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 yujiachen-y/agent-bundle --skill update-memorygit clone --depth 1 https://github.com/yujiachen-y/agent-bundleWrote 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/yujiachen-y/agent-bundle/update-memory)<a href="https://agentmods.dev/skills/yujiachen-y/agent-bundle/update-memory"><img src="https://agentmods.dev/badge/skills/yujiachen-y/agent-bundle/update-memory/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/yujiachen-y/agent-bundle/update-memory"><img src="https://agentmods.dev/badge/skills/yujiachen-y/agent-bundle/update-memory.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 | $0.00014 | $0.00164 |
| Opus 5.5 | $0.00006 | $0.00066 |
| Sonnet 5.5 | $0.00003 | $0.00033 |
| Haiku 4.5 | $0.00001 | $0.00016 |
Grade A, and why
update-memory 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 1mo 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
Update Memory
When the user provides a new event or preference update:
- Read the existing profile with
mcp__fs__read_filefrom/memory/<userId>.json. - Merge the new event details into the existing profile object.
- Write the merged profile with
mcp__fs__write_fileto/memory/<userId>.json. - Return a brief confirmation describing what was updated.
Rules:
- Never overwrite unrelated fields with empty values.
- Preserve existing profile keys unless the user explicitly changes them.
- If the profile file does not exist, create a new one with the event data.
- Always include an
updatedAtISO timestamp in the profile.
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.
- 1mo ago First seen · 21 lines · 14 tokens per session scan A b21706686e48
update-memory is a skill published in the GitHub repository yujiachen-y/agent-bundle (10 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 164 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
data-sync
Sync and archive data from messaging platforms (WhatsApp, Discord, Slack, Twitter/X, Google) into Moltis memory as daily digest summaries. Orchestrates crawl tools and writes structured markdown to the memory system.
llm-wiki
Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.
search_knowledge
Search the knowledge base using RAG (pgvector) semantic similarity.
search_past_decisions
Search for similar past decisions using hybrid search.
store_decision
Store a decision to episodic memory for future recall.
get_workflow_entities
Get entities extracted from a specific workflow.