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/agricidaniel/local-competitor-map/agents-mdgit clone --depth 1 https://github.com/AgriciDaniel/local-competitor-mapWrote 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/agricidaniel/local-competitor-map/agents-md)<a href="https://agentmods.dev/instructions/agricidaniel/local-competitor-map/agents-md"><img src="https://agentmods.dev/badge/instructions/agricidaniel/local-competitor-map/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 | $0.00380 | $0.00380 |
| Opus 5 | $0.00190 | $0.00190 |
| Sonnet 5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
local-competitor-map 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 4d 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.
What it actually says
AGENTS.md
Guidance for AI coding agents (and humans) working in this repo.
What this is
A client-side TypeScript app (Lit + Vite). A Gemini agent drives a Google
photorealistic 3D map (<gmp-map-3d>) and finds local competitors via the Google
Places API, wired over an in-process Model Context Protocol transport.
Layout
index.tsxis the entry: Gemini chat plus MCP client/server wiring and the agent system prompt.mcp_maps_server.tsdefines the MCP tools the agent can call.map_app.tsis the Lit component: the 3D map, chat, competitor list, detail card, and declutter filter.places.tsruns the Places competitor search.settings.tsresolves keys (localStorage, then the gitignoredruntime-keys.ts).dataforseo.tsis shelved for a future local-SEO ranking layer.
Workflow
- Install:
npm install(apreparestep seedsruntime-keys.tsfrom the example). - Run:
npm run dev. Type-check:npm run typecheck. Build:npm run build. - Keys come from the Settings tab or
runtime-keys.tsat runtime, not from the build.
House rules
- Never commit secrets.
runtime-keys.ts,.env*, and*.zipare gitignored; keep the bundled fallback key empty. - No em dashes anywhere. Use
-,:,,, or.. - Keep keys client-side. Do not reintroduce build-time secret injection.
- Match the surrounding style: small, dependency-light, declarative comments.
npm run typecheckmust pass before committing.
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.
- 4d ago First seen · 33 lines · 380 tokens per session scan A 7d517d2fc618
local-competitor-map AGENTS.md is an instructions file published in the GitHub repository AgriciDaniel/local-competitor-map (29 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 380 tokens to every session, about $0.0019 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 2026-08-30.
Other instructions, from other repositories
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
botmux CLAUDE.md
Claude Code instructions for deepcoldy/botmux, covering botmux, 构建 & 运行, bun 开发链路, worktree 的 nodemodules:共享还是独立(改前必读) and 编译态(单文件二进制)注意.
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.
happier CLAUDE.md
Claude Code instructions for happier-dev/happier, covering claude code and typescript commands.