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/naridon-inc/aura/gemini-mdgit clone --depth 1 https://github.com/Naridon-Inc/auraWrote 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/naridon-inc/aura/gemini-md)<a href="https://agentmods.dev/instructions/naridon-inc/aura/gemini-md"><img src="https://agentmods.dev/badge/instructions/naridon-inc/aura/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 | $0.00876 | $0.00876 |
| Opus 5 | $0.00438 | $0.00438 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
aura 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AURA SEMANTIC ENGINE — MANDATORY PROTOCOL FOR GEMINI CLI
You are Gemini (Google), running inside Gemini CLI. Model: Gemini 2.5 Pro Aura Version: v0.7.1 Integration: Shell commands + .gemini/hooks
YOU MUST USE AURA. THIS IS NOT OPTIONAL.
Aura is a semantic version control engine that tracks your code changes at the AST level. It catches bugs you miss, prevents accidental deletions, and mathematically verifies your work. Every command below exists to protect the codebase from AI mistakes — including yours.
BEFORE WRITING ANY CODE
-
Check semantic state
aura statusShows: logic nodes tracked, active session, checkpoints, strict mode status
-
Plan multi-file features (required when task touches 3+ files)
aura plan "Your objective here"Reviews gray areas, then:
aura executeExecutes wave-by-wave with AST verification after each wave
-
Verify existing logic paths
aura goal-trace "User can authenticate via OAuth"
WHILE WRITING CODE
-
Log intent before every commit
aura log-intent "Refactored retry_logic to use exponential backoff for rate limit compliance"The pre-commit hook compares your stated intent against actual AST changes. Mismatches are flagged as Intent Poisoning.
-
Review periodically
aura pr-review --base mainCatches: layer violations, security issues, architectural drift, accidental deletions
AFTER COMPLETING WORK
-
Final review
aura pr-review --base main --jsonFull semantic diff with AI-powered bug/security scanning. Fix violations before merging.
-
Prove the goal
aura goal-trace "The feature the user requested"
WHEN CONTEXT IS LARGE
- Generate handover
Produces a dense XML payload with full semantic state. Start a new session with this payload — saves ~90% of context tokens.aura handover gemini
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 · 117 lines · 876 tokens per session scan A 25364c134d95
aura GEMINI.md is an instructions file published in the GitHub repository Naridon-Inc/aura (45 stars, last pushed 14d ago), licensed Apache-2.0. It adds 876 tokens to every session, about $0.0044 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 2026-08-30.
Other instructions, from other repositories
substack-mcp AGENTS.md
AGENTS.md instructions for damienbenveniste/substack-mcp, covering agent instructions, project orientation, working style, delegation and external context and typescript tooling.
pointdev CLAUDE.md
Instructions for BraedenBDev/pointdev, covering claude.md, project, commands, architecture and key technical details.
ystack GEMINI.md
Gemini CLI instructions for Yasuui/ystack, covering gemini.md — ystack ⚡, this is the primary config file for antigravity ide, agents.md remains for compatibility with other tools, identity and subagent dispatch.
CTX copilot-instructions.md
Copilot instructions for Alegau03/CTX, a project described as: CTX - Context Runtime Engine for Coding Agents.
ystack AGENTS.md
AGENTS.md instructions for Yasuui/ystack, covering agents.md — ystack ⚡, 🏗️ who you are, ⚡ core operating principles, 🦾 autonomy and 🕵️♂️ agent roster.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.