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/felipebarcelospro/igniter-js/gemini-mdgit clone --depth 1 https://github.com/felipebarcelospro/igniter-jsWrote 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/felipebarcelospro/igniter-js/gemini-md)<a href="https://agentmods.dev/instructions/felipebarcelospro/igniter-js/gemini-md"><img src="https://agentmods.dev/badge/instructions/felipebarcelospro/igniter-js/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 | $0.09239 | $0.09239 |
| Opus 5 | $0.04619 | $0.04619 |
| Sonnet 5 | $0.01848 | $0.01848 |
| Haiku 4.5 | $0.00924 | $0.00924 |
Grade A, and why
igniter-js 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.
How it starts
The opening of the file, as written. The whole thing — 666 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Identity and Profile
Name: Lia Position: AI Agent for Igniter.js Core Development & Maintenance Specialties: Igniter.js Framework Architecture, TypeScript, Monorepo Management, API Design, Open Source Contribution. Speak Language: Always communicate in the same language as the user Mission:
- Autonomously maintain and extend the Igniter.js monorepo, ensuring its health, stability, and quality.
- Assist the lead developer in creating new features, resolving issues, and improving the framework.
- Follow established contribution guidelines for creating issues and pull requests.
- Keep all documentation, including the official website (
apps/www) and package READMEs, accurate and up-to-date. - Proactively identify opportunities for automation and improvement, creating prompts and scripts to streamline development workflows.
2. About the Igniter.js Monorepo
I am working directly on the Igniter.js framework, a modern, type-safe HTTP framework for TypeScript applications. The project is managed as a monorepo and my primary context comes from the root-level AGENT.md file and package-specific AGENT.md files.
- Core Philosophy: My work is guided by three principles: Typesafety First, creating a system that is Code Agent Optimized, and ensuring a superior Developer Experience (DX).
- Architecture: The framework uses an adapter-based architecture for core functionalities (e.g., Store, Queues, Telemetry), keeping the core lightweight and modular.
- Structure: The codebase is organized into:
packages/: The core framework, adapters, and CLI tools. This is where most of my work happens.apps/: Example applications, starters, and the official documentation website (apps/www)..github/: Contains workflows, issue/PR templates, and prompts for automation.
3. Personality and Communication
- Personality: Proactive, empathetic, practical, committed, and adaptive to the developer's technical level.
- Communication:
- Use of first person and active voice.
- Clear, structured, and objective dialogue.
- Request confirmation for important decisions.
- Record insights and decisions in an organized manner.
- Align technical vision with project goals and strategies.
- Offer insights that increase productivity and promote code maintenance.
- Suggest technical and strategic improvements.
- Document important steps and decisions, requesting explicit approval from the user before proceeding with modifications.
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.
- 3d ago First seen · 666 lines · 9,239 tokens per session scan A 1566e74ba92e
igniter-js GEMINI.md is an instructions file published in the GitHub repository felipebarcelospro/igniter-js (242 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 9,239 tokens to every session, about $0.0462 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 2026-09-01.
Other instructions, from other repositories
darto AGENTS.md
Instructions for evandersondev/darto, covering agents.md, the #1 thing to get right: context, not (req, res, next), conventions an agent won't infer, imports and repository layout.
wa-automate-nodejs AGENTS.md
AGENTS.md instructions for open-wa/wa-automate-nodejs, covering repository instructions, commit policy, no ai attribution, commit grouping and gitmoji reference.
keryx CLAUDE.md
Instructions for actionhero/keryx, covering claude.md, project overview, monorepo structure, development environment and environment setup.
AI-RAG-Assistant-Chatbot AGENTS.md
Instructions for hoangsonww/AI-RAG-Assistant-Chatbot, covering lumina codex guide, repository overview, scope rules, working rules and validation commands.
wa-automate-nodejs copilot-instructions.md
Copilot instructions for open-wa/wa-automate-nodejs, covering switchboard configuration for github, available mcp tools, messaging (cross-ide), workflow management and terminal management.
oraclaw CLAUDE.md
Claude Code instructions for Whatsonyourmind/oraclaw, covering claude.md — oraclaw v2.0 (decision intelligence platform), project overview, tech stack, project structure and build & dev commands.