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-contextnpx skills add Bumblebiber/hmem --skill hmem-contextgit 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-context)<a href="https://agentmods.dev/skills/bumblebiber/hmem/hmem-context"><img src="https://agentmods.dev/badge/skills/bumblebiber/hmem/hmem-context.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 | $0.00031 | $0.00506 |
| Opus 5 | $0.00015 | $0.00253 |
| Sonnet 5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
hmem-context 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 3d 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-context
TRIGGER
Use when:
- The current question requires a past decision not in the project brief
- You need to recall a specific bug, pattern, or lesson
- You need code details not in the Overview
Do NOT use for session start — use hmem-session-start instead.
STEP 1: Identify what type of information is needed
Pick ONE:
- Past decision → use search_memory with keywords from that decision
- Lesson or pattern → use find_related on the concept
- Code details → use read_memory on P00XX.2 (Codebase section)
STEP 2: Run the search (pick ONE)
For keyword search: search_memory(query: "")
For semantic search: find_related(id: "P00XX", query: "")
For direct node: read_memory(id: "P00XX.2")
Replace P00XX with the active project ID (e.g., P0056).
STEP 3: Filter results
Select at most 3 nodes that directly answer the question.
- Prefer L-Entries over O-Entries (more compact, already distilled)
- Prefer entries with matching keywords in title
- Discard everything else
STEP 4: Output
[CONTEXT LOADED]
If nothing relevant found:
[CONTEXT LOADED] No relevant context found for: [/CONTEXT LOADED]
→ If the missing info is code structure: dispatch an Explore agent to locate it in the filesystem. → After finding it, update the Codebase node immediately using the correct depth: L3 — module group (if the group is missing): append_memory(id="P00XX.2", title="Core modules") L4 — individual module with signature + purpose: append_memory(id="P00XX.2.N", title="moduleName.ts", body="functionName(param: Type): Return — purpose. src/path/moduleName.ts") L5 — optional extended notes (edge cases, caveats): append_memory(id="P00XX.2.N.M", title="Note", body="...")
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.
- 3d ago First seen · 65 lines · 31 tokens per session scan A 871150696c61
hmem-context is a skill published in the GitHub repository Bumblebiber/hmem (24 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 506 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
b123d-modeling
Use this skill when asked to model, build, or modify a 3D part or assembly with build123d — from a text description, a technical drawing (image or PDF), dimensions in a spec, or an existing STEP/STL file.
authoring-decorators
Use when the user wants to write a new prompt decorator - either a personal one for their repo or a contribution back to the upstream catalogue. Walks through the JSON schema, the extensions/ convention, how to verify a new decorator end-to-end through the hook, and how to diagnose failures using debug logging and…
b123d-drawing
../../../src/build123dmcp/skills/b123d-drawing/SKILL.md.
mlflow-traces
Use when working with MLflow traces: debugging via MCP tools, analyzing performance, logging feedback, writing custom scorers/evaluations, or cleaning up trace data.
gemini-visualize
Generates interactive HTML visualizations (concept maps, evidence networks, knowledge graphs) from Gemini analysis results. Triggers automatically after /gr:video, /gr:research, /gr:analyze.
tts-production
Produces voiceover audio via ElevenLabs TTS API. Activates for TTS generation, voice tuning, audio ducking, or multilingual narration — not for voice AI agents, transcription, or music.