What is coral-extend?

A guide for extending the CORAL framework, a software system that runs coding agents and evaluates their work.

Use it to add agent runtimes, command-line commands, bundled skills or agent templates, hooks, configuration fields, and shared grading infrastructure.

It distinguishes framework changes from task-specific grader changes, helping developers place new code in the correct part of the project and test it appropriately.

How Human-Agent-Society/CORAL configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Human-Agent-Society/CORAL. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Human-Agent-Society/CORAL/main/.claude/skills/coral-extend/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Human-Agent-Society/CORAL

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/human-agent-society/coral/coral-extend/github.svg)](https://agentmods.dev/skills/human-agent-society/coral/coral-extend)

Your own site

<a href="https://agentmods.dev/skills/human-agent-society/coral/coral-extend"><img src="https://agentmods.dev/badge/skills/human-agent-society/coral/coral-extend/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/human-agent-society/coral/coral-extend"><img src="https://agentmods.dev/badge/skills/human-agent-society/coral/coral-extend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,616 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00152	$0.01616
Opus 5	$0.00076	$0.00808
Sonnet 5	$0.00030	$0.00323
Haiku 4.5	$0.00015	$0.00162

Measured 12d ago against content hash 572fc0139500, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

coral-extend 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 12d 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/coral-extend/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extending the CORAL framework

For day-to-day debug / reproduce loops see the sibling coral-debug skill. For creating a new examples/<task>/ (seed + task.yaml + grader package) see coral-new-task. This skill covers adding new components to the CORAL package itself.

Extending the grader infrastructure

If you're writing a grader for a specific task, use coral-new-task. This section is only for changes to the grader framework under coral/grader/:

New helpers on TaskGrader (coral/grader/task_grader.py) — make sure they're useful to multiple existing example graders before adding.
New GraderInterface implementations (coral/grader/protocol.py / base.py) — the bar is high; the existing protocol covers everything we currently need.
Daemon-side changes (coral/grader/daemon.py) — concurrency, queue caps, worktree isolation, retry policy. Cover with tests/test_grader_daemon.py.
Built-in graders under coral/grader/builtin/ — function_grader.py is the only one today; not wired through task.yaml. New built-ins should justify why a TaskGrader subclass per task isn't enough.

A new agent runtime

Adding a new runtime (e.g. another coding-agent CLI) means three small files plus a registry entry.

Create coral/agent/builtin/<name>.py and subclass AgentRuntime (coral/agent/runtime.py). Existing runtimes are the canonical reference — claude_code.py is the most complete; codex.py and cursor_agent.py are smaller and easier to mimic.

_RUNTIMES["my_runtime"] = MyRuntime
_ALIASES["mine"] = "my_runtime"
_DEFAULT_MODELS["my_runtime"] = "default-model-id"

Decide the runtime's native shared-state directory name (.claude for Claude Code, .codex for Codex, etc.). The worktree symlink uses this; pass it through shared_dir so generate_coral_md(...) renders the right paths.
If the runtime needs special config plumbing (e.g. cursor_agent.json, opencode.json, gateway port), follow the opencode pattern: emit a per-agent config file inside the worktree at startup.
Add a smoke test in tests/test_<runtime>.py modeled on tests/test_cursor_agent.py.

Read the full file on GitHub · 86 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.

12d ago First seen · 86 lines · 152 tokens per session scan A 572fc0139500

Subscribe to this mod's changes

coral-extend is a skill published in the GitHub repository Human-Agent-Society/CORAL (972 stars, last pushed 3d ago), licensed Apache-2.0. It adds 152 tokens to every session and 1,616 once invoked, about $0.0008 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.

Building agents Claude Code alpha-evolve autoresearch codex coding-agent large-language-models

cw-gates

Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.

Hmbown/Codewhale · 48 tokens

writing

A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.

bojieli/ai-agent-book · 27 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

interview

Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.

Hmbown/CodeWhale · 40 tokens

verify

Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.

Hmbown/CodeWhale · 25 tokens

new-app

Scaffold a new Atomic Agents project from scratch — create the directory, pyproject.toml, env file, first agent, and a runnable entry point. Use when the user asks to start a new atomic-agents project from scratch, says "scaffold" / "new project" / "start from zero", or runs /atomic-agents:new-app.

Eigenwise/atomic-agents · 76 tokens

CORAL: Skill for Claude Code