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 skills add Bumblebiber/hmem --skill hmem-migrate-ogit 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-migrate-o)<a href="https://agentmods.dev/skills/bumblebiber/hmem/hmem-migrate-o"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-migrate-o/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bumblebiber/hmem/hmem-migrate-o"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-migrate-o.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00076 | $0.01701 |
| Opus 5.5 | $0.00030 | $0.00680 |
| Sonnet 5.5 | $0.00015 | $0.00340 |
| Haiku 4.5 | $0.00008 | $0.00170 |
Grade A, and why
hmem-migrate-o 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 2mo 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hmem-migrate-o — O-Entry Migration to Project-Bound Structure
Prerequisite: This skill uses
move_nodesandrename_idfrom the hmem-curate MCP server. Tell the user to activate it via/mcpbefore proceeding.
This is a one-time migration from the old flat O-entry format to the new 5-level hierarchy where each O-entry is permanently bound to a P-entry (O0048 belongs to P0048).
What Changes
Before (old format):
- New O-entry created per session, loosely linked via
linksfield - Flat structure: L2 (exchange) -> L4 (user msg) -> L5 (agent msg)
activeflag on O-entries to track current session
After (new format):
- One O-entry per project, ID matches P-entry (O0048 <-> P0048)
- 5-level hierarchy: L2 (session) -> L3 (batch) -> L4 (exchange) -> L5 (user/agent)
- No
activeflag needed — O is derived from the active P - P0000/O0000 exist as "Non-Project" catch-all
Step 1: Pre-Migration Check
Understand what you're working with before changing anything.
hmem --version # must be >= 5.3.0
Then use read_memory() to see current O-entries. Check:
- How many O-entries exist?
- Which P-entries are they linked to?
- Are any O-entries already using the new format (have L3 depth=3 nodes)?
If the version is too old, run /hmem-update first.
Step 2: Backup
Create a backup of the hmem database before migrating. This is critical — the migration rewrites entry IDs.
# Find the active hmem file
HMEM_FILE=$(find ~/.hmem -name "*.hmem" -not -path "*/Agents/*" | head -1)
echo "Backing up: $HMEM_FILE"
cp "$HMEM_FILE" "${HMEM_FILE}.pre-migration-backup"
# Also backup agent-specific hmem files
find ~/.hmem/Agents -name "*.hmem" -exec sh -c 'cp "$1" "$1.pre-migration-backup"' _ {} \;
Verify backups exist before continuing.
Step 3: Run Migration
The migration script handles everything:
hmem migrate-o-entries
This will:
- Create P0000 "Non-Project" and O0000 catch-all if they don't exist
- For each existing O-entry:
- Find its linked P-entry via the
linksJSON field - Rename it to match the P-entry's sequence number (e.g., O0042 linked to P0048 becomes O0048)
- Handle ID conflicts by moving blockers to temporary IDs (O9XXX range)
- Tag all migrated entries with
#legacy
- Find its linked P-entry via the
- Tag unlinked O-entries as
#legacy(they'll go to O0000 eventually) - Clear all
activeflags from O-entries
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.
- 2mo ago First seen · 175 lines · 76 tokens per session scan A 0bcb9ac7c3bc
hmem-migrate-o is a skill published in the GitHub repository Bumblebiber/hmem (24 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 1,701 once invoked, about $0.0003 per session on Opus 5.5. 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.
nornweave-api
Give AI agents their own email inboxes using the NornWeave API. Use when building email agents, sending/receiving emails programmatically, managing inboxes, retrieving threads, searching messages, or integrating with email providers (Mailgun, SES, SendGrid, Resend). NornWeave provides LLM-ready markdown parsing and…
faf-expert
Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, syncing project.faf into CLAUDE.md, faf-cli commands, MCP server configuration, or AI-readiness scoring (0-100%). Updated for v2.8.0 Tool Visibility System.
knowledge-base
Retrieves and updates project-specific prompt knowledge from comparison evidence and user feedback. Use only for prompt analysis or post-comparison learning within a Rashomon evaluation.
post-cortex-memory
Long-term project memory through the post-cortex MCP server (tools named session, semanticsearch, updateconversationcontext, assemblecontext, queryconversationcontext, getstructuredsummary, manageworkspace, manageentity, admin). Use it whenever those tools are available and the work could benefit from what was learned…
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"…