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/7mza/geolocation-mcp/claude-mdgit clone --depth 1 https://github.com/7mza/geolocation-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/7mza/geolocation-mcp/claude-md)<a href="https://agentmods.dev/instructions/7mza/geolocation-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/7mza/geolocation-mcp/claude-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 | $0.00464 | $0.00464 |
| Opus 5 | $0.00232 | $0.00232 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
geolocation-mcp CLAUDE.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
CLAUDE.md
NEVER COMMIT OR PUBLISH TO DOCKERHUB WITHOUT EXPLICIT USER PROMPT
stack
- Kotlin 2.4.10, Spring Boot 4.1.1, Java 25
- Spring AI MCP server Webflux
- Reactor / coroutines reactor bridge
- GraalVM native image support (musl, static, -Os, UPX, distroless)
commands
# setup graalvm
sdk env install
# run on jvm
./gradlew bootRun
# test all
./gradlew test
# test single class
./gradlew test --tests "com.hamza.mcp.geolocation.DatabaseInitializerTest"
# kotlin lint check
./gradlew ktlintCheck
# kotlin lint fix
./gradlew ktlintFormat
# prettier format for non kotlin
npm run format
# graalvm native compilation
## -PgenerateMetadata = tracing-agent will instrument tests to generate reachability metadata
./gradlew clean ktlintFormat ktlintCheck build -PgenerateMetadata
## build native docker image
./gradlew buildImage
# publish image to docker hub
./gradlew publishImage
# run native docker image
docker run -p 8891:8080 -v geolocation_data:/home/nonroot/.geolocation-mcp 7mza/geolocation-mcp:latest
# mcp inspector
npm run mcp
# dependency vulnerability scan
./gradlew dependencyCheckAnalyze
rules
- any blocking code must run on
Schedulers.boundedElastic()BlockHound is active in JUnit to enforce this - always prefer Kotlin sugar (expression bodies,
let,also,apply, destructuring,when, extension functions, trailing lambdas, ...etc.) over Java verbosity - use
reactor-kotlin-extensionsto simplify webflux verbosity when possible
native compilation
GraalVM tracing-agent is configured in build.gradle.kts to instrument test tasks
if there's an error during an *Aot task do a ./gradlew clean && ./gradlew --stop then delete
src/main/resources/META-INF/native-image/.lock
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 · 67 lines · 464 tokens per session scan A a86b3cc3c01f
geolocation-mcp CLAUDE.md is an instructions file published in the GitHub repository 7mza/geolocation-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 464 tokens to every session, about $0.0023 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
paiml-mcp-agent-toolkit CLAUDE.md
Claude Code instructions for paiml/paiml-mcp-agent-toolkit, covering claude code configuration, batuta stack (sovereign ai tools), dependencies requiring review, critical: code search policy and search mode flags.
paiml-mcp-agent-toolkit AGENTS.md
AGENTS.md instructions for paiml/paiml-mcp-agent-toolkit, covering antigravity global rules for pmat, agent guidelines and contract-first, and how it is enforced.
oracle-forms-mcp CLAUDE.md
Claude Code instructions for aoreshkov/oracle-forms-mcp, covering claude.md, layout, invariants, gotchas and commands.
openstreetmap-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/openstreetmap-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
openstreetmap-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/openstreetmap-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
minestom-mcp AGENTS.md
Instructions for RonaldBunk/minestom-mcp, a project described as: A stdio MCP server for Minestom, implemented with the Model Context Protocol SDK and TanStack AI tool definitions.