CORAL is infrastructure for autonomous coding agents that run experiments on a codebase, have their work graded, share knowledge, and evolve solutions across repeated attempts. It is used for autoresearch workflows with agents such as Claude Code, OpenCode, Codex, Cursor Agent, and Kiro. The catalogue entries provide skills, agents, instructions, a plugin, and a hook for operating these workflows.
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.
npx skills add Human-Agent-Society/CORAL --skill skill-creatorgit clone --depth 1 https://github.com/Human-Agent-Society/CORALWrote 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.
[](https://agentmods.dev/skills/human-agent-society/coral/skill-creator)<a href="https://agentmods.dev/skills/human-agent-society/coral/skill-creator"><img src="https://agentmods.dev/badge/skills/human-agent-society/coral/skill-creator/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.
<a href="https://agentmods.dev/skills/human-agent-society/coral/skill-creator"><img src="https://agentmods.dev/badge/skills/human-agent-society/coral/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.03353 |
| Opus 5.5 | $0.00023 | $0.01341 |
| Sonnet 5.5 | $0.00012 | $0.00671 |
| Haiku 4.5 | $0.00006 | $0.00335 |
Grade A, and why
skill-creator 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator (Autonomous)
Create skills by analyzing your own work patterns — you are both creator and evaluator. No human input required at any step.
Core loop: analyze context → draft SKILL.md → generate test cases → run + grade → iterate → optimize description → package
1. Context Analysis
Before drafting, identify what skill to build and confirm it doesn't already exist.
Pattern Detection
Scan these sources for repeated, reusable patterns:
- Git diffs:
git log --stat -10andgit diff HEAD~5— look for repeated file types, similar transformations, recurring helper scripts written independently across commits - Attempt history: Read
.coral/attempts/JSON files — which approaches recur? What tool sequences appear in multiple successful attempts? - Tool usage: Review your own transcript — sequences of 3+ tool calls that repeat across tasks are skill candidates
- Cross-episode notes: Run
coral notes --read all— patterns under "Patterns That Work" not yet captured as skills are prime candidates - Sibling techniques: Check
.coral/graph_state/state.yamlsiblings:— if multiple agents converged on the same technique independently, it deserves a skill
Deduplication Check
Before creating a new skill, check existing skills:
coral skills
Read each relevant SKILL.md frontmatter. If an existing skill has 70%+ overlap with your candidate, update that skill instead of creating a new one.
Output
Produce a structured spec before writing:
Skill name: <kebab-case>
Purpose: <what it enables, one sentence>
Triggers: <when should this skill activate>
Output format: <what the skill produces>
Source evidence: <which patterns/diffs/insights led to this>
2. Write the SKILL.md
Based on your context analysis, draft the skill.
Skill Writing Guide
Anatomy of a Skill
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter (name, description required)
│ └── Markdown instructions
└── Bundled Resources (optional)
├── scripts/ - Executable code for deterministic/repetitive tasks
├── references/ - Docs loaded into context as needed
└── assets/ - Files used in output (templates, icons, fonts)
What ships with it
8 files 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.
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.
- 1mo ago First seen · 398 lines · 58 tokens per session scan A 3e79068bca2b
skill-creator is a skill published in the GitHub repository Human-Agent-Society/CORAL (1,098 stars, last pushed 6d ago), licensed Apache-2.0. It adds 58 tokens to every session and 3,353 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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.
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.