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.
npx agentmods add skills/bumblebiber/hmem/hmem-using-hmemnpx skills add Bumblebiber/hmem --skill hmem-using-hmemgit clone --depth 1 https://github.com/Bumblebiber/hmemWrote 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.
[](https://agentmods.dev/skills/bumblebiber/hmem/hmem-using-hmem)<a href="https://agentmods.dev/skills/bumblebiber/hmem/hmem-using-hmem"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-using-hmem.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00038 | $0.01118 |
| Opus 5 | $0.00019 | $0.00559 |
| Sonnet 5 | $0.00008 | $0.00224 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
hmem-using-hmem 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using hmem Skills
The Rule
Before searching, looking up, or exploring anything — dispatch via hmem-dispatch. Before responding to the user about something you had to find — dispatch first, synthesize after.
This is not optional. A 3-line grep dispatched is better than a slow main-context search that pollutes the conversation.
Skill Decision Table
| When you want to... | Use |
|---|---|
| Find a file, function, or code pattern | hmem-dispatch |
| Check if a plan, spec, or doc exists | hmem-dispatch |
| Answer "does X exist?" or "find Y" | hmem-dispatch |
| Search hmem for past decisions/lessons | hmem-recall |
| Run 2+ independent tasks at once | hmem-dispatch (multiple agents) |
| Store a new insight, lesson, or decision | hmem-write |
| Load project context at session start | hmem-session-start |
| Load context for a specific topic | hmem-context |
| Create a new project (P-entry) in hmem | hmem-new-project |
| Start curation / cleanup of memory | hmem-curate |
| Migrate O-entries to new format | hmem-migrate-o |
Targeted vs. Exploratory
Not all Bash calls need dispatching. The key distinction:
| Type | Characteristics | Action |
|---|---|---|
| Targeted | Known path/pattern, single command, result ≤3 lines | Run directly |
| Exploratory | Open-ended, multiple locations, result unknown | Dispatch |
Targeted (OK to run directly): find /home/username -name "settings.json" -path "*claude*" — one known location, one expected result.
Exploratory (must dispatch): grep -r "functionName" ~/projects/ across repos, or "where is X defined?" without knowing which file.
When in doubt: if you'd be surprised by the output → dispatch it.
Red Flags
These thoughts mean STOP — dispatch instead:
| Thought | Reality |
|---|---|
| "I'll just grep this quickly" | Is it exploratory? Dispatch. Is it one targeted command with predictable output? Run it. |
| "Let me run find real fast" | Known path + expected result → OK. Unknown territory → dispatch. |
| "It's only one Bash call" | Targeted (≤3 lines expected) → fine. Exploratory → dispatch. |
| "This is too small to dispatch" | Dispatching 2-line tasks is fine and fast. |
| "I need to check the codebase first" | Dispatch the check. |
| "Let me read this file to see what's there" | Dispatch it. You only need the result. |
| "I'll search memory quickly myself" | Use hmem-recall instead. |
| "I remember how this works" | Skills evolve. Invoke the skill. |
| "I'll write the P-entry manually with write_memory" | Use hmem-new-project. It handles schema, O-entry linking, and section setup. |
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.
- 5d ago First seen · 81 lines · 38 tokens per session scan A 54585b2deb6a
hmem-using-hmem is a skill published in the GitHub repository Bumblebiber/hmem (23 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,118 once invoked, about $0.0002 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.
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.
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"…
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…
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.
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…
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.