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 skills add christopherkarani/Wax --skill wax-mcpgit clone --depth 1 https://github.com/christopherkarani/WaxWrote 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/christopherkarani/wax/wax-mcp)<a href="https://agentmods.dev/skills/christopherkarani/wax/wax-mcp"><img src="https://agentmods.dev/badge/skills/christopherkarani/wax/wax-mcp/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/skills/christopherkarani/wax/wax-mcp"><img src="https://agentmods.dev/badge/skills/christopherkarani/wax/wax-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 40 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium MCP Rug Pull · line 32 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00055 | $0.01152 |
| Opus 5 | $0.00028 | $0.00576 |
| Sonnet 5 | $0.00011 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade B, and why
wax-mcp 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 agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Codex | HTTP URL in `~/.codex/config.toml` + copy this skill to `~/.codex/skills/wax-mcp` | How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wax MCP
The MCP server instructions field is the playbook. Do not restate a second
lifecycle here.
Daily tools: session_open, remember, recall, session_close, stats,
memory_get, compact_context, session_resume. Aliases stay callable.
WAX_MCP_TOOLS=full lists the rest.
Close harvests. Do not call memory_promote or memory-maintain in the agent
loop. Never invent a session_id or put it in metadata.
Recall defaults to the current project after project/repo resolution. Empty
project recall is a miss, not “I have no memory.” Supplying both project
and repo requires both exact tags. Pass scope=global only for
cross-project retrieval (person facts, standing preferences). For person
facts pass memory_types: ["user_preference"] so project lessons do not
crowd the lane. Global searches the entire local store with no
current-project rank boost. It is not an authorization boundary.
Pass conversation_id (host chat/session id) on session_open. Do not
close between turns or after compaction. If omit-id session_close fails
after reconnect, pass the saved UUID.
Pasteable host rules: references/project-rules.md.
This is not the Swift framework skill. For embedding Wax in Swift apps, use
Resources/skills/public/wax.
Install / Host Setup
Stage binaries once:
npx -y waxmcp@latest install
Then wire the host, not a new prompt:
| Host | What to do |
|---|---|
| Claude Code | swift run --traits MCPServer wax-cli mcp install --scope user then claude install-skill ~/.local/share/waxmcp/skills/wax-mcp |
| Codex | HTTP URL in ~/.codex/config.toml + copy this skill to ~/.codex/skills/wax-mcp |
| Cursor | HTTP URL in ~/.cursor/mcp.json + paste references/project-rules.md |
| Hermes | Native memory.provider: wax-memory only (npx -y waxmcp@latest install-hermes-plugin). Never plugins.enabled. Never also mcp_servers.wax; do not also register generic MCP or this generic skill. Call wax_remember / wax_recall / wax_stats with no Wax UUID. |
| OpenClaw | HTTP + memory plugin + paste the SOUL.md stanza into workspace SOUL.md (replace existing ## Memory (Wax)) |
| Grok CLI | HTTP URL http://127.0.0.1:3000/mcp. Do not use GROK_CONFIG / GROK_CONFIG_PATH to retarget Wax. Isolated labs: project .grok/config.toml + --leader-socket (or --no-leader / GROK_HOME) — see Resources/docs/wax-mcp-hosts.md. |
| Other | HTTP URL + paste the AGENTS.md fence from references/project-rules.md |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · +40 lines bfa0910905e7
- 5d ago Changed 9c1f8058de52
- 6d ago Changed · -81 lines · -19 tokens per session 566d84787499
- 10d ago First seen · 147 lines · 74 tokens per session scan B 2cdbd3f3bf4f
wax-mcp is a skill published in the GitHub repository christopherkarani/Wax (789 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,152 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
capturing-learnings
Records a real failure-and-fix pair as a project-local lesson, with the specifics that make it recognisable next time. Use when a bug, leakage mistake, or validation error was found and corrected and should not recur. Use when someone asks to save what was learned from an experiment that went wrong.
developing-with-streamlit
Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st.…
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
distill-feedback
A process for turning corrections you give an agent into lasting working rules. It reviews saved conversations and asks for approval before changing those rules.
ml-expert
Expert-level machine learning, deep learning, model training, and MLOps. Use when the user mentions machine learning, deep learning, neural networks, MLOps, or data science, or when the task involves Machine Learning Fundamentals, Data Preparation, or Model Training.
fast-dash
Build a Fast Dash web app from a Python function. Use when the user wants to turn a function into an interactive app, add a UI to an existing function, or build a dashboard / form / wizard. Fast Dash infers UI components from type hints, so a well-typed function becomes an app with one decorator.