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.
npx agentmods add instructions/markharrison/iag-customagent-labs-old/custom-agentgit clone --depth 1 https://github.com/markharrison/IAG-CustomAgent-Labs-OLDWrote 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.
[](https://agentmods.dev/instructions/markharrison/iag-customagent-labs-old/custom-agent)<a href="https://agentmods.dev/instructions/markharrison/iag-customagent-labs-old/custom-agent"><img src="https://agentmods.dev/badge/instructions/markharrison/iag-customagent-labs-old/custom-agent.svg" alt="Measured on agentmods" height="20"></a>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 | $0.13647 | $0.13647 |
| Opus 5 | $0.06823 | $0.06823 |
| Sonnet 5 | $0.02729 | $0.02729 |
| Haiku 4.5 | $0.01365 | $0.01365 |
Grade A, and why
IAG-CustomAgent-Labs-OLD custom-agent.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.
How it starts
The opening of the file, as written. The whole thing — 1,594 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custom Agent Definition Guide
How to create well-structured, maintainable custom agent files for GitHub Copilot. This guide covers three agent archetypes — Agent, Orchestrator, and Subagent — with conventions for frontmatter, body structure, state management, and quality gates.
Official docs: https://docs.github.com/en/copilot/how-tos/use-copilot-agents
Agent Archetypes
Every agent falls into one of three archetypes. Choose the right one before writing anything.
| Agent | Orchestrator | Subagent | |
|---|---|---|---|
| Purpose | Self-contained task | Coordinates a pipeline | Executes one pipeline step |
| User-invocable | ✅ Yes | ✅ Yes | ❌ No |
| Delegates work | No | Yes (to subagents) | No |
| Writes state files | ✅ Yes (progress) | Yes (pipeline state) | Yes (step output MD) |
| Writes deliverables | Optional | No | Optional |
| Owns approval gates | No | Yes | No |
| Maintains state | Yes (checkpoints) | Yes (via state folder) | No |
| Has handoffs | Optional | No | No |
| Location | .github/agents/ |
.github/agents/ |
.github/agents/_subagents/ |
When to use each
- Agent: A single agent that does one job end-to-end. No pipeline, no
coordination. REQUIRED: Write a state file to
./output/state/00-{agent-name}.mdat startup (before Phase 1) with all phases unchecked. Update it after each phase. - Orchestrator: A multi-step workflow where each step needs a specialist
agent, human approval between steps, and the ability to resume, revert,
or stop. REQUIRED: Write
00-{orchestrator-name}.mdto track pipeline state, parameters, and step checkboxes. - Subagent: A specialist that handles one step in an orchestrator's pipeline. Never
invoked directly by users. REQUIRED: Write a step state file (
{NN}-{step}.md) at startup with all phases unchecked. Update it progressively after each phase.
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.
- 5d ago First seen · 1,594 lines · 13,647 tokens per session scan A ec4131898f03
IAG-CustomAgent-Labs-OLD custom-agent.instructions.md is an instructions file published in the GitHub repository markharrison/IAG-CustomAgent-Labs-OLD (2 stars, last pushed 5mo ago), licensed MIT. It adds 13,647 tokens to every session, about $0.0682 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.
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).
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.
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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.