add-agent

A command that creates a project-specific advisor agent, an AI persona that judges work rather than performing it. The advisor is registered as an MCP server for Claude and Codex and can later be made available to Antigravity.

In plain words
What is it for?
Use it to create an advisor from a preset template or design a custom one, then register it for use by the connected coding-agent tools.
Why use it?
It lets a project add a consistent viewpoint for evaluating decisions and results.

Command

Part of the cc-suite plugin — 13 skills, 39 commands, 4 agents, 3 hooks shipped together

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/xiaolai/cc-suite/add-agent
Clone the repo
git clone --depth 1 https://github.com/xiaolai/cc-suite

Or install cc-suite, the plugin that ships this one along with the rest of its 13 skills, 39 commands, 4 agents, 3 hooks.

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,320 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 $0.00048 $0.01320
Opus 5 $0.00024 $0.00660
Sonnet 5 $0.00010 $0.00264
Haiku 4.5 $0.00005 $0.00132

Measured 3d ago against content hash 6bd2331584ae, 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 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.

commands/add-agent.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CC-Suite Add Agent

Create a new advisor agent. Advisors are not subagents that do work — they are personas that judge work. The agent-design skill explains the philosophy; this command runs the mechanical workflow.

User Input

$ARGUMENTS

Workflow

Step 1: Load the design skill

Before doing anything else, load and read ${CLAUDE_PLUGIN_ROOT}/skills/cc-suite/agent-design/SKILL.md. Every decision below is informed by it.

Step 2: Decide preset vs custom

List the available presets:

ls "${CLAUDE_PLUGIN_ROOT}/templates/agents/"

Parse $ARGUMENTS:

Input Action
(empty) Show the preset list and ask the user to pick one or choose "custom"
<preset-name> (e.g. north_star_advisor) Use that preset
--custom Skip presets, go straight to custom flow

If using a preset, copy it to .cc-suite/agents/<name>.md:

mkdir -p .cc-suite/agents
cp "${CLAUDE_PLUGIN_ROOT}/templates/agents/<preset-name>.md" ".cc-suite/agents/<preset-name>.md"

If <preset-name> does not match a file under ${CLAUDE_PLUGIN_ROOT}/templates/agents/, stop before copying and report: No preset named '<preset-name>'. Available presets: {list from the table above}. Re-run with one of those names or with --custom.

If the file already exists, ask the user whether to overwrite, edit, or cancel.

Step 3: Tailor the preset (if used)

Open the copied file. Tell the user: "Edit the system prompt to reflect this project's values, not the generic preset. The preset is a starting point — narrow it to your codebase's actual priorities."

Offer to make common adjustments without re-asking:

AskUserQuestion:
  question: "Any quick adjustments before saving?"
  header: "Tailor"
  multiSelect: true
  options:
    - label: "Scope to subdirectory (set cwd)"
      description: "Restrict the advisor's filesystem view to a subdir like docs/ or src/"
    - label: "Change model"
      description: "Switch between opus / sonnet / haiku"
    - label: "Tighten budget"
      description: "Lower max_budget_usd or max_turns"
    - label: "Skip — use preset as-is"
      description: "Save and bridge immediately"

Read the full file on GitHub · 151 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 · 151 lines · 48 tokens per session scan A 6bd2331584ae

Subscribe to this mod's changes

add-agent is a command published in the GitHub repository xiaolai/cc-suite (44 stars, last pushed 24d ago), licensed ISC. It adds 48 tokens to every session and 1,320 once invoked, about $0.0002 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.