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.
git clone --depth 1 https://github.com/kangig94/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/plugins/kangig94/coral/clients)<a href="https://agentmods.dev/plugins/kangig94/coral/clients"><img src="https://agentmods.dev/badge/plugins/kangig94/coral/clients/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/plugins/kangig94/coral/clients"><img src="https://agentmods.dev/badge/plugins/kangig94/coral/clients.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
coral 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 2d 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.
What it actually says
{
"name": "coral",
"version": "0.10.21",
"description": "Claude Code plugin - structured agents with Codex and Claude CLI bridges, plus deterministic workflow orchestration",
"author": {
"name": "kangig94"
},
"repository": "https://github.com/kangig94/coral",
"homepage": "https://github.com/kangig94/coral",
"license": "MIT",
"keywords": [
"claude-code",
"plugin",
"agents",
"codex",
"claude",
"wait",
"workflow",
"bridge"
],
"skills": "./skills/",
"hooks": "./hooks/claude.json"
}
What it installs
The manifest is a name and a version. 12 skills, 10 agents travel with it, and installing the plugin installs all of them — 593 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill plan A 22 tokens
- Skill preplan A 22 tokens
- Skill ralph A 17 tokens
- Skill pathfind A 15 tokens
- Skill analyze A 25 tokens
- Skill statusline A 10 tokens
- Skill equip A 12 tokens
- Skill code-simplify A 23 tokens
- Skill bugfix A 20 tokens
- Skill bid A 14 tokens
- Skill discuss A 16 tokens
- Skill init-project C 17 tokens
- Agent persona-generator A 25 tokens
- Agent pioneer A 19 tokens
- Agent resolver A 60 tokens
- Agent scanner A 55 tokens
- Agent debugger A 19 tokens
- Agent red-attacker A 20 tokens
- Agent architect A 49 tokens
- Agent critic A 41 tokens
- Agent gap-finder A 68 tokens
- Agent workflow-literal A 24 tokens
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.
- 2d ago Changed 3504f18d1746
- 4d ago Changed e5efd88bb80e
- 14d ago Changed 42de2a42413a
- 17d ago Changed 26a1470c0860
- 19d ago Changed 5b95a5d69b3f
- 20d ago Changed 82fff42dbe12
- 22d ago Changed 20b3b69419a2
- 29d ago Changed 88cb6b8778db
- 1mo ago Changed f00de925e3fc
- 1mo ago First seen · 24 lines scan A bb282c01d990
coral is a plugin published in the GitHub repository kangig94/coral (11 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
saas-builder
Build a complete, professional digital product end to end — discovery, architecture, multi-tenancy, secure backend, auth, RLS audit, payments, integrations, AI features, performance, accessibility, SEO, and deploy — not generic AI output. A router skill asks 2-3 questions (English or Spanish), then activates the right.
saas-builder
22 skills to build digital products end to end — discovery, architecture, multi-tenancy, secure backend, auth, RLS audit, payments, integrations, AI features, performance, accessibility, SEO, deploy, plus anti-slop frontend and image-to-code. Carries field notes: failures from production apps that passed every test. A.
merismos
Take as yours a plan cutting one autonomous goal into units, each with its checks, accepted gaps, and held judgments — /apportion (μερισμός: an apportionment).
brana
AI development system — skills, agents, and hooks for systematic software engineering with Claude Code.
remotion
Remotion video creation skills — best practices, animations, audio, captions, 3D, and more for building programmatic videos with React.
google-apps-script
Comprehensive Google Apps Script development guide covering SpreadsheetApp, DocumentApp, GmailApp, DriveApp, CalendarApp, FormApp, SlidesApp, triggers, and Workspace automation.