agent-add

A command that creates a new coding-agent file from a template.

In plain words
What is it for?
Use it to create minimal, standard, or specialist agents, set their description and tools, choose a target platform, and select an output folder.
Why use it?
It gives a new agent a suitable starting structure and lets you choose how detailed and specialized it should be.

Command

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 commands/gobing-ai/superskill/agent-add
Clone the repo
git clone --depth 1 https://github.com/gobing-ai/superskill
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 652 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 $0.00009 $0.00652
Opus 5 $0.00005 $0.00326
Sonnet 5 $0.00002 $0.00130
Haiku 4.5 $0.00001 $0.00065

Measured 2d ago against content hash 914dd1050a6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-add 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.

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.

plugins/cc/commands/agent-add.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Add

Wraps cc:cc-agents skill.

Scaffold a new subagent file from a tiered template. Delegates to cc:cc-agents skill.

When to Use

  • Create a new agent from scratch
  • Initialize an agent with proper structure
  • Pick a template tier (minimal / standard / specialist) matching the agent's scope

Arguments

Argument Description Default
<name> Name of the agent (hyphen-case) (required)
--description Free-text description of the agent's purpose auto-generated
--target Target platform claude
--output Output directory ./agents
--template Template tier: minimal, standard, or specialist standard
--tools Comma-separated tool names to pre-populate frontmatter (tier default)
--force Overwrite existing file false

Template Tiers

  • minimal — compact persona + tools + skill link; for thin wrappers
  • standard — role, tools, skill integration, workflow sections; the common default
  • specialist — senior-persona, richer toolset, boundaries; for high-autonomy specialists

A freshly scaffolded agent PASSes the project's own evaluator (superskill agent evaluate) out of the box.

Examples

# Scaffold a standard agent (most common)
/cc:agent-add my-coder
# Scaffold with a description of its purpose
/cc:agent-add expert-foo --description "Thin wrapper for cc-foo skill"
# Scaffold a high-autonomy specialist with explicit tools
/cc:agent-add sec-reviewer --template specialist --tools Read,Grep,Bash,Edit
# Scaffold a minimal wrapper with explicit tools
/cc:agent-add router --template minimal --tools Read,Glob

Discovery Discipline

Before scaffolding, run the grill-style discovery interview — explore sibling artifacts, the target repo, and prior evaluations first; then one question at a time, each with a recommended answer. Single copy: cc:cc-skills workflows reference § "Grill-style discovery".

Implementation

Read the full file on GitHub · 77 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. 2d ago First seen · 77 lines · 9 tokens per session scan A 914dd1050a6d

Subscribe to this mod's changes

agent-add is a command published in the GitHub repository gobing-ai/superskill (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 9 tokens to every session and 652 once invoked, about $0.0000 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.