agent-presets

agent-presets is a skill for Claude Code, Codex from Insajin/autopus-adk. It costs 12 tokens per session (631 once invoked), scanned A, original, MIT.

A set of predefined agent configurations for different project types, such as Go backends, full-stack web applications, and command-line tools. Each configuration selects the agents relevant to that kind of work.

In plain words
What is it for?
Use it to choose an agent set for a Go service, a web application with a Go backend, or a CLI tool and its scripts or SDK utilities.
Why use it?
It avoids activating unnecessary roles and lets a project use a more focused set of planning, coding, testing, review, and security agents.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to choose an agent set for a Go service, a web application with a Go backend, or a CLI tool and its scripts or SDK utilities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/insajin/autopus-adk/agent-presets
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.

Any agent
npx skills add Insajin/autopus-adk --skill agent-presets
Clone the repo
git clone --depth 1 https://github.com/Insajin/autopus-adk

Made for: Claude Code, Codex.

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-presets

README.md
[![agentmods](https://agentmods.dev/badge/skills/insajin/autopus-adk/agent-presets/github.svg)](https://agentmods.dev/skills/insajin/autopus-adk/agent-presets)
Your own site
<a href="https://agentmods.dev/skills/insajin/autopus-adk/agent-presets"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/agent-presets/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 agent-presets

Your own site · 80×15
<a href="https://agentmods.dev/skills/insajin/autopus-adk/agent-presets"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/agent-presets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 631 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00012 $0.00631
Opus 5 $0.00006 $0.00316
Sonnet 5 $0.00002 $0.00126
Haiku 4.5 $0.00001 $0.00063

Measured 11d ago against content hash e2b63d563187, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-presets 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 11d 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.

.omp/skills/agent-presets/SKILL.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.

Agent Presets Skill

Overview

Agent presets define which agents are active for a given project type. Presets allow teams to activate only the agents relevant to their domain, skipping phases that reference inactive agents and reducing unnecessary overhead.

Preset Definitions

backend-go

Optimized for Go backend services.

Active agents: executor, tester, planner, reviewer, validator, security-auditor, annotator, perf-engineer

fullstack

Includes all backend-go agents plus frontend support.

Active agents: executor, tester, planner, reviewer, validator, security-auditor, annotator, perf-engineer, frontend-specialist

cli-tool

Minimal set for CLI tools and utilities.

Active agents: executor, tester, planner, reviewer, validator, annotator

Preset Table

Preset Agents Use Case
backend-go executor, tester, planner, reviewer, validator, security-auditor, annotator, perf-engineer Go microservices, APIs
fullstack All backend-go + frontend-specialist Web apps with Go backend + JS/TS frontend
cli-tool executor, tester, planner, reviewer, validator, annotator CLI utilities, scripts, SDK tools

Configuration (autopus.yaml)

Set a preset for the project:

agent_preset: backend-go  # or fullstack, cli-tool

Default Behavior

If agent_preset is not set, ALL agents are active. This is backward compatible with existing configurations that do not specify a preset.

Custom Presets

Define project-specific presets in autopus.yaml:

agent_presets:
  custom:
    agents:
      - executor
      - tester
      - planner
      - reviewer
      - validator

Then activate with:

agent_preset: custom

Custom presets extend the built-in list. Any agent name not recognized is ignored with a warning.

Pipeline Behavior

When a preset is active, phases referencing inactive agents are skipped:

Phase Skipped When
Phase 2.5 (Annotation) annotator not in preset
Phase 3.5 (UX Verify) frontend-specialist not in preset
Security audit step security-auditor not in preset
Performance check perf-engineer not in preset

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. 11d ago First seen · 95 lines · 12 tokens per session scan A e2b63d563187

Subscribe to this mod's changes

agent-presets is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 631 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 2026-08-30.