summon

A guided workflow for creating specialist agent files for Claude Code, an AI coding tool. The files describe roles such as backend developer, tester, security reviewer, or system architect and are tailored to a project's technology and conventions.

In plain words
What is it for?
Use it to generate agents for coding, testing, reviewing, security, performance, or architecture work. The files are placed in the project's `.claude/agents/` directory for Claude Code to use.
Why use it?
Generic AI instructions may not fit a team's programming languages, tools, or working practices. This workflow gathers that context before creating a more specific agent.

Skill for Claude CodeCodex

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 skills/secondorderai/summon-skill/summon
Any agent
npx skills add secondorderai/summon-skill --skill summon
Clone the repo
git clone --depth 1 https://github.com/secondorderai/summon-skill

Made for: Claude Code, Codex.

Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,996 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 $0.00194 $0.04996
Opus 5 $0.00097 $0.02498
Sonnet 5 $0.00039 $0.00999
Haiku 4.5 $0.00019 $0.00500

Measured 2d ago against content hash 2fcaf9273bb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

summon 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (agent-writer.sh, project-scanner.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/summon/SKILL.md · 569 lines

How it starts

The opening of the file, as written. The whole thing — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agency Skill Creator

A skill for generating bespoke, stack-aware Claude Code agent files through a progressive interview process. Each generated agent is a specialized AI persona with identity, personality, mission, critical rules, concrete code patterns, workflows, and success metrics — designed to be autonomously picked up by Claude Code from the project-local .claude/agents/ directory.

Why This Skill Exists

Generic agent templates are too broad to be useful. A "backend architect" agent that speaks Express.js is useless in a Hono + Drizzle + Cloudflare Workers codebase. This skill generates agents from first principles: it understands your stack, your conventions, your pain points, and produces agents that speak your language and enforce your standards.

How It Works

The skill follows a progressive interview flow:

  1. Role Selection — What kind of specialist does the user need?
  2. Stack Discovery — What technologies, patterns, and conventions define this project?
  3. Domain Drilling — Role-specific questions that shape the agent's expertise
  4. Generation — Produce the agent .md file with full structure
  5. Composition (optional) — Generate an orchestrator agent that coordinates a team

Progressive Interview Flow

Phase 1: Role Selection

Ask the user what role they need. Present the three categories:

Engineering Roles:

  • Backend Engineer
  • Frontend Engineer
  • Fullstack Engineer
  • AI/ML Engineer
  • DevOps / Infrastructure Engineer
  • Data Engineer

Quality Roles:

  • QA Engineer / Test Specialist
  • Security Auditor
  • Code Reviewer
  • Performance Engineer

Product & Architecture Roles:

  • System Architect
  • Tech Lead
  • API Designer

If the user describes something that doesn't fit these categories, derive the closest match and confirm. The categories are guidelines, not constraints — the user might want a "Database Migration Specialist" or "Observability Engineer" and that's perfectly valid.

Phase 2: Stack Discovery

Read the full file on GitHub · 569 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 569 lines · 194 tokens per session scan A 2fcaf9273bb3

Subscribe to this mod's changes

summon is a skill published in the GitHub repository secondorderai/summon-skill (1 stars, last pushed 4mo ago), licensed MIT. It adds 194 tokens to every session and 4,996 once invoked, about $0.0010 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 skills, from other repositories

vibe-to-agentic-framework

The conceptual framework behind the presentation — what "Vibe Coding to Agentic Engineering" means, why the journey is structured the way it is, and how every slide fits the narrative arc.

shanraisshan/claude-code-best-practice · 44 tokens

hns-lsel-curator

Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…

modu-ai/moai-adk · 135 tokens

moai-foundation-core

Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, agent catalog reference, and token budget management (absorbed from moai-foundation-context). Use when referencing TRUST 5 gates, SPEC workflow, or context window…

modu-ai/moai-adk · 68 tokens

hns-lsel-applier

Local Self-Evolution Loop (LSEL) APPLY engine — the playback-only consumer of approved decision.json records that drives .moai/hooks/lsel-apply.sh for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001 M3). Reads an approved decision.json, validates the target against the frozen allowlist…

modu-ai/moai-adk · 181 tokens

moai-ref-cross-model-audit

Cross-model audit convergence reference for the plan-auditor and sync-auditor agents. Documents how to invoke the auditmulti MCP tool to fan a code review out across the codex and GLM (z.ai) backends in parallel, converge their verdicts with the in-session Claude verdict, and fold the resulting per-backend verdicts +…

modu-ai/moai-adk · 99 tokens

hns-moaiadk-patterns

Skill "hns-moaiadk-patterns" from modu-ai/moai-adk, covering moai-adk-go domain patterns, architecture quick reference, key source paths, pipeline specialist delegation map and template-first build cycle.

modu-ai/moai-adk · 116 tokens