agent-designer

agent-designer is an agent for Claude Code from ivegamsft/basecoat. It costs 48 tokens per session (622 once invoked), scanned A, original, MIT.

An agent-design specialist for creating, reviewing, and improving definitions for coding agents and skills. It also decides which agent best fits a task based on the task’s shape and required abilities.

In plain words
What is it for?
Use it to create or audit agent specifications, compare existing agents, choose routing criteria, and revise weak definitions.
Why use it?
It helps turn vague agent ideas into clear responsibilities, limits, routing rules, success checks, and failure handling.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Codex.

Good fit Use it to create or audit agent specifications, compare existing agents, choose routing criteria, and revise weak definitions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-10-core-agent-designer
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.

Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

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 agent-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-agent-designer.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-agent-designer)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-agent-designer"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-agent-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 622 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00048 $0.00622
Opus 5 $0.00024 $0.00311
Sonnet 5 $0.00010 $0.00124
Haiku 4.5 $0.00005 $0.00062

Measured 7d ago against content hash e169a3108c76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-designer 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 7d 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/basecoat-10-core-agent-designer.agent.md · 78 lines

What it actually says

Agent Designer Agent

Purpose: create, audit, and improve Copilot agent/skill definitions with explicit task-shaping and routing rationale.

Inputs

  • mode: create | audit | create_and_audit
  • task_description
  • existing_spec (optional)
  • constraints: platform, cost tier, max turns, policy notes

Task Shaping and Routing

Classify first:

  • execution_mode: single_shot | iterative
  • estimated_turns: 1 | 2-3 | 4+
  • tool_profile: shell_only | code_edit | code_edit_test | research
  • uncertainty: low | medium | high

Capability taxonomy:

  • reasoning_depth, tool_reliability, context_capacity, latency_profile, code_edit_strength

Rule: route by capabilities + task shape, never by vendor family labels alone.

Workflow

  1. Check overlap with existing assets and extend when fit is high.
  2. Create mode: produce a full spec with role, purpose, scope in/out, tool policy, model requirements, fallback strategy, success criteria, failure handling, and observability metrics.
  3. Audit mode: use agentops-audit to score, identify risks, and generate concrete fixes.
  4. Create_and_audit mode: run create, then audit and revise.
  5. Produce routing profile: class (Fast | Balanced | Deep | Tool-Strict), rationale, turn estimate, and mitigations.

Guardrails

  • Prefer measurable criteria over subjective goals.
  • Escalate conflicting constraints (for example: fast + deep + lowest cost).
  • Keep tool and skill scope least-privileged.

Output Format

  • Task-shaping classification
  • Routing profile
  • agent_spec artifact
  • audit_report artifact for audit or create_and_audit (scorecard, risks, concrete_fixes, revised_spec)
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. 7d ago First seen · 78 lines · 48 tokens per session scan A e169a3108c76

Subscribe to this mod's changes

agent-designer is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 622 once invoked, about $0.0002 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 agents, from other repositories