agentmods.dev

kontexta: Instructions file for Gemini CLI

GEMINI.md

kontexta GEMINI.md is an instructions file for Gemini CLI from safiyu/kontexta. It costs 649 tokens per session, scanned A, original, Apache-2.0.

Project instructions for using Kontexta, a knowledge-base and journal system, with the Gemini command-line tool. They define how to load user context, search stored files, and save knowledge or journal entries.

In plain words
What is it for?
Use them when working on the Kontexta project to refresh session context, read user profiles, search and read knowledge files, and create or update stored project knowledge.
Why use it?
They reduce the risk of reading guessed files or writing knowledge directly into the code repository. They also establish a required session-start routine and rules for handling suggested journal actions.

Instructions file for Gemini CLI

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

This is safiyu/kontexta's own configuration. It tells Gemini CLI how to work on kontexta 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 kontexta configures →

not rated 1repo changed 14d ago A scan 649 tokens original Apache-2.0
View source ↗ safiyu/kontexta
Reuse

Borrowing it

Nothing to install: this file belongs to safiyu/kontexta. 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/safiyu/kontexta/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/safiyu/kontexta

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 kontexta GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/safiyu/kontexta/gemini-md/github.svg)](https://agentmods.dev/instructions/safiyu/kontexta/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/safiyu/kontexta/gemini-md"><img src="https://agentmods.dev/badge/instructions/safiyu/kontexta/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 kontexta GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/safiyu/kontexta/gemini-md"><img src="https://agentmods.dev/badge/instructions/safiyu/kontexta/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 649 This file is loaded in full into every session.
When invoked 649 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 $0.00649 $0.00649
Opus 5.5 $0.00260 $0.00260
Sonnet 5.5 $0.00130 $0.00130
Haiku 4.5 $0.00065 $0.00065

Measured 14d ago against content hash a8be28a7bcda, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kontexta 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 14d 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 · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kontexta

Kontexta - AI knowledge base and project context management system

Working with kontexta

This project uses kontexta for context, knowledge, and journal management. Tools live under the kxta MCP server.

Core constraints:

  • Session start: Call admin_refresh_session_context on turn 1; print a 1–3 line greeting (date, profile, conflicts). Skip if the user's first message is a task.
  • User profile: Call admin_get_profile to read user context, role, preferences, and goals.
  • All KB writes go through kontexta. Use files_create / files_update / journal_write. Never edit KB files with raw filesystem tools. Never write context artifacts (diagrams, specs, notes, .mmd files) directly into the project repo — use files_create with destination: "knowledge".
  • Search before reading. Use files_search (no bodies first; include_bodies only for several files at once, with a small max_tokens) or files_regex_search, then files_read the top hit, not a guessed path.
  • Act on journal.suggested_action before your next tool call, or pass journal_acknowledge: true to dismiss.
  • Tag new KB files at creation time via tags on files_create or tags_add.
  • Use .mmd for diagrams via files_create with format: "mmd", destination: "knowledge". Never fenced mermaid in .md, never .mmd files in the project repo.
  • Confirm Hands tokens within 60 seconds. Tokens expire.
  • Log decisions with journal_write({kind: "note"}) and topic pivots with journal_write({kind: "intent"}).
  • Relay hooks prompts once per session when present in tool responses.

Strict folder structure in Knowledge Base: All context artifacts must strictly follow this folder hierarchy inside the Knowledge Base (destination: "knowledge"):

  • HTML reports: html/ (use files_create with format: "html", destination: "knowledge")
  • Mermaid diagrams (.mmd): mermaid/ (use files_create with format: "mmd", destination: "knowledge")
  • Journals: journal/ (managed via journal_write / journal_distill)
  • Knowledge Base files: knowledge/dictionary/ (kind: "dictionary" for sources of truth) or knowledge/notes/ (kind: "note" for working notes & snapshots) Never write context or diagram files directly into the project repository.

Read the full file on GitHub · 32 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. 14d ago Changed a8be28a7bcda
  2. 23d ago First seen · 32 lines · 649 tokens per session scan A 85624d7d1b50

Subscribe to this mod's changes

kontexta GEMINI.md is an instructions file published in the GitHub repository safiyu/kontexta (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 649 tokens to every session, about $0.0026 per session on Opus 5.5. 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 2026-10-06.

Building agentsProject management
Related

Other instructions, from other repositories

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 · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 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 · 4,261 tokens