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 agentmods add instructions/final-commerce/final-pos-mcp/gemini-mdgit clone --depth 1 https://github.com/Final-Commerce/final-pos-mcpWrote 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/instructions/final-commerce/final-pos-mcp/gemini-md)<a href="https://agentmods.dev/instructions/final-commerce/final-pos-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/final-commerce/final-pos-mcp/gemini-md.svg" alt="Measured on agentmods" 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 | $0.00789 | $0.00789 |
| Opus 5 | $0.00394 | $0.00394 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
final-pos-mcp GEMINI.md 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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building Final POS apps
You are connected to the Final Flows MCP server (final-flows), the
build API for Final — a platform for creating custom
point of sale, kiosk, self-checkout, KDS, and in-person payment apps that run
on any hardware (desktop, tablet, mobile, payment terminal, line buster, menu
board). A second server, final-docs, answers questions about the Final POS
REST API (https://api.finalpos.com).
Everything you do through final-flows shows up live in the user's builder at
build.finalpos.com: the flow appears in their home grid, your session appears
as a chat in the rail, and every file write is a restorable checkpoint.
The build loop
Follow this order for every POS app you build:
get_scaffold— call once per session to learn the app contract: engine-owned files (never write them), the baselinepackage.json, and the construction rules.create_flowfor a new app, orconnect_chatto attach to an existing flow the user gives you. Never create a new flow when the user already has one.log_message(role"user") with the user's build brief, so their builder timeline stays faithful. Log short assistant notes at milestones.- Ground before you write. Every
renderClientcall must be verified withlookup_command_framefirst — never guess a method signature, entity field, or pub/sub topic. Uselookup_engine_componentfor./final/*helpers andlookup_pos_api(or thefinal-docsserver) for REST calls. - Start from blueprints. Check
list_blueprints/get_blueprintfor vetted screens (product grids, carts, payment surfaces, receipts) and adapt them instead of writing screens from scratch. write_flow_fileswith full file contents. App code lives undersrc/, entry pointsrc/App.tsx. Writes to engine-owned paths are rejected.validate_flowand fix every finding — guardrails, command-frame typecheck, and secret scan must all pass.start_previewand give the user the public preview URL so they can see the app live. Usesync_previewafter edits (it is also the fastest compile check) andget_preview_statusif something looks wrong.
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.
- 3d ago First seen · 61 lines · 789 tokens per session scan A b0ad7f40ae13
final-pos-mcp GEMINI.md is an instructions file published in the GitHub repository Final-Commerce/final-pos-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 789 tokens to every session, about $0.0039 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 instructions, from other repositories
gemini-extension GEMINI.md
Instructions for conversiontools/gemini-extension, covering conversion tools, if the tools are not available, how to convert a file, build a custom converter (ai studio) and tip: prefer the ctio cli when available.
meteocontrol-mcp GEMINI.md
Gemini CLI instructions for nielsvbrecht/meteocontrol-mcp, covering meteocontrol extension context, core mandates & communication style, operational guidelines, 1. performance analysis & metrics translation and 2. proactive troubleshooting.
visual-explainer-extension GEMINI.md
Instructions for Jakedismo/visual-explainer-extension, covering visual-explainer, project overview, main technologies, extension structure and available commands.
gemini-mem GEMINI.md
Instructions for djinn-soul/gemini-mem, covering gemini.md, memory behavior and operator notes.
victoriametrics-logs-mcp GEMINI.md
Gemini CLI instructions for nielsvbrecht/victoriametrics-logs-mcp, covering core capabilities, victoriametrics (metrics), victorialogs (logs), available tools and metrics tools.
gemini-api-docs-mcp-ext GEMINI.md
Gemini CLI instructions for derailed-dash/gemini-api-docs-mcp-ext, covering gemini api documentation agent instructions, capabilities, when to use, best practices and official reference.