What is Malon_mcp AGENTS.md?

A project guide for AI coding assistants working on the Malon MCP codebase. It explains the project's purpose, installed agent skills, and required workflows for development, debugging, review, and testing.

Use it when adding features, fixing bugs, reviewing code, refactoring, or following the repository's debugging, testing, and security procedures.

It gives the assistant the project's rules and known safeguards before it changes code, reducing the risk of skipping required checks.

How malon-mcp/Malon_mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to malon-mcp/Malon_mcp. 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/malon-mcp/Malon_mcp/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/malon-mcp/Malon_mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/malon-mcp/malon_mcp/agents-md/github.svg)](https://agentmods.dev/instructions/malon-mcp/malon_mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/malon-mcp/malon_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/malon-mcp/malon_mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/malon-mcp/malon_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/malon-mcp/malon_mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33,970 This file is loaded in full into every session.

When invoked 33,970 The same file — it is already loaded in full.

Security scan D 3 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.

Model	Per session	Once invoked
Fable 5.1	$0.33970	$0.33970
Opus 5.5	$0.13588	$0.13588
Sonnet 5.5	$0.06794	$0.06794
Haiku 4.5	$0.03397	$0.03397

Measured 2mo ago against content hash b835f7d8304e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

Malon_mcp AGENTS.md scanned grade D with 3 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 2mo 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

the Subagent: lines starting with "Ignore previous instructions," "System:",

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`rm -rf .malon/memory/` and start over. This is the trust feature as much

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { execFile } from 'node:child_process';

AGENTS.md · 3,157 lines

How it starts

The opening of the file, as written. The whole thing — 3,157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

The operating manual for the AI coding agent working inside the Malon codebase. Read this in full on your first session. Re-read §7 (Security), §19 (Common Tasks), and §20 (Debugging Playbook) before every non-trivial change.

If anything here conflicts with a direct instruction from the founder, the founder's instruction wins — but flag the conflict out loud before obeying, because most of this file exists precisely to prevent known-bad patterns from creeping back in.

Agent Skills (addyosmani/agent-skills)

24 production-grade engineering skills are installed from addyosmani/agent-skills. They are auto-discovered by the skill tool from .opencode/skills/ and ~/.config/opencode/skills/.

When a task matches a skill, you MUST load and follow it. Skills enforce structured workflows (spec → plan → build → test → review → ship) with verification gates at every step. Do not skip to implementation directly.

Feature / new functionality → load spec-driven-development, incremental-implementation, test-driven-development
Bug / failure / unexpected behavior → load debugging-and-error-recovery
Code review → load code-review-and-quality
Refactoring / simplification → load code-simplification
API or interface design → load api-and-interface-design
UI work → load frontend-ui-engineering
Security review → load security-and-hardening
Performance work → load performance-optimization
Ship / deploy → load shipping-and-launch
Multi-step reasoning / complex problem solving → load chain-of-thought
Exploration with branching / multiple hypotheses → load tree-of-thoughts
Self-correction / learning from failures → load reflexion

Load a skill via the skill tool: skill({ name: "code-review-and-quality" }). Always follow the skill instructions exactly.

⚡ Auto-loaded skills (load on every session start)

On session start, you MUST call skill() for each of these before any other work:

Read the full file on GitHub · 3,157 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.

2mo ago First seen · 3,157 lines · 33,970 tokens per session scan D b835f7d8304e

Subscribe to this mod's changes

Malon_mcp AGENTS.md is an instructions file published in the GitHub repository malon-mcp/Malon_mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 33,970 tokens to every session, about $0.1359 per session on Opus 5.5. A static security scan graded it D with 3 findings (instruction-override phrasing, recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Malon_mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Malon_mcp AGENTS.mdmalon-mcp/Malon_mcp	Instructions file	2	3mo ago	MIT	D	33,970	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Malon_mcp: Instructions file for Codex