Roslynk: Instructions file for Codex

AGENTS.md

Roslynk AGENTS.md is an instructions file for Codex, OpenCode from mrpmorris/Roslynk. It costs 9,238 tokens per session, scanned A, original, MIT.

A repository guide for working on Roslynk, a C# source-analysis project. It explains where the solution lives, which tools and workflow to use, and how to build and validate changes.

In plain words
What is it for?
Use it when changing Roslynk features or tools, inspecting C# and Razor code, tracing callers, running tests, and following the repository's build and lifecycle conventions.
Why use it?
It gives a coding agent the project-specific rules needed to avoid editing the wrong files, misusing analysis tools, or confusing the running service with the checked-out code.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is mrpmorris/Roslynk's own configuration. It tells Codex and OpenCode how to work on Roslynk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Roslynk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mrpmorris/Roslynk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mrpmorris/Roslynk/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mrpmorris/Roslynk

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for Roslynk AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mrpmorris/roslynk/agents-md/github.svg)](https://agentmods.dev/instructions/mrpmorris/roslynk/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mrpmorris/roslynk/agents-md"><img src="https://agentmods.dev/badge/instructions/mrpmorris/roslynk/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Roslynk AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mrpmorris/roslynk/agents-md"><img src="https://agentmods.dev/badge/instructions/mrpmorris/roslynk/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,238 This file is loaded in full into every session.
When invoked 9,238 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.09238 $0.09238
Opus 5.5 $0.03695 $0.03695
Sonnet 5.5 $0.01848 $0.01848
Haiku 4.5 $0.00924 $0.00924

Measured 3d ago against content hash 9b0337e1a931, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Roslynk 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 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.

AGENTS.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working on Roslynk

This is a source-based implementation guide for future changes. Paths below are relative to the repository root unless a section says otherwise. Re-check the affected implementation before changing it; this guide describes the architecture and its current limits, not a substitute for the source.

Start here

  • The solution is Source/Morris.Roslynk.slnx (not under Source/App).
  • Read git status before editing and preserve unrelated work.
  • When Roslynk is connected, use its semantic tools for compiled C#, Razor and CSHTML: open the solution, use get_members/get_symbol_body to inspect implementations, and use reference/caller queries for impact analysis. Follow skills/roslynk/SKILL.md for routing; each tool's contract lives in its C# method's [Description] attribute and is published in MCP metadata. Retry Indexing while loading; do not manually reload for ordinary source edits.
  • Batch related read-only questions with multi_query. Re-query after writes. A running Roslynk daemon can inspect edited source, but editing this repository does not replace the daemon's executing implementation; run tests against the checkout to validate new behavior.
  • Use normal file tooling for non-source configuration, documentation, and new-file creation. Roslynk's patch tool only edits existing files, and its plain-text fallback is rooted at the solution directory (Source), not the repository root.
  • The most important seams are RoslynInstance, SolutionModel, ApplyPipeline, AtomicFileWriter, SolutionFileSync, and the internal cores used by MultiQueryCatalog.

Required workflow for feature and tool changes

  • When creating a new read-only tool, assess whether it is a candidate for multi_query and ask the user whether to include it, unless the user's request already explicitly says to add the tool to multi_query (then include it without asking). Otherwise do not silently include or exclude it. Continue independent implementation work while that choice is pending; if included, implement the pinned-model core, catalog/enum integration and relevant tests described below.
  • Add every new feature and feature change to the # Unreleased section at the top of releases.md. Create that section at the top if it is missing, preserving existing release history. Each addition is a terse one-line bullet ending with (Fixes #xx), where xx is the GitHub issue number, e.g. - New `get_callees` tool: the inverse of `get_callers` (Fixes #58). Detail belongs in the skill/tool docs, not in releases.md. If the issue number is unknown, ask the user.
  • Documentation ownership: routing guidance lives in the roslynk skill (skills/roslynk/SKILL.md); shared workflows live in McpServerRegistration.Configure as MCP server instructions; each tool's complete contract lives in its C# method's [Description] attribute and is published in MCP metadata; parameter contracts stay in code as [Description] attributes on parameters, with identical parameter contracts reusing ParameterDescriptions. Server instructions carry shared conventions once; tool descriptions contain only their own contracts. When a tool's contract or behavior changes, update its method description in the same change (and SKILL.md when routing changes), and check for contradictory or obsolete copies of the guidance.

Read the full file on GitHub · 234 lines

Changes

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.

  1. 3d ago Changed · +2 tokens per session 9b0337e1a931
  2. 9d ago Changed · +103 tokens per session c3d4fa357f3b
  3. 10d ago Changed · +243 tokens per session abd69ffc482c
  4. 12d ago Changed · +6 lines · +649 tokens per session 8bad243881cc
  5. 13d ago Changed · +8 lines · +1,452 tokens per session 2a93b9dad9c8
  6. 15d ago Changed · +11 lines · +538 tokens per session 4637d4b35a69
  7. 27d ago First seen · 209 lines · 6,251 tokens per session scan A f27ad1fd1d37

Subscribe to this mod's changes

Roslynk AGENTS.md is an instructions file published in the GitHub repository mrpmorris/Roslynk (149 stars, last pushed today), licensed MIT. It adds 9,238 tokens to every session, about $0.0370 per session on Opus 5.5. 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 2026-09-26.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,549 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens