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/arnaudgelas/k-ops/gemini-mdgit clone --depth 1 https://github.com/arnaudgelas/K-OpsWrote 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/arnaudgelas/k-ops/gemini-md)<a href="https://agentmods.dev/instructions/arnaudgelas/k-ops/gemini-md"><img src="https://agentmods.dev/badge/instructions/arnaudgelas/k-ops/gemini-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 5.1 | $0.00818 | $0.00818 |
| Opus 5 | $0.00409 | $0.00409 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
K-Ops 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 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md
This repository is an Obsidian-aligned living research vault. The same operating contract should work whether the active CLI is Claude Code, Codex CLI, or Gemini CLI/Antigravity (agy).
Canonical rules: see OPERATING_RULES.md. This file adds Gemini-specific and Antigravity (agy) CLI overrides.
Gemini-Specific Notes
- Use
uv run kops compile --agent gemini(or the/compilecommand inagy) for wiki compilation passes. - Use
uv run kops heal --agent gemini(or the/healcommand inagy) for structural repair and linting. - Use
uv run kops validateto confirm config before running workflows. - Use
uv run kops install-agent-assets --agent geminito sync skills and commands to the Gemini/agyruntime directory. - Grounding via Google Search is available — prefer vault-first answers, use web grounding only for missing evidence.
Mission
Turn raw sources into a durable Markdown knowledge base. Every answer should either:
- reference existing vault notes, or
- improve the vault if durable new knowledge was produced.
Operating rules
- Treat
data/raw/as immutable source evidence. - Treat
notes/as the curated Obsidian vault. - Treat
research/as the active run workspace for resumable research jobs, not as a substitute for the curated vault. - Prefer updating existing concept pages instead of creating duplicates.
- Keep always-on instructions short; move command detail into runbooks, skills, or templates.
- Every concept page should link to related pages and relevant source summaries.
- Record contradictions, uncertainties, and missing evidence explicitly.
- Do not silently invent citations.
- Treat imported model-generated reports as leads that must be verified against primary sources before they can shape concept pages.
- If a question cannot be answered from the vault, say so and propose the minimum fetch needed.
Default workflow
- Read relevant source summaries in
notes/Sources/. - Read the linked concept pages in
notes/Concepts/. - Use
notes/Runbooks/Agent_Workflow_Quick_Reference.mdwhen you need command syntax or command order. - Answer from the vault.
- If the answer yields durable knowledge, file it back into the vault.
- Run
heal(uv run kops heal --agent geminior the/healcommand inagy) after structural edits. - Update
notes/Home.mdandnotes/TODO.mdwhen the vault's structure or gaps change.
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 · 76 lines · 818 tokens per session scan A 53e966e601d6
K-Ops GEMINI.md is an instructions file published in the GitHub repository arnaudgelas/K-Ops (1 stars, last pushed 17d ago), licensed MIT. It adds 818 tokens to every session, about $0.0041 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
BITE AGENTS.md
Instructions for RipeMangoBox/BITE, covering agent guide, working surface, local pipeline, branch sync policy and rules.
open-llm-wiki AGENTS.md
Instructions for AIwork4me/open-llm-wiki, covering agents.md, project scope, hard rules, repo map and before submitting changes.
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
obsidian-wiki AGENTS.md
AGENTS.md instructions for Ar9av/obsidian-wiki, covering obsidian wiki — agent context, readme translation parity, configuration, targeting a specific vault and vault structure.