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/rnett/gradle-mcp/agents-mdgit clone --depth 1 https://github.com/rnett/gradle-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/rnett/gradle-mcp/agents-md)<a href="https://agentmods.dev/instructions/rnett/gradle-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rnett/gradle-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 | $0.00880 | $0.00880 |
| Opus 5 | $0.00440 | $0.00440 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
gradle-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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gradle MCP Project Memory
This repository contains a Model Context Protocol (MCP) server providing deep, programmatic access to Gradle build systems.
Primacy Zone: Fundamental Mandates
- Security & Secrets: NEVER log, print, or commit API keys, secrets, or .env contents.
- Source Control: NEVER create commits or push unless explicitly instructed.
- Tool Preference: ALWAYS prefer Gradle MCP tools (
gradle,query_build, etc.) over raw shell execution. - Verification: NO WORK IS COMPLETE WITHOUT TESTS. Use
testfor most changes;checkorintegrationTestfor wider impacts. See testing-standards. - Tool Metadata: After modifying tool source, MUST run
./gradlew :updateToolsListto sync documentation. - Isolated Contexts: NEVER use Koin's global context (
startKoin). ALWAYS use local isolated contexts. - JBang Catalog: We maintain a catalog at
https://github.com/rnett/jbang-catalogfor easy execution. - No Backwards Compatability: The only consumers of MCP servers like this one are AI agents, which live entirely in the moment and do not care about backwards compatability of tools.
Technical Standards (OpenSpec)
OpenSpec specs are the primary source of truth for architectural rationale, implementation standards, and technical mandates. Refer to them for all project-specific guidance:
- Testing Standards: testing-standards (Power Assert, tool verification, mocking, async events).
- Concurrency & Execution: build-execution and build-output-concurrency (Thread safety, atomic operations, hot-path optimizations, output parsing, REPL sessions).
- Indexing & Search: multi-reader-search (Lucene standards, FQN/Regex search, match expansion, pooling, fail-fast).
- Caching & Locking: cas-dependency-cache (CAS model, granular locking, failure detection, GC, path abstractions).
- Progress Reporting: build-monitoring-progress (UX, parsing, init script reporting, parallel strategies).
- Gradle Source Overview: gradle-internal-research (Core APIs, platforms, and research workflows).
- Architecture Overview: build-output-concurrency and concurrency-cas-architecture.
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 · 52 lines · 880 tokens per session scan A d61d50c9c76e
gradle-mcp AGENTS.md is an instructions file published in the GitHub repository rnett/gradle-mcp (60 stars, last pushed yesterday), licensed Apache-2.0. It adds 880 tokens to every session, about $0.0044 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
mcp AGENTS.md
AGENTS.md instructions for Teamwork/mcp, covering agents.md, this repository is public, project overview, setup commands and build and run.
raindrop-mcp AGENTS.md
Instructions for adeze/raindrop-mcp, covering raindrop mcp — codex guide, commands, architecture, non-negotiable contracts and codex workflow.
raindrop-mcp mcp-inspector.instructions.md
Instructions for adeze/raindrop-mcp, covering mcp inspector cli prompt, prerequisites, usage examples, list available tools and send a protocol request (e.g., ping).
raindrop-mcp GEMINI.md
Instructions for adeze/raindrop-mcp, covering raindrop mcp server - project context, project overview, core technologies, architecture and key commands.
raindrop-mcp dxt.instructions.md
Instructions for adeze/raindrop-mcp: I want to build this as an MCP Bundle, abbreviated as "MCPB". Please follow these steps.
mcpscore AGENTS.md
AGENTS.md instructions for mcp-box/mcpscore, covering agent instructions for mcpscore and gotchas (learned the hard way).