCR skanow na CPU, OCR PATRONa/Gaius-Lex) do jednego audytowalnego kontraktu {blocktype, bbox, text, confidence} inspirowanego architektura Mistral OCR 4 (idea, nie wagi - model zamkniety=SKIP). Daje trzy…
waliduj-podpis-pdf-pl
Sprawdza podpis elektroniczny w PRZYCHODZĄCYM PDF - czy plik zmieniono po podpisaniu, kto go podpisał, kiedy, czy jest znacznik czasu i czy podpis obejmuje cały dokument. Działa lokalnie na pyHanko, bez sieci i bez wysyłania pliku gdziekolwiek (RODO-safe, tajemnica zawodowa). Wyłącznie odczyt - NIE podpisuje niczego.…
opendataloader-pdf
Wysokiej jakości konwerter PDF→JSON/Markdown dla AI - zachowuje reading order, strukturę tabel, headings. Użyj gdy użytkownik mówi "wysoka jakość PDF", "papers naukowe PDF", "tabele z PDF", "opendataloader", "PDF z skomplikowaną strukturą", albo gdy MarkItDown daje słaby output. Główny konwerter PDF→MD w pipeline…
akta-przeszukiwalne-pl
Zamienia folder akt sprawy (PDF, takze skany bez warstwy tekstowej) w tekst z numerami stron, lokalna wyszukiwarke i raport: strony nieczytelne, duplikaty plikow oraz pliki o IDENTYCZNEJ tresci pod roznymi nazwami (bywa sladem brakujacego pisma). OCR dziala lokalnie na CPU - tekst akt nie opuszcza komputera, bez konta…