agentmods.dev

foundation-base: Instructions file for Gemini CLI

GEMINI.md

foundation-base GEMINI.md is an instructions file for Gemini CLI from zcaudate-xyz/foundation-base. It costs 15,903 tokens per session, scanned A, original, MIT.

Project-specific instructions for the foundation-base codebase, covering its testing framework, scheduler, runtime components, and related tools.

In plain words
What is it for?
Writing tests and making changes involving the code.test framework, scheduled processes, runtimes, and foundation tools.
Why use it?
They record codebase rules and known behaviours that a general-purpose coding agent may not know.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions Gemini CLI.

This is zcaudate-xyz/foundation-base's own configuration. It tells Gemini CLI how to work on foundation-base itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything foundation-base configures →

not rated 42repo changed 2d ago A scan 15,903 tokens original MIT
View source ↗ zcaudate-xyz/foundation-base zcaudate.xyz
Reuse

Borrowing it

Nothing to install: this file belongs to zcaudate-xyz/foundation-base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zcaudate-xyz/foundation-base/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/zcaudate-xyz/foundation-base

Made for: Gemini CLI.

Wrote 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.

agentmods badge for foundation-base GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zcaudate-xyz/foundation-base/gemini-md/github.svg)](https://agentmods.dev/instructions/zcaudate-xyz/foundation-base/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/zcaudate-xyz/foundation-base/gemini-md"><img src="https://agentmods.dev/badge/instructions/zcaudate-xyz/foundation-base/gemini-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for foundation-base GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zcaudate-xyz/foundation-base/gemini-md"><img src="https://agentmods.dev/badge/instructions/zcaudate-xyz/foundation-base/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15,903 This file is loaded in full into every session.
When invoked 15,903 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.15903 $0.15903
Opus 5 $0.07952 $0.07952
Sonnet 5 $0.03181 $0.03181
Haiku 4.5 $0.01590 $0.01590

Measured 2d ago against content hash 171538d2e1da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

foundation-base GEMINI.md scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Install Leiningen**: Leiningen must be installed manually using: `curl -O https://raw.githubusercontent.com/technomancy/leiningen/stable/bin/lein && chmod +x lein`.
GEMINI.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learnings

code.test Framework

  • Fact Structure: Tests are defined using fact. Metadata controls execution.
  • Component Injection: Components like |rt| are NOT injected via :use or :let in the way standard clojure.test fixtures might work.
  • Global Components: fact:global defines components that can be accessed in tests.
  • Broken :use/:let: The :use and :let keys in fact metadata are stripped out by fact-thunk in src/code/test/compile.clj and are not functional for binding in the test body.
  • Setup/Teardown: The correct way to handle per-test setup/teardown is using :setup and :teardown metadata keys, which can call helper functions.
  • Global State: fact:global can define :setup and :teardown for the entire namespace, but per-fact isolation requires explicit :setup/:teardown on the fact itself if not using the global ones.

std.scheduler.spawn

  • Runtime Management: Spawns are managed within a runtime atom.
  • Testing Spawns: Tests often require a runtime |rt| to be initialized.
  • Clear Operation: The clear function needed to be updated to also remove spawns from the :running map, not just :programs and :past.

lang.core Tests

  • Macro Expansion: defstruct.rs and other macros in lang.core.model.spec-rust work correctly in isolation, suggesting previous "Syntax error macroexpanding" issues might have been context-dependent or transient.
  • R Integration: lang.core.model.spec-r-test uses a guard lang.core.spec.r/CANARY. If this guard fails (returns false), the tests in that fact are skipped or fail with "Guard failed".

Foundation MCP Server

  • Server Location: The foundation MCP server is defined in code.ai.server within foundation-base.
  • Transport: By default, code.ai.server/create-server configures the server to use SSE transport on port 3001.
  • Tools:
    • echo, ping: Basic connectivity tests.
    • lang-emit-as: Transpiles Clojure DSL code to target languages (e.g., JS, Lua).
    • std-lang-list, std-lang-modules: Introspection for lang.core languages and modules.
    • clj-eval: Evaluates arbitrary Clojure code.
    • code-test: Runs tests using code.test.task/run.
    • code-doc-init, code-doc-deploy, code-doc-publish: Manages documentation sites.
    • code-manage: Executes management tasks defined in code.manage.
  • Stdio Support: While mcp-clj supports stdio transport (as seen in mcp-clj.stdio-server.main), code.ai.server currently hardcodes SSE. To use it via stdio, a custom entry point or modification to create-server would be required.

Read the full file on GitHub · 335 lines

Changes

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.

  1. 2d ago Changed · -29 tokens per session 171538d2e1da
  2. 7d ago First seen · 335 lines · 15,932 tokens per session scan A 3aa318edd8b1

Subscribe to this mod's changes

foundation-base GEMINI.md is an instructions file published in the GitHub repository zcaudate-xyz/foundation-base (42 stars, last pushed 3d ago), licensed MIT. It adds 15,903 tokens to every session, about $0.0795 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-02.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens