add-agent

A command for creating a specialised Claude Code helper for a Copana setup. It asks what the helper should do and what access it needs, then creates its configuration and instructions.

In plain words
What is it for?
Use it to create helpers for tasks such as code review, calendar management, or habit tracking, with selected abilities like reading, editing files, or web access.
Why use it?
It provides a repeatable way to define a helper’s role, files, tools, model, and optional persistent memory. Testing the result helps ensure it stays within those permissions.

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

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 457 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 $0.00000 $0.00457
Opus 5 $0.00000 $0.00229
Sonnet 5 $0.00000 $0.00091
Haiku 4.5 $0.00000 $0.00046

Measured 2d ago against content hash fcc1e60c0f96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-agent 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.

.claude/skills/add-agent/SKILL.md · 61 lines

What it actually says

/add-agent — Create a Custom Subagent

Create a specialized Claude Code subagent for your Copana setup.

Steps

  1. Ask the user:

    • What should the agent do? (e.g., "review my code", "manage my calendar", "track habits")
    • Should it have web access? (WebSearch, WebFetch)
    • Should it be able to edit files? (Write, Edit)
    • Should it use a smaller model for speed? (haiku vs sonnet)
    • Should it have persistent memory? (remembers across sessions)
  2. Create .claude/agents/agent-name.md with YAML frontmatter:

    ---
    name: agent-name
    description: One-line description
    model: haiku  # or omit for default
    tools:
      - Read
      - Write    # only if needed
      - Edit     # only if needed
      - Glob
      - Grep
      - WebSearch  # only if needed
      - WebFetch   # only if needed
    memory: project  # or omit for no persistence
    ---
    
  3. Write the agent instructions below the frontmatter:

    • Clear role description
    • What files it manages
    • Output format
    • Rules and constraints
  4. Test the agent:

    • Run it with a sample task
    • Verify it stays within its tool permissions
    • Check that output is useful
  5. Commit changes.

Built-in Agents

Copana ships with three agents:

Agent Purpose Model
memory-manager Consolidate and clean memory files haiku
research Web research with structured output default
daily-review End-of-day file review and summary haiku

Tips

  • Use model: haiku for simple, repetitive tasks (faster and cheaper)
  • Only grant tools the agent actually needs — fewer tools = more focused
  • memory: project lets the agent build up knowledge across sessions
  • Keep agent instructions under 100 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 · 61 lines · 0 tokens per session scan A fcc1e60c0f96

Subscribe to this mod's changes

add-agent is a skill published in the GitHub repository PayRequest/copana (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 457 tokens. 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

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

fastclaw-ai/fastclaw · 64 tokens

fastclaw-skill-guide

Create new skills for FastClaw agents. Use when the user asks to create a skill, turn a workflow into a skill, or build reusable automation. Also use when discussing skill format, structure, or best practices.

fastclaw-ai/fastclaw · 51 tokens

image-gen

Generate images, charts, plots, and visualizations. Use when the user asks to draw, plot, chart, visualize data, or create images.

fastclaw-ai/fastclaw · 33 tokens

weekly-digests

Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…

thedotmack/claude-mem · 93 tokens

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

skill-template

Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.

muratcankoylan/Agent-Skills-for-Context-Engineering · 24 tokens