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 Fusion-Data-Company/bristol-os --skill deal-packetgit clone --depth 1 https://github.com/Fusion-Data-Company/bristol-osWrote 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/fusion-data-company/bristol-os/deal-packet)<a href="https://agentmods.dev/skills/fusion-data-company/bristol-os/deal-packet"><img src="https://agentmods.dev/badge/skills/fusion-data-company/bristol-os/deal-packet/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/fusion-data-company/bristol-os/deal-packet"><img src="https://agentmods.dev/badge/skills/fusion-data-company/bristol-os/deal-packet.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 | $0.00083 | $0.00959 |
| Opus 5 | $0.00042 | $0.00479 |
| Sonnet 5 | $0.00017 | $0.00192 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
deal-packet 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 12d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deal Packet — the full institutional set
The flagship deliverable: one cohesive, branded, fully-cited package a principal or IC can act on. Claude builds all of it (HARD LAW: do it for them) and saves it to the deal folder.
Read first
bristol-os/reference/underwriting-model.md— every line item, formula, sensitivity (the analytical authority).bristol-os/reference/property-data-dictionary.md— parcel → development read.bristol-os/brand/STYLE.md— the look (colors, type, tables, charts) for ALL pieces.bristol-os/docs/CITATIONS.md— cite everything; build the sources registry.bristol-os/reference/rigor-standard.md— the institutional metric set + checks every piece must hit. Produce the packet via thedeal-evolutionloop (V1→V2→V3) — don't ship a first draft.
Build order (gather data once, render four ways)
- Pull the data (cite each as you go into
deals/<name>/sources.md):- Parcel/owner via
quarry-parcels(owner, zoning, units, acreage, value). - Market & comps via
market-comp-analysis(rents, occupancy, supply pipeline). - Macro via FRED (rates), demographics via Census, deeper context via Tavily/Exa (see
docs/DATA-SOURCES.md). - Bristol's model inputs from the user (tag "per Bristol underwriting").
- Parcel/owner via
- Excel model (
xlsxskill) — build from the model-tab outline inunderwriting-model.md: Inputs, Revenue, OpEx, Dev Budget, Returns, Sensitivity, Comps, Sources tab. Branded per STYLE.md (navy headers, input cells highlighted, number formats, "Src" columns). Savedeals/<name>/<name>-model.xlsx. - IC memo (
docxskill) — fromtemplates/investment-memo.md: recommendation & ask, snapshot, market, site, assumptions (with sensitivity), capital, risks/mitigants, appendix. Every figure[S#]; sources as endnotes. Savedeals/<name>/<name>-IC-memo.docx. - Deck (
pptxskill) — ~8–10 slides: title, recommendation, market, site/parcel, returns, sensitivity, capital stack, risks, sources slide. STYLE.md master. Savedeals/<name>/<name>-deck.pptx. - One-pager (
report-visuals→infographic-deal-snapshot.svg→ PDF/PNG) — the at-a-glance snapshot with cited figures. Savedeals/<name>/<name>-one-pager.pdf. - Sources registry —
deals/<name>/sources.mdpopulated; every deliverable backlinks to it.
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.
- 12d ago First seen · 41 lines · 83 tokens per session scan A b9378672869e
deal-packet is a skill published in the GitHub repository Fusion-Data-Company/bristol-os (1 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 959 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 2026-08-31.
Other skills, from other repositories
cwicr-report-generator
Generate professional cost estimation reports from CWICR calculations. HTML, PDF, Excel outputs with charts and breakdowns.
audit-xls
Audit spreadsheet, formula error detection, hardcoded cell finder, cross-sheet reference audit, workbook auditor, Excel model audit, financial model QA, spreadsheet review, cell dependency trace, formula integrity check.
xlsx-financials
Produce formatted .xlsx financial statement workbooks from XBRL statement data. Uses Bash + openpyxl (Python) following Anthropic FSI xlsx-author conventions for professional Excel output with calculation arc cross-validation.
synthesize
Thesis report synthesis — turn a thesis's markdown artifacts into its letter-size thesis-report.html, then OPTIMIZE it against real page renders. Four-step loop — pack (deterministic Python bundle of all sources + report/metrics.json), author (the LLM writes report/content.html — narrative, KPI tiles, badges…
procesar-mis-estados-de-cuenta
Proceso un lote de estados de cuenta bancarios y de tarjeta de crédito en PDF o CSV de principio a fin: extraigo cada transacción (subagentes Haiku en paralelo), normalizo los nombres de las contrapartes, categorizo contra tu plan de cuentas bloqueado (subagentes Sonnet en paralelo), detecto transferencias entre…
historical-data-manager
Extract, clean, and organize legacy construction data from archives. Migrate historical project data, cost records, and schedules into modern formats.