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 skills/corezoid/corezoid-ai-plugin/corezoid-initnpx skills add corezoid/corezoid-ai-plugin --skill corezoid-initgit 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/skills/corezoid/corezoid-ai-plugin/corezoid-init)<a href="https://agentmods.dev/skills/corezoid/corezoid-ai-plugin/corezoid-init"><img src="https://agentmods.dev/badge/skills/corezoid/corezoid-ai-plugin/corezoid-init.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 5.1 | $0.00086 | $0.02558 |
| Opus 5 | $0.00043 | $0.01279 |
| Sonnet 5 | $0.00017 | $0.00512 |
| Haiku 4.5 | $0.00009 | $0.00256 |
Grade A, and why
corezoid-init 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 6d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize Corezoid Environment
You are a specialist in setting up the Corezoid working environment using the corezoid MCP server.
Step 1 — Call login
Call MCP tool login with no arguments. It will guide setup in one of two modes depending on whether the client supports MCP elicitation.
Mode A — Elicitation supported (interactive forms)
The login tool handles everything automatically in sequence:
- Account URL prompt — interactive form asking for
account_url - OAuth2 — browser window opens for authentication; the token is saved to
~/.corezoid/config.json(access_tokenfield on the current Folder) - Workspace picker — fetches available workspaces and shows a dropdown; saves
workspace_id - Stage picker — lists projects then stages for selection; the chosen stage is materialized on disk as
<id>_<name>.stage/<id>_<name>.stage.json(the marker file — NOT stored inconfig.json)
Interpreting the login response
"Setup complete! ... Stage <N> selected."→ stage was picked and pulled. Proceed to Step 2."Setup incomplete: stage not selected. ..."→ elicitation was cancelled or returned no stage. Follow the instructions in the message (usually: runlist-stages+ calllogin(stage_id=…)again). Do not fall back to Mode B — the token and workspace are already saved.
Mode B — Elicitation not supported (chat-based collection)
When elicitation is unavailable, drive the setup yourself using explicit tool calls. Follow this sequence exactly — never pick a workspace, project, or stage on behalf of the user. Always present the full list and wait for the user's explicit choice.
B1 — Collect Account URL
→ Ask the user: "What is your Corezoid Account URL? (e.g. https://account.corezoid.com)"
→ Call login(account_url=<value>)
The tool opens a browser for OAuth2 authentication and saves the token to the current Folder in ~/.corezoid/config.json.
B2 — Select Workspace
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.
- 6d ago First seen · 209 lines · 86 tokens per session scan A 5cb2689661a0
corezoid-init is a skill published in the GitHub repository corezoid/corezoid-ai-plugin (73 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 2,558 once invoked, about $0.0004 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.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration in proposals and decision-facing writing. Use when the user asks to rewrite or audit a proposal, plan, research contribution, executive summary, or similar text for directness. Do not use for ordinary code work or unrelated prose.
mindtrain
Configure a private MindTrain instance, query its knowledge catalog, create user-approved training domains and knowledge points from AI dialogue or local reference libraries, and run persistent conversational training through Trainer MCP. Use when the user configures MindTrain, asks what domains or topics exist…