mcp-homelab agent-workflow.instructions.md

mcp-homelab agent-workflow.instructions.md is an instructions file for GitHub Copilot from asvarnon/mcp-homelab. It costs 513 tokens per session, scanned A, original, MIT.

A set of workflow instructions for an AI coding agent working on the mcp-homelab project. It defines what to read at the start of a session, what notes to record, and what to check before releasing or publishing changes.

In plain words
What is it for?
Use it to start sessions, read prior notes, record significant actions, preserve permanent findings, and follow release or publication procedures.
Why use it?
It keeps project context and decisions from being lost between sessions. It also makes release work more consistent by requiring relevant versioning and checklist steps.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt. Also seen: mentions Codex.

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/asvarnon/mcp-homelab/agent-workflow
Clone the repo
git clone --depth 1 https://github.com/asvarnon/mcp-homelab

Made for: GitHub Copilot.

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 mcp-homelab agent-workflow.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/asvarnon/mcp-homelab/agent-workflow.svg)](https://agentmods.dev/instructions/asvarnon/mcp-homelab/agent-workflow)
Your own site
<a href="https://agentmods.dev/instructions/asvarnon/mcp-homelab/agent-workflow"><img src="https://agentmods.dev/badge/instructions/asvarnon/mcp-homelab/agent-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 513 This file is loaded in full into every session.
When invoked 513 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 5.1 $0.00513 $0.00513
Opus 5 $0.00257 $0.00257
Sonnet 5 $0.00103 $0.00103
Haiku 4.5 $0.00051 $0.00051

Measured 5d ago against content hash 9b26d2a1f70b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-homelab agent-workflow.instructions.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 5d 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.

.github/instructions/agent-workflow.instructions.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Workflow Instructions

These rules apply to every interaction in this workspace. They are non-negotiable and override default agent behavior.

Session Start (do this before anything else)

  1. Run memory view /memories/session/ to list session files
  2. Read the most recent session file relevant to the current task before taking any action
  3. Read /memories/repo/versioning.md before any release, deployment, or version-related work
  4. Only then proceed with the user's request

Session Notes (during the session)

  • Write to /memories/session/ after each significant action — not at the end
  • Use one rolling file per topic/task (e.g., session-v1.5.0.md, dhcp-backend.md)
  • Record: decisions made, files modified, commands run, open questions, pending steps
  • If a session file for the current topic already exists, update it — don't create a duplicate

Promote Findings Immediately

  • When something permanent is discovered (a correct process, a wrong assumption, a repo convention), write it to /memories/repo/ or /memories/user-preferences.md immediately — not at end of session
  • Do not rely on session compaction to preserve important facts

Release / Publish Checklist

Before any PyPI publish, package build, or version tag operation:

  1. Check .github/workflows/ for an existing release workflow
  2. If a workflow exists: push a vX.Y.Z tag — the workflow handles everything
  3. NEVER run twine upload or python -m build + upload directly — this bypasses Trusted Publishing and triggers a PyPI security warning
  4. The publish workflow (publish-release.yml) has skip-existing: true — re-tagging is safe

Code Authorship

  • NEVER write or edit Python code directly — always delegate to Codex Agent via runSubagent
  • This includes: new files, edits to existing Python files, test files, config changes in Python projects
  • Orchestrator role only: plan, scope, review, validate tests, manage git

Git Workflow

  • Feature/fix branches only → PR → merge
  • NEVER push directly to master — no exceptions, even for "just a config file"
  • CI workflow (publish-release.yml) uses branch protection — direct pushes will warn

Read the full file on GitHub · 48 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. 5d ago First seen · 48 lines · 513 tokens per session scan A 9b26d2a1f70b

Subscribe to this mod's changes

mcp-homelab agent-workflow.instructions.md is an instructions file published in the GitHub repository asvarnon/mcp-homelab (2 stars, last pushed 3mo ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens