MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
One-time machine setup after installing the coral CLI — register local agent runtimes as named bindings with coral setup / coral setup agent, validate them with coral agents doctor (incl.
Install Setting Up Coral
$ npx skills add Human-Agent-Society/CORAL --skill setting-up-coral -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Human-Agent-Society/CORAL setting-up-coral --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Human-Agent-Society/CORAL.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/setting-up-coral .claude/skills/setting-up-coral && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "setting-up-coral" agent skill from https://github.com/Human-Agent-Society/CORAL/tree/main/plugin/skills/setting-up-coral into .claude/skills/setting-up-coral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setting-up-coral", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Human-Agent-Society/CORAL/tree/main/plugin/skills/setting-up-coralType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Human-Agent-Society/CORAL --skill setting-up-coral -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Human-Agent-Society/CORAL setting-up-coral --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Human-Agent-Society/CORAL.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugin/skills/setting-up-coral .agents/skills/setting-up-coral && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "setting-up-coral" agent skill from https://github.com/Human-Agent-Society/CORAL/tree/main/plugin/skills/setting-up-coral into .agents/skills/setting-up-coral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setting-up-coral", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Human-Agent-Society/CORAL --skill setting-up-coral -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Human-Agent-Society/CORAL setting-up-coral --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Human-Agent-Society/CORAL.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugin/skills/setting-up-coral .cursor/skills/setting-up-coral && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "setting-up-coral" agent skill from https://github.com/Human-Agent-Society/CORAL/tree/main/plugin/skills/setting-up-coral into .cursor/skills/setting-up-coral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setting-up-coral", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Human-Agent-Society/CORAL.git --path plugin/skills/setting-up-coral--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Human-Agent-Society/CORAL --skill setting-up-coral -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Human-Agent-Society/CORAL setting-up-coral --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Human-Agent-Society/CORAL.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugin/skills/setting-up-coral .gemini/skills/setting-up-coral && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "setting-up-coral" agent skill from https://github.com/Human-Agent-Society/CORAL/tree/main/plugin/skills/setting-up-coral into .gemini/skills/setting-up-coral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setting-up-coral", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Human-Agent-Society/CORAL setting-up-coralInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Human-Agent-Society/CORAL --skill setting-up-coral -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Human-Agent-Society/CORAL.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugin/skills/setting-up-coral .github/skills/setting-up-coral && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "setting-up-coral" agent skill from https://github.com/Human-Agent-Society/CORAL/tree/main/plugin/skills/setting-up-coral into .github/skills/setting-up-coral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setting-up-coral", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Human-Agent-Society/CORAL --skill setting-up-coral -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Human-Agent-Society/CORAL setting-up-coral --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Human-Agent-Society/CORAL.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugin/skills/setting-up-coral .opencode/skills/setting-up-coral && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "setting-up-coral" agent skill from https://github.com/Human-Agent-Society/CORAL/tree/main/plugin/skills/setting-up-coral into .opencode/skills/setting-up-coral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "setting-up-coral", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
setting-up-coral- GitHub stars
- 1.1k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 727 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
One-time machine setup after installing the coral CLI — register local agent runtimes as named bindings with coral setup / coral setup agent, validate them with coral agents doctor (incl.
- Works in 4 steps: Detect + create bindings (the fast path) → Create / update a single binding… → Validate before running → …
- The user is configuring which agent runtimes/models coral can use
- SKILL.md covers 1. Detect + create bindings…, 2. Create / update a single…, 3. Validate before running and Per-runtime authentication, plus 2 more sections
- Calls codex and opencode
What it does
Setting Up Coral is an agent skill from Human-Agent-Society/CORAL. One-time machine setup after installing the coral CLI — register local agent runtimes as named bindings with coral setup / coral setup agent, validate them with coral agents doctor (incl. a live hello-ping that catches expired auth and model typos), and reference them from a task via agents.binding. Use when the user is configuring which agent runtimes/models coral can use, hits a "runtime not found" / auth error when starting a run, or asks how to set up claude/codex/cursor for coral.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. The repository describes itself as: Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026. The licence is Apache-2.0.
When your agent uses it
- The user is configuring which agent runtimes/models coral can use
- Hits a runtime not found / auth error when starting a run
- Asks how to set up claude/codex/cursor for coral
Example prompts
- “runtime not found”
- “/setting-up-coral”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 0123dfb. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
codexopencode
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
coral.compounding-intelligence.ai
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Setting Up Coral loads about 1.7k tokens when it runs. Until then it costs about 129 tokens; SKILL.md has 727 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Human-Agent-Society/CORAL at commit 0123dfb, republished under its Apache-2.0 licence (© Human-Agent-Society). 727 words, ~1,733 tokens.
Download SKILL.mdSave it as
.claude/skills/setting-up-coral/SKILL.md (or your agent's skills folder).- name
- setting-up-coral
- description
- One-time machine setup after installing the `coral` CLI — register local agent runtimes as named bindings with `coral setup` / `coral setup agent`, validate them with `coral agents doctor` (incl. a live hello-ping that catches expired auth and model typos), and reference them from a task via `agents.binding`. Use when the user is configuring which agent runtimes/models coral can use, hits a "runtime not found" / auth error when starting a run, or asks how to set up claude/codex/cursor for coral.
Setting up coral (agent bindings)
After installing the coral CLI, the one-time machine setup is registering which agent runtimes you have as named bindings. A binding bundles a runtime + CLI command + default model + runtime options under a short name, stored at:
~/.config/coral/agents.yaml # honors $XDG_CONFIG_HOME; override with $CORAL_AGENTS_CONFIGTasks then reference a binding by name (agents.binding: claude-opus) instead of repeating runtime/model in every task.yaml. This keeps task.yaml portable (topology: how many agents, which roles) and machine-specific details (which CLIs are installed here) in a user-level file that's never committed.
Bindings store no credentials. Authentication stays with each runtime's native login (
claude,codex,cursor-agent login,kiro-clisetup).coral setuponly records runtime/command/model metadata. If a run fails to auth, fix it via the runtime's own login, not coral.
1. Detect + create bindings (the fast path)
coral setupScans PATH for every supported runtime (claude, codex, cursor-agent, opencode, kiro-cli, pi), prints a detection report (✓ = found), then offers a numbered wizard. For each pick it asks for a binding name, model, and an optional role-seed file. After each one it asks "Add another binding for X?" — say yes to make several bindings for the same runtime (e.g. claude-opus and claude-sonnet). The first binding created becomes the default.
coral setup --non-interactive— just print the detection report (CI / piping); creates nothing.
2. Create / update a single binding (scriptable)
For a custom command path, model, or runtime option — or for CI where you can't use the wizard:
coral setup agent --name claude-opus --runtime claude_code --model opus
coral setup agent --name codex-high --runtime codex --option model_reasoning_effort=high
coral setup agent --name claude-opus --runtime claude_code --model opus --default # make it the default--runtime accepts a builtin (claude_code | codex | cursor_agent | opencode | kiro) or a custom module.path:ClassName. Re-running with an existing --name updates that binding. Each coral setup agent finishes with a lightweight doctor pass on that binding.
3. Validate before running
coral agents list # numbered; default marked
coral agents show claude-opus # one binding's resolved fields
coral agents doctor # validate ALL bindings
coral agents doctor claude-opus # validate onedoctor runs five checks per binding: the binding resolves to a valid spec, the CLI is on PATH (or at the configured command), --version works, the role file exists (if set), and — by default — a live hello-ping that spawns the runtime with a one-word prompt and waits for a reply. The live ping is what catches the failures the cheap checks miss: expired auth, broken provider credentials, network issues, model-name typos.
--no-live— skip the hello-ping (CI / quick sanity check; costs one LLM round-trip per binding otherwise).--timeout SECS— per-ping wait (default 30s).
When the ping fails, doctor points you at the runtime's login flow rather than asking for credentials.
coral agents remove # interactive numbered wizard
coral agents remove claude-opus codex-high # delete one or more by nameShow full SKILL.md (348 more words)Show less
Reading a doctor failure
doctor tells you which of the five checks failed — match it to the fix:
| Failed check | What it means | Fix |
|---|---|---|
| binding resolves | agents.yaml entry is malformed or names an unknown runtime | coral agents show <name>; recreate with coral setup agent --name ... --runtime .... |
| CLI on PATH | the runtime binary isn't found | install the runtime, or point the binding at it with --command /abs/path. |
--version works | binary found but won't run | reinstall the runtime; check it runs standalone. |
| role file exists | a configured role-seed file was moved/deleted | fix the path or drop the role file from the binding. |
| live hello-ping | binary runs but the model call fails | almost always auth or a model typo — log in via the runtime (table below) and check the model name. Re-run; add --no-live only to skip the check, not to fix it. |
Per-runtime authentication
Bindings store no credentials — each runtime owns its own login. The hello-ping failing means you log in here, not in coral:
| Runtime | --runtime | Log in with |
|---|---|---|
| Claude Code | claude_code | claude (interactive login) |
| Codex | codex | codex login flow |
| Cursor Agent | cursor_agent | cursor-agent login |
| Kiro | kiro | kiro-cli setup |
| OpenCode | opencode | opencode auth |
Codex reasoning effort is a runtime option, not a model: coral setup agent --name codex-high --runtime codex --option model_reasoning_effort=high. For custom or self-hosted models across runtimes, route through the LiteLLM gateway (agents.gateway in task.yaml): https://coral.compounding-intelligence.ai/docs/guides/gateway
4. Use a binding in a task
Single runtime:
agents:
binding: claude-opus
count: 4Mixed team — one binding per assignment:
agents:
assignments:
- binding: researcher
count: 1
- binding: implementer
count: 3Precedence when a binding expands: explicit task.yaml fields win → binding fields → runtime defaults. So binding: claude-opus plus model: sonnet uses the binding's runtime/options but the overriding model. Bindings are purely additive — agents.runtime / agents.model / agents.assignments still work unchanged, and after expansion the run's stored config.yaml holds only concrete fields (so resumes and the dashboard never depend on your local bindings file).
Where this sits
coral-quickstart (install) → setting-up-coral (bindings, here) → creating-a-coral-task (author) → running-coral-experiments (run). Setup is optional — you can put runtime/model straight in task.yaml — but bindings + coral agents doctor are the reliable way to confirm a runtime is installed and authenticated before you launch agents. Full reference: https://coral.compounding-intelligence.ai/docs/guides/agent-bindings
© Human-Agent-Society, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugin/skills/setting-up-coral of Human-Agent-Society/CORAL.
Open the folder on GitHubat commit 0123dfb
Compare with similar skills
Setting Up Coral next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Setting Up Coral this skillHuman-Agent-Society/CORAL | 1.1k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 36 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 796 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
- Official
Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
- Official
Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
More from Human-Agent-Society/CORAL
Creating A Coral Task
Human-Agent-Society/CORAL
Author a new CORAL task — the three pieces that must line up (task.yaml, seed/, a packaged grader/), the coral init → coral validate → smoke-test loop, and how to pick a grader pattern (stdout…
Running Coral Experiments
Human-Agent-Society/CORAL
Run and manage CORAL experiments from the operator side — launch agents with coral start (dotlist overrides, model/count, tmux vs local), monitor with coral status / coral log / coral show / the web…
Coral Debug
Human-Agent-Society/CORAL
Verify and debug changes to CORAL itself — smallest reproduce loop per area (grader / daemon / CLI / hooks / manager / workspace / hub / template / config / web), where to look when something breaks…
Coral New Task
Human-Agent-Society/CORAL
End-to-end recipe for adding a new task under examples/ — the three pieces that have to line up (task.yaml, seed/, and grader/), what to put in each, the TaskGrader API surface, the coral validate →…
Promoting Dev To Main
Human-Agent-Society/CORAL
A skill your agent uses when preparing, reviewing, resolving conflicts for, or merging a CORAL release pull request from the long-lived dev branch into main.
Coral Extend
Human-Agent-Society/CORAL
Add a new component to the CORAL framework itself — a new agent runtime under coral/agent/builtin/ (claudecode/codex/cursoragent style), a new CLI command in coral/cli/, a new bundled skill or…
Related
Categories
Questions about Setting Up Coral
What does Setting Up Coral do?
One-time machine setup after installing the coral CLI — register local agent runtimes as named bindings with coral setup / coral setup agent, validate them with coral agents doctor (incl. Setting Up Coral is an agent skill from Human-Agent-Society/CORAL. One-time machine setup after installing the coral CLI — register local agent runtimes as named bindings with coral setup / coral setup agent, validate them with coral agents doctor (incl.
When should I use Setting Up Coral?
Setting Up Coral fits situations like: the user is configuring which agent runtimes/models coral can use; hits a runtime not found / auth error when starting a run; asks how to set up claude/codex/cursor for coral.
How do I install Setting Up Coral in Claude Code?
Run `npx skills add Human-Agent-Society/CORAL --skill setting-up-coral -a claude-code`. Or copy the skill folder (plugin/skills/setting-up-coral in Human-Agent-Society/CORAL) into .claude/skills/setting-up-coral in your project. Claude Code loads it when a task matches its description.
How do I install Setting Up Coral in Codex?
Run `npx skills add Human-Agent-Society/CORAL --skill setting-up-coral -a codex`. Or copy the skill folder (plugin/skills/setting-up-coral in Human-Agent-Society/CORAL) into .agents/skills/setting-up-coral in your project. Codex loads it when a task matches its description.
Can I use Setting Up Coral in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Human-Agent-Society/CORAL --skill setting-up-coral -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/setting-up-coral, .gemini/skills/setting-up-coral, .github/skills/setting-up-coral and .opencode/skills/setting-up-coral in your project.
What does Setting Up Coral need to run?
Going by SKILL.md and its folder, Setting Up Coral needs the command-line tools its instructions call (codex and opencode).
Does Setting Up Coral access the network?
SKILL.md names 1 domain. As links in the text: coral.compounding-intelligence.ai. This is read from the text; nothing was executed.
Is Setting Up Coral safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Setting Up Coral use?
Setting Up Coral is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Setting Up Coral use?
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Setting Up Coral?
Skills that share tags, products or a category with Setting Up Coral: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Setting Up Coral?
Human-Agent-Society (a GitHub organization) maintains it in Human-Agent-Society/CORAL, which has 1,060 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 8, 2026.
Source: Human-Agent-Society/CORAL on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.