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/n-r-w/asteria/agents-mdgit clone --depth 1 https://github.com/n-r-w/asteriaWrote 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/n-r-w/asteria/agents-md)<a href="https://agentmods.dev/instructions/n-r-w/asteria/agents-md"><img src="https://agentmods.dev/badge/instructions/n-r-w/asteria/agents-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 | $0.01244 | $0.01244 |
| Opus 5 | $0.00622 | $0.00622 |
| Sonnet 5 | $0.00249 | $0.00249 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
asteria AGENTS.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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Specific Rules and Information
Project Overview
Symbolic(LSP) Search MCP Server. Designed for AI agents, not for humans.
Goal
- Provide LLM agents with the ability to efficiently and accurately navigate code, minimizing the number of tokens (file content reading).
- CRITICAL: No unnecessary "noise" in responses to the client. Only information that helps the LLM agent understand where the needed symbol is located, what it represents, and how to reach it.
Tech stack
- go 1.26
github.com/modelcontextprotocol/go-sdkfor MCP server implementationgithub.com/stretchr/testifyfor testsgo.uber.org/mock(no custom mocks,//go:generatedirectives in interface files)github.com/caarlos0/env/v11for loading configuration from environment variableslog/slogfor logging (must use structured logging with context). Use global logger with context, instead of passing logger instances around. E.g.slog.DebugContext.
Documentation
- How to implement a new LSP adapter:
docs/lsp-server-implementation-guide.md. MUST read before starting implementation. - Implementation of a similar service in python to identify patterns of working with various LSP adapters:
/Users/rvnikulenk/dev/nrw/serena/src/solidlsp/language_servers/. No need to copy algorithms from there, it's only for borrowing ideas and practical examples. Use it as well when problems arise with implementation, especially withinitialize_params.
MCP Tools
This server implements following tools:
get_symbols_overview: high-level understanding of the code symbols in a file. Returns information containing symbols grouped by kind in a compact format.find_symbol: retrieves information on all symbols/code entities (classes, methods, etc.) based on the given name path pattern. The returned symbol information can be used for edits or further queries.find_referencing_symbols: Finds references to the symbol. Returns metadata and code snippets around each reference.
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 · 76 lines · 1,244 tokens per session scan A 693d40ef656e
asteria AGENTS.md is an instructions file published in the GitHub repository n-r-w/asteria (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,244 tokens to every session, about $0.0062 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
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
nvim-mcp CLAUDE.md
Claude Code instructions for linw1995/nvim-mcp, covering claude.md, project overview, development commands, building and running and development build and run.
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
codescout CLAUDE.md
Claude Code instructions for mareurs/codescout, covering codescout, development commands, bug tracking, session intelligence trackers and querying active trackers (librarian).
rosetta command-versions-vs-presence.instructions.md
Instructions for tikoci/rosetta, a project described as: MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik.