XRefkit.MCP AGENTS.md

Project instructions for working with the XRefKit.MCP repository and its governance documents. They require reading specific startup guidance and retrieving linked documents before using the MCP server.

In plain words
What is it for?
Use them when working through XRefKit.MCP to load startup context, resolve linked documents, and follow the repository's instructions.
Why use it?
They ensure the agent follows the repository's own definitions and startup process instead of inventing rules. This is important when the project has formal terms for evidence, risk, escalation, and handoff.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/synthaicode/xrefkit.mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/synthaicode/XRefkit.MCP

Made for: Codex, OpenCode.

Per session 244 This file is loaded in full into every session.
When invoked 244 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00244 $0.00244
Opus 5 $0.00122 $0.00122
Sonnet 5 $0.00049 $0.00049
Haiku 4.5 $0.00024 $0.00024

Measured 2d ago against content hash b5e04e93ecae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

XRefkit.MCP 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 2d 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 · 28 lines

What it actually says

Personal Codex instruction

This user works with XRefKit-style repository governance.

At session start, follow the repository-defined loading process and treat loaded AGENTS.md, Skills, knowledge, workflow definitions, and governance labels as authoritative.

Do not redefine XRefKit concepts such as unknown, risk, judgment, escalation, evidence, handoff, or skill routing in global custom instructions. Use the repository definitions.

Global instructions should only control:

  • concise communication
  • progress visibility
  • explicit summary of changes
  • explicit list of unverified items
  • respect for repository-defined stop-and-escalate rules

If a required rule is missing, do not invent a project rule. Mark it as missing and suggest whether it belongs in AGENTS.md, a Skill, knowledge, or workflow definition.

--- project-doc ---

AGENTS Startup (XRefKit MCP)

As your first action, read the MCP startup contract below:

  • README.md#ai-client-instruction-template
  • README.md#required-client-startup-flow

When working against an XRefKit repository through this MCP server, call get_startup_context first and resolve XID-linked documents with get_document_by_xid.

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. 2d ago First seen · 28 lines · 244 tokens per session scan A b5e04e93ecae

Subscribe to this mod's changes

XRefkit.MCP AGENTS.md is an instructions file published in the GitHub repository synthaicode/XRefkit.MCP (0 stars, last pushed 1mo ago), licensed MIT. It adds 244 tokens to every session, about $0.0012 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.