hmem-search

hmem-search is a skill for Claude Code, Codex from Bumblebiber/hmem. It costs 79 tokens per session (1,282 once invoked), scanned A, original, MIT.

A memory-search procedure for finding past discussions, definitions, schemas, or decisions when no exact hmem entry ID is provided.

In plain words
What is it for?
Searching with keywords and date ranges, dropping restrictive filters, trying related wording, and locating relevant hmem records.
Why use it?
It searches documented project knowledge before asking the user for information that may already be stored.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-search.svg)](https://agentmods.dev/skills/bumblebiber/hmem/hmem-search)
Your own site
<a href="https://agentmods.dev/skills/bumblebiber/hmem/hmem-search"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,282 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 $0.00079 $0.01282
Opus 5 $0.00039 $0.00641
Sonnet 5 $0.00016 $0.00256
Haiku 4.5 $0.00008 $0.00128

Measured 6d ago against content hash 5954c5b67439, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hmem-search 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 6d 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-search/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When the user references past context without pinning it to an ID, or when looking up definitions, schemas, or decisions stored in hmem — convert the intent into a targeted read_memory query.

Workflow

  1. Extract from the prompt:

    • Keywords — distinctive nouns, project names, error fragments, schema names. Skip filler like "wir", "neulich", "besprochen", "Schema für".
    • Time hint — map to after/before range using the current date as anchor. "gestern" → narrow (−1 to 0d), "letzte Woche" → medium (−10 to −3d), "neulich"/"vor kurzem" → generous (−21d). No time hint → skip the range.
  2. First search:

    read_memory({ search: "<keywords>", after: "<ISO>", before: "<ISO>" })
    

    Keywords as a single space-separated string. Use ISO dates (2026-04-11), not relative forms.

  3. If results are empty or off-topic — work through this sequence immediately, without waiting:

    a) Drop time filter, keep keywords Time hints from humans are fuzzy; the memory may sit just outside the window.

    b) Try term variations — systematically, not just once The stored entry may use a different phrasing than what the user said. Try all that apply:

    • German ↔ English: "Schema" → "schema", "Entscheidung" → "decision", "Fehler" → "error"
    • Abbreviations or expansions: "H-Schema" → "H-Entry Schema", "O-Eintrag" → "O-entry"
    • Compound splits: "Standardschema" → "Standard Schema", "Checkpoint-Strategie" → "checkpoint strategy"
    • Synonyms: "Kollision" → "conflict", "Struktur" → "structure", "Vorlage" → "template"
    • Broader category: "H-Standardschema" → "H-entry", "entry schema", "Human schema"
    • Related prefix: if the topic is about a specific entry type (H, P, E, I…), search that prefix directly via read_memory({ prefix: "R", search: "H" })

    Don't try one variation and stop. Run 2–3 variations before concluding nothing was found.

    c) Switch store Default is personal. If the topic is work-related and personal turned up nothing, try store: "company".

Read the full file on GitHub · 82 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. 6d ago First seen · 82 lines · 79 tokens per session scan A 5954c5b67439

Subscribe to this mod's changes

hmem-search is a skill published in the GitHub repository Bumblebiber/hmem (23 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,282 once invoked, about $0.0004 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