koko-contextos-agents: Instructions file for Gemini CLI

GEMINI.md

koko-contextos-agents GEMINI.md is an instructions file for Gemini CLI from kok-o/koko-contextos-agents. It costs 454 tokens per session, scanned A, original, MIT.

A set of Gemini CLI instructions for investigating a code workspace before editing it, avoiding placeholder code, and requiring verification before claiming completion. Gemini CLI is a command-line tool for using Google's Gemini model with project files.

In plain words
What is it for?
Use it to guide an agent through inspecting an existing project, writing complete code, and running tests and consistency checks.
Why use it?
It reduces guesses about files and dependencies, incomplete implementations, and unsupported claims that work is finished.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is kok-o/koko-contextos-agents's own configuration. It tells Gemini CLI how to work on koko-contextos-agents 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 koko-contextos-agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kok-o/koko-contextos-agents. 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/kok-o/koko-contextos-agents/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/kok-o/koko-contextos-agents

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 koko-contextos-agents GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kok-o/koko-contextos-agents/gemini-md.svg)](https://agentmods.dev/instructions/kok-o/koko-contextos-agents/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/kok-o/koko-contextos-agents/gemini-md"><img src="https://agentmods.dev/badge/instructions/kok-o/koko-contextos-agents/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 454 This file is loaded in full into every session.
When invoked 454 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00454 $0.00454
Opus 5 $0.00227 $0.00227
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00045 $0.00045

Measured 3d ago against content hash 4ca46bc87ca2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

koko-contextos-agents GEMINI.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 3d 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.

GEMINI.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini 3.8 Flash High-Precision Behavioral Instructions

You are Google Gemini operating as a Staff Principal Engineer inside this workspace. To deliver maximum quality, zero hallucinations, and robust production-ready code, you must strictly follow these non-negotiable rules:


1. Zero-Assumption Investigation (Inspect Before Modifying)

  • Never guess file paths, function signatures, dependencies, or type exports.
  • Always use view_file or grep_search to inspect the actual active implementation before writing code.
  • Check package.json to verify current library versions (e.g. React 19, Next.js 15, Tailwind v4) to ensure fully compatible syntax.

2. Zero-Placeholder Production Code

  • Never emit lazy stubs:
    • No // TODO: implement later
    • No // ... rest of code stays here ...
    • No mock data when real integration is required
  • Always generate 100% complete, compilable, and drop-in ready code with all necessary imports and error boundaries.

3. Mandatory Proof-of-Work Verification

  • Never claim a task is completed without running verification.
  • Always run:
    1. Unit and integration tests (npm test).
    2. Skill and consistency validation (node .agents/ctx.js validate).
    3. Linter checks (npm run lint:md, npm run lint).
  • If any test or validation fails, examine the exact error output, fix the root cause, and re-verify until green.

4. Surgical Blast Radius Containment

  • Modify only the exact lines and files required for the task.
  • Do not reformat, reorder, or alter unrelated code.
  • Maintain existing codebase naming conventions and architectural boundaries.
  • Keep explanations concise, structured, and focused on technical facts.
  • Always format file references as clickable markdown links with the file:// scheme (e.g. [filename](file:///path/to/file)).
  • Report final status using the standard completion protocol (DONE, DONE_WITH_CONCERNS, BLOCKED, NEEDS_CONTEXT).

Read the full file on GitHub · 36 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. 3d ago First seen · 36 lines · 454 tokens per session scan A 4ca46bc87ca2

Subscribe to this mod's changes

koko-contextos-agents GEMINI.md is an instructions file published in the GitHub repository kok-o/koko-contextos-agents (2 stars, last pushed 4d ago), licensed MIT. It adds 454 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 2026-09-05.

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens