skill-add

A command that creates a new coding-agent skill directory and its SKILL.md instruction file from a template.

In plain words
What is it for?
Use it to create technique, pattern, or reference skills, set their platform and tools, and choose whether people or the agent should invoke them.
Why use it?
It provides a consistent starting structure for a new skill and prompts discovery of related work before scaffolding.

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/skill-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 740 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 $0.00740
Opus 5 $0.00005 $0.00370
Sonnet 5 $0.00002 $0.00148
Haiku 4.5 $0.00001 $0.00074

Measured 3d ago against content hash 06ac64d54d5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-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 3d 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/skill-add.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Add

Wraps cc:cc-skills skill.

Scaffold a new skill directory with SKILL.md from a tiered template. Delegates to cc:cc-skills skill.

When to Use

  • Create a new skill from scratch
  • Initialize a skill with proper directory structure and frontmatter
  • Pick a template tier (technique / pattern / reference) matching the skill's shape

Arguments

Argument Description Default
<name> Name of the skill (hyphen-case) (required)
--description Free-text description of the skill's purpose auto-generated
--target Target platform claude
--output Output directory ./skills
--template Template tier: technique, pattern, or reference default
--tools Comma-separated tool names to pre-populate frontmatter (tier default)
--invocation-mode user (emits disable-model-invocation: true + one-line human-facing description) or model (trigger-rich description) model
--force Overwrite existing file false

Discovery Discipline

Before scaffolding, run the grill-style discovery interview — explore sibling skills, 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".

Template Tiers

  • technique — step-by-step workflows with concrete instructions and verification gates; for procedural skills
  • pattern — decision frameworks with trade-off analysis and core principles; for design-decision skills
  • reference — lookup tables and documentation; for factual/API-reference skills

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

Examples

# Scaffold a default skill (most common)
/cc:skill-add my-skill
# Scaffold with a description of its purpose
/cc:skill-add my-skill --description "Wraps the foo API"
# Scaffold a technique-tier skill with explicit tools
/cc:skill-add deploy-skill --template technique --tools Read,Write,Bash
# Scaffold a reference-tier skill
/cc:skill-add api-ref --template reference
# Scaffold a user-invoked skill (human picks it directly; other skills cannot fire it)
/cc:skill-add release-runner --invocation-mode user --description "Run the release checklist"

Read the full file on GitHub · 80 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. 3d ago First seen · 80 lines · 9 tokens per session scan A 06ac64d54d5a

Subscribe to this mod's changes

skill-add is a command published in the GitHub repository gobing-ai/superskill (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 9 tokens to every session and 740 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.