hmem-curate

hmem-curate is a skill for Claude Code, Codex from Bumblebiber/hmem. It costs 218 tokens per session (2,772 once invoked), scanned A, original, MIT.

A procedure for cleaning up an .hmem memory file, which stores notes and context from coding-agent work.

In plain words
What is it for?
Use it to review, reorganize, rename, merge, tag, export, or import stored project memories.
Why use it?
It identifies obsolete entries, duplicates, bad titles, and broken links while requiring a separate server because cleanup can make destructive changes.

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-curate
Any agent
npx skills add Bumblebiber/hmem --skill hmem-curate
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-curate

README.md
[![agentmods](https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-curate.svg)](https://agentmods.dev/skills/bumblebiber/hmem/hmem-curate)
Your own site
<a href="https://agentmods.dev/skills/bumblebiber/hmem/hmem-curate"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-curate.svg" alt="Measured on agentmods" height="20"></a>
Per session 218 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,772 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 5.1 $0.00218 $0.02772
Opus 5 $0.00109 $0.01386
Sonnet 5 $0.00044 $0.00554
Haiku 4.5 $0.00022 $0.00277

Measured 5d ago against content hash 8310899348b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

hmem-curate 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 5d 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.

skills/hmem-curate/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hmem Curation

Prerequisite: Activate hmem-curate MCP Server

Curation tools (memory_health, memory_stats, update_many, tag_bulk, tag_rename, move_memory, rename_id, move_nodes, export_memory, import_memory, reset_memory_cache) are in the separate hmem-curate MCP server — not in the daily hmem server. They are not available by default; curation cannot start until the user enables them.

Check the available tools first. If memory_health is not callable, tell the user:

"I need the hmem-curate MCP server to be active. It is not enabled by default because curation writes destructively. To register it once:

npx hmem mcp-add-curate

Then run /mcp to enable it, and come back. (Fallback if the hmem CLI isn't on PATH: claude mcp add hmem-curate -s user -- npx hmem-curate.)"

Wait for confirmation before proceeding. Do not attempt curation calls until the tools are available — they will fail silently or with cryptic errors. Once confirmed, continue with Step 0 below.

Curate hmem memory — mark obsolete/irrelevant/favorite, fix titles, consolidate duplicates, fix broken links.

Two modes:

  • Self-curation (default): you curate your own memory. No extra params.
  • Foreign-file curation: pass hmem_path=/absolute/path/to/file.hmem to read_memory, update_memory, memory_health, find_related. Sync and session cache are disabled. All updates land in that file.

Step 0: Health Check First

memory_health()                  # own store
memory_health(hmem_path="...")   # foreign file

Shows:

  • Broken links — entries with refs to deleted IDs
  • Orphaned entries — roots with no sub-nodes (likely draft stubs)
  • Stale favorites/pinned — not accessed in >60 days (demote or verify)
  • Broken obsolete chains[✓ID] pointing to deleted entries

Severity classification — prioritize fixes in this order:

Severity Examples Action
BLOCKER Broken links, broken obsolete chains Fix before any other curation
WARNING Orphaned stubs, stale favorites >90 days, P-entry token bloat Fix in current session
INFO Vague titles, duplicate candidates, minor tag cleanup Fix if time allows

Read the full file on GitHub · 281 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. 5d ago First seen · 281 lines · 218 tokens per session scan A 8310899348b4

Subscribe to this mod's changes

hmem-curate is a skill published in the GitHub repository Bumblebiber/hmem (23 stars, last pushed 1mo ago), licensed MIT. It adds 218 tokens to every session and 2,772 once invoked, about $0.0011 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

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