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/kevyder/banrepco_mcp/agents-mdgit clone --depth 1 https://github.com/kevyder/banrepco_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/kevyder/banrepco_mcp/agents-md)<a href="https://agentmods.dev/instructions/kevyder/banrepco_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kevyder/banrepco_mcp/agents-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 5.1 | $0.00840 | $0.00840 |
| Opus 5 | $0.00420 | $0.00420 |
| Sonnet 5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
banrepco_mcp AGENTS.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 5d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Stack
- Single-package TypeScript Cloudflare Worker project. Use Bun commands; the repo is locked with
bun.lockand Dependabot is configured for thebunecosystem. - Main Worker entrypoint is
src/index.ts, configured bywrangler.jsoncmain.
Runtime Wiring
- This is an MCP server built on Cloudflare Workers Durable Objects.
BanrepcoMCPextendsMcpAgentinsrc/index.tsand is also the Durable Object class bound asMCP_OBJECTinwrangler.jsonc. - HTTP routing is minimal and path-sensitive:
/sseand/sse/messageuseBanrepcoMCP.serveSSE("/sse");/mcpusesBanrepcoMCP.serve("/mcp"). Preserve those paths unless the protocol surface is being changed deliberately. - Tool registration: new MCP tools extend
BaseTool(src/tools/tool.interface.ts), implementprotected initTools(), and get instantiated +start()-ed inBanrepcoMCPconstructor.start()is final — callsinitTools()internally.
Environment And Generated Types
BAN_REP_CO_API_URLis required at runtime.src/index.tspasses it intoHttpClient, andworker-configuration.d.tsdeclares it.wrangler.jsonchas"vars"commented out — the var is NOT declared in config. Provide it viawrangler secret put BAN_REP_CO_API_URL(prod) or.dev.vars(local dev). Wrangler does NOT read.env; use.dev.varsfor local secrets.- After changing Worker bindings or env vars in
wrangler.jsonc, runbun run cf-typegento regenerateworker-configuration.d.ts.
Commands
- Dev server:
bun run devorbun run start. - Deploy:
bun run deploy. - Typecheck:
bun run type-check. - Regenerate Cloudflare types:
bun run cf-typegen. - Format:
bun run format. - Autofix lint:
bun run lint:fix.
Verification Notes
- There is no test suite or CI workflow in this repo today.
biome.jsononly includessrc/**/*and explicitly excludesworker-configuration.d.ts, so lint/format commands do not cover generated Worker types.bunx biome check srccurrently reports existing repo issues outside any new change, so avoid broad formatting-only churn unless the task is specifically to clean that up.
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.
- 5d ago First seen · 53 lines · 840 tokens per session scan A c7c3e75c0d5d
banrepco_mcp AGENTS.md is an instructions file published in the GitHub repository kevyder/banrepco_mcp (9 stars, last pushed 24d ago), licensed MPL-2.0. It adds 840 tokens to every session, about $0.0042 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
mcp AGENTS.md
AGENTS.md instructions for cloudflare/mcp, covering agents.md, project overview, mcp specification compliance, repository structure and setup.
mcp-ts-core AGENTS.md
AGENTS.md instructions for cyanheads/mcp-ts-core, covering developer protocol, consumers, core rules, exports reference and import conventions.
flaim AGENTS.md
AGENTS.md instructions for jdguggs10/flaim, covering repo agent guide, scope, public/private boundary, important distinction: product assets vs repo instructions and start here.
mcp-migration-check AGENTS.md
AGENTS.md instructions for AlpayC/mcp-migration-check, covering working in this repository, shape, rules that are not negotiable, before you say it works and adding a rule.
sidewise CLAUDE.md
Claude Code instructions for nulljosh/sidewise, covering sidewise, architecture, endpoints, develop and tests.
ai-engineering-leader-toolkit CLAUDE.md
Claude Code instructions for marian-kamenistak/ai-engineering-leader-toolkit, covering eng-leadership-toolkit, what this is, stack, run / build / deploy / test and dev: npm run dev.