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-new-rulegit 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-new-rule)<a href="https://agentmods.dev/skills/bumblebiber/hmem/hmem-new-rule"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-new-rule/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-new-rule"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-new-rule.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 | $0.00095 | $0.00953 |
| Opus 5.5 | $0.00038 | $0.00381 |
| Sonnet 5.5 | $0.00019 | $0.00191 |
| Haiku 4.5 | $0.00010 | $0.00095 |
Grade A, and why
hmem-new-rule 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hmem-new-rule — Place a Rule in the Right Place
R-prefix entries are surfaced in the session-start Rules listing for every session. A project-specific rule written as an R-entry leaks into other projects' context. A cross-project rule buried inside one project never surfaces when working on another. Same content, very different consequence — scope decides.
Step 1: Determine scope BEFORE writing
Ask the user, unless they already said:
"Gilt die Regel projektübergreifend (alle Projekte) oder nur für das aktive Projekt?"
Suggest a default from these heuristics:
| Signal | Likely scope |
|---|---|
| Rule names a specific repo path, file, CLI tool, schema field, project's tech stack | Project-specific |
| Rule mentions hmem code, propagation to end users, project structure | Project-specific (P0048-specific) |
| Rule is about agent behavior, communication style, write protocols, MCP interaction | Cross-project (R) |
| Rule references infrastructure used in many projects (e.g. Strato server, npm publish in general) | Cross-project (R) |
| Rule applies only when one specific project is active | Project-specific |
When in doubt, ask. Wrong scope is the most common failure mode of this workflow.
Step 2A: Cross-project rule → R-entry
write_memory(
prefix="R",
title="<short imperative title>",
body="<full rule text — what / why / examples / counter-examples>",
tags=["#hmem", "#<topic-tag>"],
links=["<active-project-id-if-relevant>"],
pinned=<true only if it MUST surface in session-start every session>
)
linksmay include a project ID for context, but the rule still applies broadly.pinned=trueonly when the rule belongs in the always-visible Rules block at session start (after the v6.x hook trim, only pinned/favorite R-entries surface). Use sparingly — pinning everything defeats the purpose.
Step 2B: Project-specific rule → subnode under Rules
First check whether the active project has a Rules section:
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 · 94 lines · 95 tokens per session scan A 28b37f1fd429
hmem-new-rule is a skill published in the GitHub repository Bumblebiber/hmem (24 stars, last pushed 4d ago), licensed MIT. It adds 95 tokens to every session and 953 once invoked, about $0.0004 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…
alice-memory
Use Alice as the user's durable local memory. Load before answering from context, and whenever you learn something worth keeping across sessions.