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/sarutobisasuke8/agentops-template/gemini-mdgit clone --depth 1 https://github.com/SarutobiSasuke8/agentops-templateWrote 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/sarutobisasuke8/agentops-template/gemini-md)<a href="https://agentmods.dev/instructions/sarutobisasuke8/agentops-template/gemini-md"><img src="https://agentmods.dev/badge/instructions/sarutobisasuke8/agentops-template/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 | $0.00465 | $0.00465 |
| Opus 5 | $0.00233 | $0.00233 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
agentops-template 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 4d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md - Gemini Coding Contract
Canonical source: AGENTS.md
Gemini must follow AGENTS.md. This file holds Gemini-specific guidance only; the principles, operating loop, commands, and handoff standard live in AGENTS.md.
Alignment Markers
Gemini is bound by all five principles defined in AGENTS.md:
- Think Before Coding — read
docs/PROJECT_BRIEF.mdandROADMAP.md; state assumptions and uncertainty. - Simplicity First — recommend the simplest verifiable path; avoid premature architecture.
- Surgical Changes — keep recommendations and edits scoped to the request; do not rewrite project direction unprompted.
- Goal-Driven Execution — convert broad asks into decisions, acceptance checks, and slices with verification at each milestone.
- Vibe Coding Quality Bar — protect tone, accessibility, and failure-state coverage; copy stays specific.
Required Workflow
- Read project context (
AGENTS.md,docs/PROJECT_BRIEF.md, relevant code). - Define the decision or outcome needed.
- Compare viable options and recommend one.
- Convert the recommendation into concrete tasks or changes.
- Hand off with evidence, verification, and open questions.
- Append a session log under
Session Logs/when analysis changes project direction, usingTemplates/SESSION_LOG_TEMPLATE.md.
Gemini-Specific Emphasis
- Long-context discipline. When given a large context window, summarize and cite the specific files/sections you used; do not let "I read everything" become a substitute for naming what mattered.
- Analysis vs execution. Strong on tradeoffs and synthesis — but do not let analysis become the deliverable when the user asked for a change.
- Confidence on volatile facts. Mark externally sourced or fast-changing facts with confidence; separate verified from assumed.
- Research mode. When researching, return primary sources and dates, not vibes.
- Drift check. After editing any agent doc, run
./scripts/check-agent-docs.sh(or the.ps1twin on Windows).
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.
- 4d ago First seen · 40 lines · 465 tokens per session scan A cfe055c3b7c8
agentops-template GEMINI.md is an instructions file published in the GitHub repository SarutobiSasuke8/agentops-template (9 stars, last pushed 15d ago), licensed MIT. It adds 465 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 2026-08-31.
Other instructions, from other repositories
agentic-code AGENTS.md
Instructions for shinpr/agentic-code, covering agents.md, goal, operating boundaries, session setup and task routing.
agentic-workstation AGENTS.md
Instructions for ulises-jeremias/agentic-workstation, covering ai agent guidelines for agentic-workstation, purpose, core principles, script standards and naming and structure.
agentic-workstation CLAUDE.md
Instructions for ulises-jeremias/agentic-workstation, a project described as: AI-native workstation provisioning layer — chezmoi, host policies and tooling that installs/configures Agent Toolkit across modern coding agents.
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.