wax-memory-maintenance

wax-memory-maintenance is a skill for Claude Code, Codex from christopherkarani/Wax. It costs 18 tokens per session (258 once invoked), scanned A, original, Apache-2.0.

A maintenance guide for the Wax memory store used by the Hermes wax-memory provider. It covers checking the service, finding stored context, saving durable facts, and preserving session handoffs.

In plain words
What is it for?
It helps diagnose the memory service, search or recall stored information, save facts and decisions, record session continuity, and recover missing or disabled search functionality.
Why use it?
It reduces the risk of lost, poorly stored, or incorrectly recalled information during and between coding sessions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/christopherkarani/wax/maintenance
Any agent
npx skills add christopherkarani/Wax --skill maintenance
Clone the repo
git clone --depth 1 https://github.com/christopherkarani/Wax

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for wax-memory-maintenance

README.md
[![agentmods](https://agentmods.dev/badge/skills/christopherkarani/wax/maintenance.svg)](https://agentmods.dev/skills/christopherkarani/wax/maintenance)
Your own site
<a href="https://agentmods.dev/skills/christopherkarani/wax/maintenance"><img src="https://agentmods.dev/badge/skills/christopherkarani/wax/maintenance.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 258 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00258
Opus 5 $0.00009 $0.00129
Sonnet 5 $0.00004 $0.00052
Haiku 4.5 $0.00002 $0.00026

Measured 4d ago against content hash 213df92671b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wax-memory-maintenance 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 4d 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.

Resources/hermes/wax-memory-plugin/skills/maintenance/SKILL.md · 23 lines

What it actually says

Wax Memory Maintenance

Use when the active Hermes memory provider is wax-memory.

Checks

  1. Confirm the broker is reachable: hermes wax-memory doctor
  2. Prefer wax_recall for assembled context and wax_search for raw hits
  3. Store durable facts with wax_remember and memory_type from note, user_preference, decision, lesson, handoff, constraint, fact; task_state is session-local working state and requires an active session
  4. Write session continuity with wax_handoff; do not dump raw transcripts
  5. Use structured tools (wax_entity_upsert, wax_fact_assert, wax_facts_query) only for stable knowledge-graph facts

Recovery

  • If recall is empty, run npx waxmcp --embedder minilm --transport http
  • If vector search is disabled, rebuild both wax-cli and wax-mcp with MiniLM/Arctic traits
  • After /reset or /resume, rely on the provider session switch — do not invent a new session id
Changes

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.

  1. 4d ago First seen · 23 lines · 18 tokens per session scan A 213df92671b4

Subscribe to this mod's changes

wax-memory-maintenance is a skill published in the GitHub repository christopherkarani/Wax (790 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 258 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

dataframe-performance

Decides when pandas is fine and when to reach for Polars, plus vectorisation, dtype, and memory technique either way. Use when an operation such as a groupby, join, or apply is slow, or a script takes far longer than it should. Use when a dataset no longer fits in memory. Use when someone asks about Polars…

StamKavid/last-ds-mile · 82 tokens

ds-evaluate

Measures how a model really performs — the metric at a stated operating point, a confusion matrix, calibration, and performance broken out by slice rather than one aggregate number. Use when someone asks how well a model does on held-out data, wants precision and recall at a threshold, or wants a confusion matrix. Use…

StamKavid/last-ds-mile · 83 tokens

metric-selection

Picks the evaluation metric that matches the decision and the shape of the target, and says plainly when a familiar one is wrong. Use when someone asks whether accuracy is the right thing to report, or whether to optimise for precision or recall. Use when choosing or defending a metric for classification, regression…

StamKavid/last-ds-mile · 86 tokens

dask

Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed…

Lord1Egypt/scientific-agent-toolkit · 69 tokens

get-available-resources

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to…

Lord1Egypt/scientific-agent-toolkit · 115 tokens

polars

Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.

Lord1Egypt/scientific-agent-toolkit · 69 tokens