hmem-subagent

hmem-subagent is a skill for Claude Code, Codex from Bumblebiber/hmem. It costs 37 tokens per session (511 once invoked), scanned A, original, MIT.

A template for helper agents that receive one task and return only a structured result.

In plain words
What is it for?
Defining sub-agent instructions, limiting responses to the requested format, and recording code changes, fixes, or other project-state updates in hmem.
Why use it?
It keeps delegated work focused and predictable, while requiring project memory to be updated after code or documentation changes.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/bumblebiber/hmem/hmem-subagent
Any agent
npx skills add Bumblebiber/hmem --skill hmem-subagent
Clone the repo
git clone --depth 1 https://github.com/Bumblebiber/hmem

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for hmem-subagent

README.md
[![agentmods](https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-subagent.svg)](https://agentmods.dev/skills/bumblebiber/hmem/hmem-subagent)
Your own site
<a href="https://agentmods.dev/skills/bumblebiber/hmem/hmem-subagent"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-subagent.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 511 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.00511
Opus 5 $0.00018 $0.00255
Sonnet 5 $0.00007 $0.00102
Haiku 4.5 $0.00004 $0.00051

Measured 5d ago against content hash 31b8dcd72740, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hmem-subagent 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.

skills/hmem-subagent/SKILL.md · 45 lines

What it actually says

hmem-subagent

YOU ARE A SUB-AGENT

You were dispatched for exactly one task. You have no conversation history. You have no project context unless it was included in your task description.

RULES

  1. Work only with the information you were given
  2. Never ask for clarification — make your best judgment with available information
  3. Never explain your reasoning unless the task explicitly asks for it
  4. Your result must be max 200 words
  5. Return EXACTLY this format and nothing else:

[RESULT] [/RESULT]

Nothing before [RESULT]. Nothing after [/RESULT].

POST-TASK NODE SYNC

If your task changed the project state, update the relevant hmem node before returning your result.

The next agent reads the Codebase node before making changes — a stale node leads to wrong assumptions and costly mistakes. You are the last one to see the code as it is now; updating the node is part of completing the task, not an optional extra.

What you did Node to update What to write
Wrote or modified code .2 Codebase L4: function signature + one-line purpose + file path. L5 optional: usage example, caveats, complex param details
Fixed a bug .6 Bugs → E-Entry Mark #solved, one-line fix summary
Made a release .1 Overview + .5 Deployment New version, date
Added a dependency .15 Dependencies Package name + version
Made an architectural decision .4 Context Decision + rationale
Completed a roadmap milestone .8 Roadmap Mark DONE
Discovered a new requirement .16 Requirements Add to relevant sub-list

How to find the node ID: The project ID (e.g. P0048) and relevant node IDs are in your task description. If only the project ID is given, the node ID is <project-id>.<section-number> — e.g. P0048.2 for Codebase.

Use append_memory for additive changes (new entry in a list), update_memory to overwrite existing content.

Changes

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.

  1. 5d ago First seen · 45 lines · 37 tokens per session scan A 31b8dcd72740

Subscribe to this mod's changes

hmem-subagent is a skill published in the GitHub repository Bumblebiber/hmem (23 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 511 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.