hmem-update

hmem-update is a skill for Claude Code, Codex from Bumblebiber/hmem. It costs 82 tokens per session (11,599 once invoked), scanned C, original, MIT.

An update routine for hmem, a memory system for coding-agent work, and its encrypted synchronization service.

In plain words
What is it for?
Checking versions, updating the hmem package, synchronizing skills, applying required migrations, verifying hooks, and running a smoke test.
Why use it?
It keeps the installed tools, skills, migrations, hooks, and configuration aligned during an upgrade.

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/bumblebiber/hmem/hmem-update
Any agent
npx skills add Bumblebiber/hmem --skill hmem-update
Clone the repo
git clone --depth 1 https://github.com/Bumblebiber/hmem

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 hmem-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-update.svg)](https://agentmods.dev/skills/bumblebiber/hmem/hmem-update)
Your own site
<a href="https://agentmods.dev/skills/bumblebiber/hmem/hmem-update"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,599 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 3 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 $0.00082 $0.11599
Opus 5 $0.00041 $0.05799
Sonnet 5 $0.00016 $0.02320
Haiku 4.5 $0.00008 $0.01160

Measured 4d ago against content hash 9eff6deb3f3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

hmem-update scanned grade C with 3 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **Server:** sudo access, package manager quirks, which user Claude runs as

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/settings.json | grep -A5 hooks

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls ~/.claude/skills/hmem-*/SKILL.md # Claude Code
skills/hmem-update/SKILL.md · 1,069 lines

How it starts

The opening of the file, as written. The whole thing — 1,069 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/hmem-update — Update Routine

Drives the full update flow for hmem and hmem-sync: detects the current version, runs npm update -g if outdated, syncs skill files, applies any migrations, verifies hooks and configs, runs the smoke test. Every step is important — do not skip steps.

Package naming note: The npm package is hmem (formerly its-over-9k, before that hmem-mcp). The installed CLI is still hmem, the MCP server tools still use the hmem prefix, and the GitHub repo is Bumblebiber/hmem. The its-over-9k name now belongs to a separate project (the o9k efficiency meta-framework) — do not npm-update via that name anymore. Always use the current package name (hmem) for npm commands.

Version mapping: The renames reset the version line twice:

hmem-mcp (legacy) its-over-9k (1.x line) hmem (current)
up to 7.4.x 1.0.0 – 1.3.8 8.0.0+

Steps 2d–2l below describe migrations only relevant when upgrading from the legacy 5.x/6.x/7.x line. Skip them if your installed version is 1.x or 8.x — they are already baked into the rename baseline.

Upgrading from its-over-9k 1.x: uninstall the old package and install the new name — npm update -g its-over-9k will never reach 8.0:

npm uninstall -g its-over-9k
npm install -g hmem
npx hmem update-skills        # also removes the old o9k-* skill folders

The skills were renamed o9k-*hmem-* in 8.0.0. update-skills cleans up stale o9k-* folders automatically.


Step 1: Version Check

Determine the current and latest version:

hmem --version                            # current installed version (e.g. "hmem 1.2.1")
npm view hmem version              # latest on npm
npm view hmem versions --json      # all versions (for changelog range)

Read the changelog for the version range:

cd ~/projects/hmem && git log --oneline <old-tag>..HEAD  # if local repo exists

Read the full file on GitHub · 1,069 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. 4d ago First seen · 1,069 lines · 82 tokens per session scan C 9eff6deb3f3d

Subscribe to this mod's changes

hmem-update is a skill published in the GitHub repository Bumblebiber/hmem (23 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 11,599 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, enumerates other installed skills). 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

kayba-ace

This skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.

kayba-ai/agentic-context-engine · 0 tokens

rekal-init

Bootstrap rekal memory for a project. Scans the codebase for architecture, conventions, dependencies, workflows, and config, then stores durable knowledge as properly typed, tagged, deduplicated memories. Use when starting rekal on a new project, or when user says "init rekal", "bootstrap memory", "populate rekal"…

janbjorge/rekal · 83 tokens

rekal-save

End-of-session memory capture with deduplication. Extracts durable knowledge, checks for duplicates, stores or replaces as appropriate. Use whenever a session wraps up, a task finishes, or the user says goodbye/thanks/done. Also use when significant preferences, decisions, or discoveries emerge mid-session. Make sure…

janbjorge/rekal · 79 tokens

rekal-usage

Operational guide for rekal memory tools. Precise rules for when/how to call each tool, with exact parameters and decision trees. Use at session start, when onboarding to a rekal workspace, or when user asks "how do I use rekal", "what rekal tools", "help with memory". Trigger: /rekal-usage.

janbjorge/rekal · 75 tokens

rekal-hygiene

Periodic memory maintenance and cleanup. Finds duplicates, contradictions, and quality issues in the memory database. Proposes fixes for user approval. Never auto-deletes or auto-modifies. Use when user says "clean up memories", "memory maintenance", "check memory health", or invokes /rekal-hygiene. Run monthly or…

janbjorge/rekal · 77 tokens

vault-for-llm

Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.

zycaskevin/Vault-Agent-Memory · 46 tokens