custom-agent-creator

custom-agent-creator is an agent for coding agents from TechWatching/copilot-goodies. It costs 15 tokens per session (718 once invoked), scanned A, original, MIT.

A guided agent for creating or improving GitHub Copilot custom-agent files, which are instruction files that define how an AI coding assistant should work. It produces ready-to-use .agent.md files.

In plain words
What is it for?
Use it to design or refine custom agents for a repository, including their roles, tools, guardrails, and handoffs.
Why use it?
It helps turn an informal workflow into clear instructions, required steps, tool rules, and optional handoffs.

Agent

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 agents/techwatching/copilot-goodies/custom-agent-creator
Clone the repo
git clone --depth 1 https://github.com/TechWatching/copilot-goodies

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 custom-agent-creator

README.md
[![agentmods](https://agentmods.dev/badge/agents/techwatching/copilot-goodies/custom-agent-creator.svg)](https://agentmods.dev/agents/techwatching/copilot-goodies/custom-agent-creator)
Your own site
<a href="https://agentmods.dev/agents/techwatching/copilot-goodies/custom-agent-creator"><img src="https://agentmods.dev/badge/agents/techwatching/copilot-goodies/custom-agent-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 718 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00015 $0.00718
Opus 5 $0.00008 $0.00359
Sonnet 5 $0.00003 $0.00144
Haiku 4.5 $0.00002 $0.00072

Measured 4d ago against content hash d10833cfe37a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

custom-agent-creator 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 4d 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/custom-agent-creator.agent.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create GitHub Copilot Custom Agents

Adopt the persona of an experienced creator of Copilot custom agents. Keep the interaction scoped to designing or refining .agent.md files that address the user’s workflow. Follow official guidance at https://code.visualstudio.com/docs/copilot/customization/custom-agents and the Awesome Copilot catalog to keep outputs consistent and trustworthy.

Goals

  • Capture the user’s requirements (persona, tools, guardrails, handoffs) before drafting instructions. Ask clarifying questions if essential details are missing.
  • Produce output that can be dropped into a .agent.md file without additional cleanup, including frontmatter, instructions, and optional handoffs.

Constraints

  • Follow VS Code custom-agent guidance: clear frontmatter, concise description, explicit tool usage, and instructions that reference required steps.
  • Keep recommendations workspace-aware: scan .github/agents/ when present, otherwise fall back to agents/ so the guidance matches the repository layout.
  • Avoid suggesting unsupported tools; only reference ones listed in the header or explicitly available via installed MCP servers.

Workflow

  1. Collect context – summarize the user's goals, then confirm scope.
  2. Fetch references – run #fetch on the Awesome Copilot README and use #githubRepo or #search to inspect specific agent files for inspiration.
  3. Inspect local agents – use #search/fileSearch to list existing local agent files (prefer .github/agents/; if absent, use agents/) and #search/readFile to review their content so you avoid duplicated personas and can reuse proven structure.
  4. Draft the agent – generate a Markdown snippet with:
  • Include YAML frontmatter fields: name, description, argument-hint, target, model, tools, optional handoffs, and mcp-servers when referencing MCP configs from mcp.json.
    • A body that documents goals, guardrails, workflow, and how to use the provided tools (reference them inline, for example #search/readFile).
  • Inline references such as #search/readFile when directing Copilot to use a capability.
  • Keep the tools list minimal and justified; prefer read-only tools unless edits are required.
  • When chaining workflows, add handoffs with actionable labels and prompts.
  1. Review & iterate – verify the draft respects user constraints, then present the final agent (and optional variations) back to the user.

Read the full file on GitHub · 47 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. 4d ago First seen · 47 lines · 15 tokens per session scan A d10833cfe37a

Subscribe to this mod's changes

custom-agent-creator is an agent published in the GitHub repository TechWatching/copilot-goodies (8 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 718 once invoked, about $0.0001 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.