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 agentmods add instructions/corezoid/corezoid-ai-plugin/claude-mdgit clone --depth 1 https://github.com/corezoid/corezoid-ai-pluginWrote 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/instructions/corezoid/corezoid-ai-plugin/claude-md)<a href="https://agentmods.dev/instructions/corezoid/corezoid-ai-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/corezoid/corezoid-ai-plugin/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02573 | $0.02573 |
| Opus 5 | $0.01287 | $0.01287 |
| Sonnet 5 | $0.00515 | $0.00515 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade B, and why
corezoid-ai-plugin CLAUDE.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
Skills and commands use `${CLAUDE_PLUGIN_ROOT}` to reference files relative to the installed plugin root. This token is a host-side text substitution that Claude Code performs at skill-load time (see anthropics/claude-co How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Purpose
This is a Claude Code / Codex / Kiro plugin (@corezoid/corezoid-ai-plugin) that gives the AI the knowledge and tools to create, edit, and review Corezoid BPM processes directly from the IDE. The repo ships:
- Static skills (
plugins/corezoid/skills/*/SKILL.md+ reference docs, JSON samples). - Plugin manifests for Claude Code, Codex, Kiro, and the agents marketplace, plus
POWER.mdfor the Kiro Powers registry. - A Go-based MCP server (
convctl) inplugins/corezoid/mcp-server/that exposes Corezoid operations as MCP tools. It has real tests (go test -race), golden tests for layout and lint, integration tests, and a release pipeline that builds signed multi-platform binaries.
Plugin Development Commands
# Publish a new version (triggers GitHub Actions on tag push)
git tag v1.x.x && git push origin v1.x.x
# Install the plugin locally for testing
npm install -g .
claude plugin install @corezoid/corezoid-ai-plugin
convctl MCP server (bundled in this plugin)
The MCP server is bundled as Go source at plugins/corezoid/mcp-server/. All operations are exposed as MCP tools — no separate installation required, only Go must be available. The server starts automatically via .mcp.json.
To test the MCP server without Claude:
cd plugins/corezoid/mcp-server && npx @modelcontextprotocol/inspector go run . mcp-server
MCP server: build, test, lint
Run these from plugins/corezoid/mcp-server/:
go build ./... # compile
go vet ./... # static analysis
go test -race -coverprofile=coverage.out ./... # tests with race detector
go tool cover -func=coverage.out # coverage summary
Golden tests (layout coordinates in testdata/golden/layout_*.json, lint output in testdata/golden/lint_*.txt) are regenerated with the -update flag after an intentional algorithm change:
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.
- today Changed · +2 lines · +45 tokens per session f6af754e145b
- 5d ago First seen · 164 lines · 2,528 tokens per session scan B e4016cdbad39
corezoid-ai-plugin CLAUDE.md is an instructions file published in the GitHub repository corezoid/corezoid-ai-plugin (73 stars, last pushed today), licensed MIT. It adds 2,573 tokens to every session, about $0.0129 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
supergraph AGENTS.md
AGENTS.md instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
project-legibility AGENTS.md
AGENTS.md instructions for perhapsspy/project-legibility, covering agents.md and 검증.
lianhuanhua-skills AGENTS.md
Instructions for littlewindy123/lianhuanhua-skills, covering agents.md, project goal, architecture rules, commands and before committing.
avoid-overkill AGENTS.md
AGENTS.md instructions for 6Kmfi6HP/avoid-overkill: This repository packages a reusable Agent Skill and plugin manifests.
ai-plugin GEMINI.md
Gemini CLI instructions for PostHog/ai-plugin, covering posthog extension, available tool categories and guidelines.
quantcoder-plugin GEMINI.md
Gemini CLI instructions for nutdnuy/quantcoder-plugin: Follow AGENTS.md. Use skills/quantcoder-research/SKILL.md as the primary task guide for QuantCoder research-paper to QuantConnect workflows.