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-wipenpx skills add Bumblebiber/hmem --skill hmem-wipegit 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-wipe)<a href="https://agentmods.dev/skills/bumblebiber/hmem/hmem-wipe"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-wipe.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 | $0.00064 | $0.01409 |
| Opus 5 | $0.00032 | $0.00705 |
| Sonnet 5 | $0.00013 | $0.00282 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
hmem-wipe 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wipe — Prepare & Clear Context
Follow these steps in order.
Step 0: Abort if repos touched this session have uncommitted changes
Hard gate — must complete before any other step. Wiping context with unfinished local work risks losing track of why those changes exist. The post-clear session has no memory of the chat that produced them.
Scope this check to only the repos the session actually touched — not every repo on the machine. Unrelated work on other projects is not your concern here.
-
Look back over this session's tool history and identify every file path you've modified (Edit, Write, NotebookEdit, or any Bash commands that wrote to a tracked file). If no files were modified at all, skip Step 0 entirely and proceed to Step 1.
-
For each unique path, resolve its git repo root:
git -C <path> rev-parse --show-toplevel 2>/dev/nullDedupe to a set of repo roots. Drop any path that isn't inside a repo.
-
For each repo root, check status:
git -C <repo-root> status --porcelain -
If any repo has non-empty status output:
- Do not proceed to Step 1 or beyond. Do not tell the user to
/clear. - Print the dirty file list per repo so the user sees exactly what's at risk.
- Reply with:
Wipe aborted — uncommitted changes in repo(s) you worked on this session. Commit, stash, or discard the listed files first, then re-run /wipe. (If the changes are intentional WIP you want to keep across the wipe, stash them with a clear message:
git stash push -m "WIP: <what + why>".) - End the skill.
- Do not proceed to Step 1 or beyond. Do not tell the user to
Only proceed to Step 1 when every session-touched repo is clean.
Why session-scoped, not whole-machine: other repos may have intentional WIP unrelated to this conversation — those aren't your responsibility to gate on. The risk this guard prevents is losing the why behind changes you just helped make.
Step 1: Optionally save high-value knowledge
Check checkpointMode in hmem.config.json to decide what to do:
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 · 133 lines · 64 tokens per session scan A d73308249958
hmem-wipe is a skill published in the GitHub repository Bumblebiber/hmem (23 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,409 once invoked, about $0.0003 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.