zer0dex: Skill for Claude Code

.agents/skills/zer0dex/SKILL.md

zer0dex is a skill for Claude Code, Codex from hermes-labs-ai/zer0dex. It costs 57 tokens per session (720 once invoked), scanned A, original, Apache-2.0.

A local memory pattern for AI agents that combines a readable Markdown index with semantic search in a local vector store. Semantic search finds related meaning rather than only matching exact words, and the stored memory is queried before each model request.

In plain words
What is it for?
Use it to prototype local, persistent agent memory, seed and query recalled information, and run a local memory server before model calls.
Why use it?
It helps an agent recall information across projects without depending on a hosted memory service. Combining an index with vector search addresses limits of using either flat files or vector search alone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is hermes-labs-ai/zer0dex's own configuration. It tells Claude Code and Codex how to work on zer0dex itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zer0dex configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hermes-labs-ai/zer0dex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hermes-labs-ai/zer0dex/main/.agents/skills/zer0dex/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hermes-labs-ai/zer0dex

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 zer0dex

README.md
[![agentmods](https://agentmods.dev/badge/skills/hermes-labs-ai/zer0dex/zer0dex/github.svg)](https://agentmods.dev/skills/hermes-labs-ai/zer0dex/zer0dex)
Your own site
<a href="https://agentmods.dev/skills/hermes-labs-ai/zer0dex/zer0dex"><img src="https://agentmods.dev/badge/skills/hermes-labs-ai/zer0dex/zer0dex/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.

agentmods 80×15 button for zer0dex

Your own site · 80×15
<a href="https://agentmods.dev/skills/hermes-labs-ai/zer0dex/zer0dex"><img src="https://agentmods.dev/badge/skills/hermes-labs-ai/zer0dex/zer0dex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 720 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00057 $0.00720
Opus 5.5 $0.00023 $0.00288
Sonnet 5.5 $0.00011 $0.00144
Haiku 4.5 $0.00006 $0.00072

Measured 1mo ago against content hash f9ad1bf047a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zer0dex 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 1mo 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.

.agents/skills/zer0dex/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

zer0dex

zer0dex is a local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic retrieval from a local vector store, queried before each message. It targets cross-project recall where flat memory files or vector-only RAG fall short. Reference implementation, local-first, Alpha (0.1.x line).

Use it for

  • Combining a compressed markdown memory index with vector retrieval in one local loop
  • Running a local memory server an agent host queries before model calls
  • Seeding and querying persistent memory without standing up a hosted service
  • Prototyping the dual-layer (index + vector) pattern before adopting a heavier memory stack

Do not use it for

  • A hosted or multi-tenant memory platform
  • A governance or safety layer for memory content
  • Proof that any benchmark result transfers unchanged to a different corpus or workload

Quickstart

pip install zer0dex
zer0dex check

Or without installing, via uv:

uvx zer0dex check

Real output from a working local setup (Ollama running, models pulled):

✅ Ollama is running at http://localhost:11434
✅ Model present: nomic-embed-text
✅ Model present: mistral:7b
✅ mem0ai is importable
✅ chromadb is importable
✅ Python Ollama client is importable

Commands

zer0dex check              # validate prerequisites (Ollama, models, mem0ai, chromadb)
zer0dex init                # initialize a new memory store
zer0dex seed --source <path> # seed from markdown files
zer0dex serve               # start the local memory server
zer0dex query "<text>"      # query memories
zer0dex status              # check server health

Output shape

  • check: per-prerequisite pass/fail lines (Ollama reachability, model presence, library importability)
  • serve / status: local HTTP health and query results
  • query: ranked memory matches from the vector store

Common gotchas

  • check fails closed if Ollama isn't running locally or the required models (nomic-embed-text, an LLM tag) aren't pulled — read the specific failing line, it names the missing prerequisite.
  • This is a reference pattern, not a managed service: there is no built-in multi-user isolation or remote auth.
  • 0.1.x is a developer-preview compatibility line; check docs/compatibility.md before pinning across upgrades.

Read the full file on GitHub · 88 lines

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. 1mo ago Changed f9ad1bf047a9
  2. 1mo ago First seen · 88 lines · 57 tokens per session scan A a4223ced3336

Subscribe to this mod's changes

zer0dex is a skill published in the GitHub repository hermes-labs-ai/zer0dex (64 stars, last pushed 18d ago), licensed Apache-2.0. It adds 57 tokens to every session and 720 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-16.

Related

zer0dex compared with skills from other repositories

zer0dex next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
zer0dexhermes-labs-ai/zer0dexSkill6418d agoApache-2.0A57Claude Code, Codex
xerjxerj-org/xerjSkill19kyesterdayApache-2.0A38Claude Code, Codex
goodmem:helpPAIR-Systems-Inc/goodmem-claude-code-pluginSkill92d agoMITA46Claude Code
strata-memorySherryLi-vc/strata-memorySkill05d agoMITB76Claude Code, Codex
knowledge-orgbojieli/ai-agent-bookSkill57k29d agoApache-2.0A96Claude Code, Codex
memory-to-skillzilliztech/memsearchSkill2.8kyesterdayMITA82Claude Code, Codex
install-openviking-memoryvolcengine/OpenVikingSkill42kyesterdayAGPL-3.0A191Claude Code, Codex