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/commitnpx skills add corezoid/corezoid-ai-plugin --skill commitgit clone --depth 1 https://github.com/corezoid/corezoid-ai-pluginWhat 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 | $0.00051 | $0.00703 |
| Opus 5 | $0.00026 | $0.00351 |
| Sonnet 5 | $0.00010 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
commit 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- commit — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit with auto version bump
This project follows semver. Every commit must include a version bump in:
plugins/corezoid/.claude-plugin/plugin.json.claude-plugin/marketplace.json
Step 1 — Inspect changes
Run in parallel:
git diff HEAD— see what changedgit status— see untracked filesgit log -5 --oneline— see recent commit style
Step 2 — Determine bump type
| Change type | Bump |
|---|---|
| New feature, new tool, new skill, new node type | minor (2.3.x → 2.4.0) |
| Bug fix, doc update, text fix, refactor | patch (2.3.x → 2.3.x+1) |
| Breaking change, major redesign | major (2.x.x → 3.0.0) |
Read current version from plugins/corezoid/.claude-plugin/plugin.json.
Step 3 — Update versions
Update the "version" field in both files to the new version:
plugins/corezoid/.claude-plugin/plugin.json.claude-plugin/marketplace.json
Step 3.5 — Update CHANGELOG.md
Prepend a new entry at the top of CHANGELOG.md (right after the # Changelog heading) following the existing format:
## [<new_version>]
- <bullet summarising what changed — one line per logical change>
Derive the bullets from the staged diff: group related changes into a single readable line each. Keep it concise — one sentence per item.
Step 3.6 — Update README.md
Review the diff for changes that affect README content and update the relevant sections in README.md:
| What changed | What to update in README.md |
|---|---|
New or removed skill (SKILL.md added/deleted) |
What it does table — add/remove the row |
| New or removed MCP tool | MCP Tools table — add/remove the row; Architecture code block if the tool group changes |
| New plugin directory or top-level file | Project structure code block |
| Breaking change to install/config | Installation or Configuration section |
If none of the above apply (e.g. pure bug fix, refactor, doc-only change inside an existing skill), skip this step — do not touch README.md.
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.
- yesterday First seen · 78 lines · 51 tokens per session scan A a52b8b151d1d
commit is a skill published in the GitHub repository corezoid/corezoid-ai-plugin (73 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 703 once invoked, about $0.0003 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.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
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.
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…