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/davidmosiah/delx-memory/skillnpx skills add davidmosiah/delx-memory --skill skillgit clone --depth 1 https://github.com/davidmosiah/delx-memoryWrote 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/davidmosiah/delx-memory/skill)<a href="https://agentmods.dev/skills/davidmosiah/delx-memory/skill"><img src="https://agentmods.dev/badge/skills/davidmosiah/delx-memory/skill.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 | $0.00040 | $0.00273 |
| Opus 5 | $0.00020 | $0.00137 |
| Sonnet 5 | $0.00008 | $0.00055 |
| Haiku 4.5 | $0.00004 | $0.00027 |
Grade A, and why
delx-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 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.
This is a copy
88% identical to google-health — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Delx Memory — skill or MCP
Same binary either way. Do not duplicate the API client.
Choose a surface
MCP — tools appear natively after stdio/HTTP config:
{ "mcpServers": { "delx-memory": { "command": "npx", "args": ["-y", "delx-memory"] } } }
Do not put mutation flags in that snippet.
Skill / CLI — no MCP client required. Same tools:
npx -y delx-memory call memory_connection_status --json '{}'
If MCP tools named memory_* are already available, use them. Do not also shell out.
Loop
- Call
memory_connection_status(ordoctor --jsonwhen that exists). - Use read tools as asked.
- Stop on
USER_ACTION_REQUIRED. Do not invent env flags. Do not enable mutations from this skill.
Never
- Paste tokens into git, chat logs, or the prompt
- Copy a mutations-enabled assignment into config
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 · 40 lines · 40 tokens per session scan A 94ab6577653f
delx-memory is a skill published in the GitHub repository davidmosiah/delx-memory (1 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 273 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to google-health, differing in 16 lines, and is treated as a copy.
Other skills, from other repositories
membrain
Shared long-term memory over MCP. Call memorycontext once at the start of any session/task to load what is already known; use searchmemory before answering questions about the user or their projects; save durable facts, preferences, and decisions with savememory / savememories. All agents and the user share the same…
reset_project
Wipe the per-project memory cache for the active project when it was re-cloned from the same path. Use when the user says "reset project memory", "wipe this project's memory", "I re-cloned the repo", or "memory is stale".
kimi-memory
Persistent memory for Kimi Code across three layers (global user preferences, project decisions, session archives). Use when the user asks to remember, recall, or persist a fact, preference, decision, or convention. Also use at session start to recall context.
advisor
Reflect on the active project and propose what to change, do differently, or consider that has not been considered. Invoke when the user asks "would we change anything", "what would you do differently", "how can we improve", "what are we missing", "is there a better way", "second opinion", "review this approach"…
list_memories
Show the kimi-memory entries currently on file for this project (and the global layer when relevant). Use when the user asks to "list memories", "what do you remember", "show project memory", or "listmemories".
seller-research
Use when researching a merchant, storefront, marketplace seller, or merchant of record for a buying decision, especially when identity, refund terms, fulfillment, counterfeit risk, domain history, or independent buyer outcomes are uncertain.