dev-mcp-skills: Instructions file for Codex

AGENTS.md

dev-mcp-skills AGENTS.md is an instructions file for Codex, OpenCode from appian/dev-mcp-skills. It costs 947 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for contributors to a skill that teaches coding agents how to build Appian applications. They cover Git workflow, writing style, file size, and organising reference material.

In plain words
What is it for?
Use them when editing this skill, preparing feature branches and pull requests, writing instructions, and deciding when to split large reference files.
Why use it?
They give contributors shared rules for making changes safely and keeping the skill clear and maintainable.

Instructions file for CodexOpenCode

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

This is appian/dev-mcp-skills's own configuration. It tells Codex and OpenCode how to work on dev-mcp-skills 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 dev-mcp-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to appian/dev-mcp-skills. 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/appian/dev-mcp-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/appian/dev-mcp-skills

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 dev-mcp-skills AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/appian/dev-mcp-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/appian/dev-mcp-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 947 This file is loaded in full into every session.
When invoked 947 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 $0.00947 $0.00947
Opus 5.5 $0.00379 $0.00379
Sonnet 5.5 $0.00189 $0.00189
Haiku 4.5 $0.00095 $0.00095

Measured 2mo ago against content hash a11e82c6b357, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dev-mcp-skills 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 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.

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 · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repository contains a skill that teaches AI coding agents how to build Appian applications. The skill content is domain knowledge — platform conventions, patterns, and gotchas — that the agent can't infer from tool schemas alone.

Git Workflow

  • Work on feature branches off main. Never commit directly to main.
  • Push to your fork only. Use pull requests to propose changes to the upstream repository.
  • Do not force push to any shared branch.
  • Do not amend commits that have already been pushed.

Content Principles

Sizing

  • SKILL.md should stay under 500 lines — it's always loaded when the skill triggers
  • Reference files can be longer but for files over 300 lines, include a table of contents at the top
  • If a reference is growing past useful size, split into focused files and add rows to the resource reference map

Writing style

  • Use imperative form for instructions
  • Explain why things matter rather than piling on MUSTs and NEVERs
  • Be concrete — show correct and incorrect examples
  • Stay general enough to apply across projects, not narrow to one specific scenario

Tool-agnostic references

All files under skills/appian/references/ (except tools-mcp.md) must be tool-agnostic:

  • Describe what to do, not which tool to call
  • No MCP tool names (e.g., createRecordType, addRecordTypeRelationship)
  • No CLI commands or flags
  • Use generic language: "create the record type", "list fields", "get the configuration"

Only references/tools-mcp.md may reference MCP tool names. It covers patterns and non-obvious behaviors — not a catalog of available tools (the MCP schema already provides that).

Don't duplicate tool metadata

The MCP tool schemas describe parameters, types, and return values. Reference files should cover what schemas cannot: conventions, patterns, gotchas, ordering constraints, and domain knowledge.

Skill content vs. tool issues

The skill teaches durable domain knowledge — patterns and conventions that are true regardless of tool implementation. Do not encode workarounds for tool bugs or limitations in the skill. If a failure is caused by the tool itself (e.g., validation behavior that doesn't match Appian Designer, missing support for an object type), file a GitHub issue with the tool-change-proposal label instead. See CONTRIBUTING.md for the issue format.

Read the full file on GitHub · 95 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. 2mo ago First seen · 95 lines · 947 tokens per session scan A a11e82c6b357

Subscribe to this mod's changes

dev-mcp-skills AGENTS.md is an instructions file published in the GitHub repository appian/dev-mcp-skills (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 947 tokens to every session, about $0.0038 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.

Related

dev-mcp-skills AGENTS.md compared with instructions from other repositories

dev-mcp-skills AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dev-mcp-skills AGENTS.mdappian/dev-mcp-skillsInstructions file131mo agoApache-2.0A947Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot