CORAL: Skill for Claude Code

.claude/skills/coral-debug/SKILL.md

coral-debug is a skill for Claude Code from Human-Agent-Society/CORAL. It costs 129 tokens per session (1,852 once invoked), scanned A, original, Apache-2.0.

A debugging and change-checking guide for CORAL, the software package that runs and evaluates coding tasks. It covers areas such as graders, the command-line interface, hooks, workspaces, templates, configuration, and the web system.

In plain words
What is it for?
It helps reproduce and test problems in CORAL using its validation commands, focused test files, command-line checks, and recent task results.
Why use it?
It gives developers a small reproduction path for each part of CORAL, making failures easier to isolate instead of investigating the whole package.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code; mentions Codex; mentions OpenCode.

This is Human-Agent-Society/CORAL's own configuration. It tells Claude Code how to work on CORAL itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CORAL configures →

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-debug/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.

agentmods badge for coral-debug

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/human-agent-society/coral/coral-debug"><img src="https://agentmods.dev/badge/skills/human-agent-society/coral/coral-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,852 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00129 $0.01852
Opus 5 $0.00064 $0.00926
Sonnet 5 $0.00026 $0.00370
Haiku 4.5 $0.00013 $0.00185

Measured 10d ago against content hash 422e905422d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

coral-debug 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 10d 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-debug/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CORAL debug & change-verification workflows

This skill is for people (and Claude Code) hacking on the CORAL package itself, not for users authoring a task. For authoring guides see the siblings:

  • coral-new-task — creating a new examples/<task>/ (seed + task.yaml + grader)
  • coral-extend — extending CORAL itself (new runtime, new CLI command, new bundled skill, ...)

Reproduce loops

Pick the smallest one that exercises your change.

Editing... Fastest reproduce
coral/grader/{task_grader,loader,subprocess_grader}.py or a builtin grader uv run coral validate examples/circle_packing (or any example with a packaged grader)
coral/grader/daemon.py (parallel grading, queueing, worktree isolation) uv run pytest tests/test_grader_daemon.py -v
coral/grader/{base,protocol}.py uv run pytest tests/test_grader.py tests/test_subprocess_grader.py -v
coral/cli/*.py (argparse, dispatch, output formatting) Run the command directly: uv run coral log --help, uv run coral status, etc. against a latest run under examples/<task>/results/
coral/hooks/post_commit.py (submit_eval) uv run pytest tests/test_hooks.py -v, then end-to-end via coral start -c task.yaml agents.count=1 and watch .coral/public/attempts/
coral/agent/manager.py, state.py, exit_classifier.py uv run pytest tests/test_manager_reliability.py tests/test_manager_seen_attempts.py -v
coral/agent/builtin/*.py (a runtime) uv run pytest tests/test_<runtime>.py if it exists, then coral start -c task.yaml agents.runtime=<name> agents.count=1
coral/workspace/{project,worktree,repo,grader_env}.py uv run pytest tests/test_workspace.py tests/test_grader_env.py -v
coral/hub/{attempts,notes,skills,checkpoint,heartbeat}.py uv run pytest tests/test_hub.py tests/test_checkpoint.py tests/test_heartbeat.py -v
coral/template/coral_md.py or templates uv run pytest tests/test_template.py -v
coral/config.py uv run pytest tests/test_config.py -v
coral/web/* (dashboard) uv run coral ui against any existing run; reload the browser after edits

Read the full file on GitHub · 95 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. 10d ago First seen · 95 lines · 129 tokens per session scan A 422e905422d7

Subscribe to this mod's changes

coral-debug is a skill published in the GitHub repository Human-Agent-Society/CORAL (965 stars, last pushed yesterday), licensed Apache-2.0. It adds 129 tokens to every session and 1,852 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

codegraph

Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…

QwenLM/qwen-code · 0 tokens

stuck

Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.

QwenLM/qwen-code · 57 tokens

structured-debugging

Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…

QwenLM/qwen-code · 85 tokens

memory-leak-debug

Diagnose memory leaks in the Qwen Code CLI using heap snapshots and the chrome-devtools CLI. Use when investigating high memory usage, unbounded growth, or suspected object retention issues.

QwenLM/qwen-code · 42 tokens

bugfix

Fix a bug from a GitHub issue, following the reproduce-first workflow. Use when the user asks to fix a bug, investigate a GitHub issue, or debug a user-reported problem. Takes a GitHub issue URL or number as input.

QwenLM/qwen-code · 53 tokens

rust-check

Run cargo check on the current Rust project to find compile errors.

Hmbown/CodeWhale · 15 tokens