Xolotl-Code AGENTS.md

Project instructions for Xolotl-Code, including its code knowledge graph and configuration for connecting to several AI model providers.

In plain words
What is it for?
Use them when answering Xolotl-Code architecture questions, changing its code, updating its knowledge graph, or configuring supported AI models.
Why use it?
They tell a coding agent where to look for architecture information and which settings and environment variables control the model connections.

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/cesarfrancots/xolotl-code/agents-md
Clone the repo
git clone --depth 1 https://github.com/cesarfrancots/Xolotl-Code

Made for: Codex, OpenCode.

Per session 854 This file is loaded in full into every session.
When invoked 854 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 $0.00854 $0.00854
Opus 5 $0.00427 $0.00427
Sonnet 5 $0.00171 $0.00171
Haiku 4.5 $0.00085 $0.00085

Measured 3d ago against content hash 03d152f930c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Xolotl-Code 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

graphify

This project has a graphify knowledge graph at graphify-out/.

Rules:

  • Before answering architecture or codebase questions, read graphify-out/GRAPH_REPORT.md for god nodes and community structure
  • If graphify-out/wiki/index.md exists, navigate it instead of reading raw files
  • After modifying code files in this session, run graphify update . to keep the graph current (AST-only, no API cost)

Model Harness Configuration

Supported Models

Alias Provider Endpoint Context Thinking
kimi-coding Kimi Coding api.kimi.com/coding/v1 256K Yes (32K budget)
kimi2.6 Moonshot api.moonshot.cn/v1 256K Yes
minimax2.7 MiniMax api.minimax.chat/v1 1M Yes
deepseek DeepSeek api.deepseek.com 1M Yes
glm5.1 Zhipu GLM open.bigmodel.cn/api/paas/v4 128K Yes
qwen3.6 Alibaba Qwen dashscope.aliyuncs.com/compatible-mode/v1 128K Yes
sonnet AWS Bedrock bedrock-runtime.us-east-1.amazonaws.com 200K Yes
opus AWS Bedrock bedrock-runtime.us-east-1.amazonaws.com 200K Yes

Environment Variables

  • KIMI_CODING_API_KEY - Kimi K2.6 Coding API (coding-optimized model)
  • KIMI_API_KEY - Standard Kimi / Moonshot API
  • MINIMAX_API_KEY - MiniMax API
  • DEEPSEEK_API_KEY - DeepSeek API
  • GLM_API_KEY - Zhipu GLM API
  • DASHSCOPE_API_KEY - Alibaba Qwen API
  • ANTHROPIC_API_KEY - Anthropic direct API
  • BEDROCK_API_KEY - AWS Bedrock API key

Model-Specific Behavior

Kimi K2.6 Coding:

  • Uses extended thinking with 32K budget
  • Optimized system prompt for software engineering tasks
  • Aggressive file reading (threshold: 12 files)
  • Higher compaction ratio (0.7) due to 256K context

MiniMax 2.7:

  • 1M token context - most generous for large codebases
  • Aggressive file reading (threshold: 10 files)
  • Prefers comprehensive initial research

DeepSeek V4:

  • 1M token context
  • Thinking mode enabled by default; max effort is available
  • Good fit for chat, evals, and agentic coding tasks

Read the full file on GitHub · 90 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 First seen · 90 lines · 854 tokens per session scan A 03d152f930c1

Subscribe to this mod's changes

Xolotl-Code AGENTS.md is an instructions file published in the GitHub repository cesarfrancots/Xolotl-Code (5 stars, last pushed 2mo ago), licensed MIT. It adds 854 tokens to every session, about $0.0043 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.