agentmods.dev

McpServer: Instructions file for Codex

AGENTS.md

McpServer AGENTS.md is an instructions file for Codex, OpenCode from sharpninja/McpServer. It costs 2,015 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for an MCP server, a service that lets coding agents call registered tools through a shared protocol. They define how agents should start work, follow source files, and record session changes.

In plain words
What is it for?
Use them when contributing to the repository, especially when bootstrapping a session, following prompt templates, calling helper modules, and updating the session log after meaningful work.
Why use it?
They prevent agents from using outdated instructions, making raw API calls, or losing important decisions and file changes between work sessions.

Instructions file for CodexOpenCode

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

This is sharpninja/McpServer's own configuration. It tells Codex and OpenCode how to work on McpServer 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 McpServer configures →

not rated 5repo changed 21d ago A scan 2,015 tokens original Apache-2.0
View source ↗ sharpninja/McpServer sharpninja.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to sharpninja/McpServer. 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/sharpninja/McpServer/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/sharpninja/McpServer

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 McpServer AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sharpninja/mcpserver/agents-md/github.svg)](https://agentmods.dev/instructions/sharpninja/mcpserver/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sharpninja/mcpserver/agents-md"><img src="https://agentmods.dev/badge/instructions/sharpninja/mcpserver/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 McpServer AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sharpninja/mcpserver/agents-md"><img src="https://agentmods.dev/badge/instructions/sharpninja/mcpserver/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,015 This file is loaded in full into every session.
When invoked 2,015 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 $0.02015 $0.02015
Opus 5.5 $0.00806 $0.00806
Sonnet 5.5 $0.00403 $0.00403
Haiku 4.5 $0.00201 $0.00201

Measured 21d ago against content hash da41bc2b2e4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

McpServer 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 21d 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 · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Session Start

  1. Read AGENTS-README-FIRST.yaml in the repo root for the current API key and endpoints.
  2. For specific operational steps (session bootstrap, session log turn workflow, and helper command sequence), follow AGENTS-README-FIRST.yaml.

On every subsequent user message:

  1. Follow AGENTS-README-FIRST.yaml for specific operational instructions.
  2. Complete the user's request.

Rules

  1. templates/prompt-templates.yaml (default-marker-prompt) is the source of truth for specific agent instructions. AGENTS-README-FIRST.yaml is the rendered runtime instruction set.
  2. Keep this file focused on durable workspace policy and conventions; avoid duplicating marker-file operational procedures.
  3. Use helper modules for session log and TODO operations. Do not make raw API calls.
  4. Persist session log updates immediately after each meaningful change (turn creation, action append, decision, requirement, blocker, file/context update). Do not defer saves.
  5. Capture rich turn detail: interpretation, response, status, actions (type/status/filePath), contextList, filesModified, designDecisions, requirementsDiscovered, blockers, and relevant processing dialog.
  6. Follow workspace conventions in .github/copilot-instructions.md for build, test, and architecture guidance.
  7. Use only pwsh.exe for shell commands and script execution; do not use powershell.exe.
  8. When you need API schemas, module examples, or compliance rules, load them from docs/context/ or use context_search.
  9. Do not fabricate information. If you made a mistake, acknowledge it. Distinguish facts from speculation.
  10. Prioritize correctness over speed. Do not ship code you have not verified compiles and is logically sound.
  11. When writing session logs or other audit records, agents must identify themselves accurately using their real agent identity in Pascal-Case. Do not use placeholder, legacy, or misleading sourceType values.
  12. Never edit YAML by appending, replacing, or removing text lines. Deserialize the complete document into an object, mutate the object, serialize it, and save it. Use plugins/core/lib-ps/yaml-object-mutation.ps1 for PowerShell work.

Read the full file on GitHub · 156 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. 21d ago Changed · +1 lines · +22 tokens per session da41bc2b2e4b
  2. 2mo ago First seen · 155 lines · 1,993 tokens per session scan A 18a62a877a6d

Subscribe to this mod's changes

McpServer AGENTS.md is an instructions file published in the GitHub repository sharpninja/McpServer (5 stars, last pushed today), licensed Apache-2.0. It adds 2,015 tokens to every session, about $0.0081 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 2026-08-31.

ai-agentsai-mcpai-tools
Related

McpServer AGENTS.md compared with instructions from other repositories

McpServer AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
McpServer AGENTS.mdsharpninja/McpServerInstructions file5todayApache-2.0A2,015Codex, OpenCode
vibetags com-example-config-AsyncTestConfig.instructions.mdPIsberg/vibetagsInstructions file25yesterdayMITA82GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot