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 Bevel-Software/Hexis --skill memory-managementgit clone --depth 1 https://github.com/Bevel-Software/HexisWrote 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/bevel-software/hexis/memory-management)<a href="https://agentmods.dev/skills/bevel-software/hexis/memory-management"><img src="https://agentmods.dev/badge/skills/bevel-software/hexis/memory-management/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/bevel-software/hexis/memory-management"><img src="https://agentmods.dev/badge/skills/bevel-software/hexis/memory-management.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 | $0.00072 | $0.02586 |
| Opus 5.5 | $0.00029 | $0.01034 |
| Sonnet 5.5 | $0.00014 | $0.00517 |
| Haiku 4.5 | $0.00007 | $0.00259 |
Grade A, and why
memory-management 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 6d 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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Management
Memory makes your agent a workplace collaborator - someone who speaks your internal language.
The Goal
Transform shorthand into understanding:
User: "ask todd to do the PSR for oracle"
↓ the agent decodes
"Ask Todd Martinez (Finance lead) to prepare the Pipeline Status Report
for the Oracle Systems deal ($2.3M, closing Q2)"
Without memory, that request is meaningless. With memory, the agent knows:
- todd → Todd Martinez, Finance lead, prefers Slack
- PSR → Pipeline Status Report (weekly sales doc)
- oracle → Oracle Systems deal, not the company
Architecture
CLAUDE.md ← Hot cache, personal (~30 people, common terms, your preferences)
Knowledge base (Hexis, shared with your team)
Glossary.md ← Full decoder ring (everything)
People/ ← Work profiles of colleagues
Projects/ ← Project details
How we work.md ← Teams, tools, processes
CLAUDE.md (Hot Cache): the file your agent reads at the start of every conversation, in its own working directory. Claude reads CLAUDE.md; other agents read their own file (often AGENTS.md). Use whichever your agent reads. It is NOT the AGENTS.md at the root of the knowledge base, which the platform maintains.
- Top ~30 people you interact with most
- ~30 most common acronyms/terms
- Active projects (5-15)
- Your preferences
- Goal: Cover 90% of daily decoding needs
Glossary (Full Glossary): the Glossary page in the knowledge base.
- Complete decoder ring - everyone, every term
- Searched when something isn't in CLAUDE.md
- Shared: the whole team benefits from every term anyone adds
People/, Projects/, How we work:
- Rich detail when needed for execution
- Full profiles, history, context
The knowledge base lives in the knowledge folder (KnowledgeBase/ unless your workspace renamed it). Search it with the Hexis tools (grep, list_files, read_file) and write to it with write_file or edit_file. If the team already keeps these pages under other names, use theirs.
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.
- 6d ago First seen · 333 lines · 72 tokens per session scan A efa196c9801a
memory-management is a skill published in the GitHub repository Bevel-Software/Hexis (115 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 2,586 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 2026-10-10.
Other skills, from other repositories
kb-workflow
Use before starting any non-trivial task to search the knowledge base for context, and after completing work to capture findings. Teaches the token-efficient retrieval pattern and self-learning loop.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
mindbase
Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.