coral-quickstart

coral-quickstart is a skill for Claude Code from Human-Agent-Society/CORAL. It costs 185 tokens per session (1,814 once invoked), scanned C, original, Apache-2.0.

A quick-start guide for CORAL, a system where coding agents repeatedly edit code in separate Git workspaces and receive scores from a grader. CORAL is intended for experiments where success can be measured with a number.

In plain words
What is it for?
Use it to optimize code, algorithms, prompts, or other measurable tasks through repeated agent experiments and scored evaluations.
Why use it?
It explains how to set up and run many independent attempts on the same coding problem, while comparing their results.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the coral plugin — 4 skills, 2 agents, 1 hook shipped together

Good fit Use it to optimize code, algorithms, prompts, or other measurable tasks through repeated agent experiments and scored evaluations.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Human-Agent-Society/CORAL
Claude Code
/plugin install coral

Made for: Claude Code.

Or install coral, the plugin that ships this one along with the rest of its 4 skills, 2 agents, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for coral-quickstart

README.md
[![agentmods](https://agentmods.dev/badge/skills/human-agent-society/coral/coral-quickstart/github.svg)](https://agentmods.dev/skills/human-agent-society/coral/coral-quickstart)
Your own site
<a href="https://agentmods.dev/skills/human-agent-society/coral/coral-quickstart"><img src="https://agentmods.dev/badge/skills/human-agent-society/coral/coral-quickstart/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for coral-quickstart

Your own site · 80×15
<a href="https://agentmods.dev/skills/human-agent-society/coral/coral-quickstart"><img src="https://agentmods.dev/badge/skills/human-agent-society/coral/coral-quickstart.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,814 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00185 $0.01814
Opus 5 $0.00093 $0.00907
Sonnet 5 $0.00037 $0.00363
Haiku 4.5 $0.00018 $0.00181

Measured 11d ago against content hash a3687c600c77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

coral-quickstart scanned grade C with 2 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/new-coral-workspace.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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/Human-Agent-Society/CORAL/main/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/Human-Agent-Society/CORAL/main/install.sh | sh
plugin/skills/coral-quickstart/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CORAL quickstart

CORAL is infrastructure for autonomous coding agents: you give it a codebase (seed/) and a grader (turns a commit into a number), and it spawns agents in isolated git worktrees that edit code, submit commits, and get scored on a shared leaderboard — looping to push the score up. The agents are the optimizer; your grader defines "better".

When to reach for CORAL

Good fit:

  • You can express success as a number — accuracy, runtime ratio, pass rate, or a rubric-judge score for open-ended work.
  • The work is iterative search: many attempts at one well-scoped problem (kernel/algorithm optimization, benchmark solving, prompt/program tuning, "make this function faster").
  • You want parallel agents exploring independently and sharing what works.

Not a fit:

  • One-shot tasks with no measurable objective.
  • Work that needs a human judging every attempt (use a rubric-judge grader if a model can score it).

How a run is shaped

you provide:   seed/ (starter code)  +  a grader (commit → number)
coral spawns:  N agents, each in its own git worktree
each agent:    edit code → `coral eval` → grader scores it → read leaderboard → repeat
shared state:  attempts, notes, and skills are visible across agents in real time

Two things you build (seed/ + grader) and one thing you tune (how many agents, which model). Worktrees, scoring daemon, shared state, and restarts are handled for you.

Get running — four steps

1. Install the CLI

curl -fsSL https://raw.githubusercontent.com/Human-Agent-Society/CORAL/main/install.sh | sh
# or, if you have uv:
uv tool install git+https://github.com/Human-Agent-Society/CORAL.git
coral --help      # verify

The installer grabs the latest coral release by default — that's what you want. (Only pin a specific release with CORAL_VERSION=<tag> before the curl if you have a reason to.)

2. Register a runtime (coral setup)

coral shells out to a coding-agent CLI (Claude Code, Codex, Cursor, Kiro, OpenCode) — each installed and authenticated separately. Tell coral which to use:

Read the full file on GitHub · 107 lines

Files

What ships with it

1 file 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. 11d ago First seen · 107 lines · 185 tokens per session scan C a3687c600c77

Subscribe to this mod's changes

coral-quickstart is a skill published in the GitHub repository Human-Agent-Society/CORAL (972 stars, last pushed 3d ago), licensed Apache-2.0. It adds 185 tokens to every session and 1,814 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.