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-consolidategit 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-consolidate)<a href="https://agentmods.dev/skills/bumblebiber/hmem/hmem-consolidate"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-consolidate/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-consolidate"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-consolidate.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 | $0.00031 | $0.00351 |
| Opus 5 | $0.00015 | $0.00176 |
| Sonnet 5 | $0.00006 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
hmem-consolidate 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 9d 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.
What it actually says
hmem-consolidate
TRIGGER
Run when:
- The session is ending AND hmem-checkpoint ran 2 or more times
- User types /consolidate
Do NOT run if there was only one checkpoint — that summary is already final.
STEP 1: Read the O-Entry
Call read_memory on the active O-Entry:
read_memory(id: "O00XX", depth: 2)
Replace O00XX with the active O-Entry ID (P0056 → O0056).
Identify all child nodes with titles starting with "Summary YYYY-MM-DD". Collect their content.
STEP 2: Write merged summary
From all collected summaries, write ONE final summary with max 10 bullets:
- Each bullet names a specific decision, file, command, or outcome
- Never write "discussed X" or "made progress on Y"
- Cover: main topic, decisions made, what changed, next step
STEP 3: Append to O-Entry
append_memory( id: "O00XX", content: "Final Summary <today's date e.g. 2026-04-24>\n\n- <bullet 1>\n- <bullet 2>\n...\n- " )
Do NOT delete or overwrite the individual checkpoint summaries.
OUTPUT
[CONSOLIDATED] Final summary written to O-Entry O00XX.
- <bullet 1>
- <bullet 2> ... [/CONSOLIDATED]
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.
- 9d ago First seen · 49 lines · 31 tokens per session scan A 831bed589f01
hmem-consolidate is a skill published in the GitHub repository Bumblebiber/hmem (23 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 351 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.