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 OnourImpram/mneme --skill mneme-searchgit clone --depth 1 https://github.com/OnourImpram/mnemeWrote 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/onourimpram/mneme/mneme-search)<a href="https://agentmods.dev/skills/onourimpram/mneme/mneme-search"><img src="https://agentmods.dev/badge/skills/onourimpram/mneme/mneme-search/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/onourimpram/mneme/mneme-search"><img src="https://agentmods.dev/badge/skills/onourimpram/mneme/mneme-search.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 | $0.00069 | $0.00380 |
| Opus 5.5 | $0.00028 | $0.00152 |
| Sonnet 5.5 | $0.00014 | $0.00076 |
| Haiku 4.5 | $0.00007 | $0.00038 |
Grade A, and why
mneme-search 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
mneme-search
When the user asks a question that sounds like recall from prior work or notes, search the vault first instead of guessing.
When to invoke
- "Did we decide X?"
- "What was the conclusion about Y?"
- "Show me everything I have on Z."
- The user invokes this skill directly.
How to invoke
Call the mneme_search MCP tool with:
query: the user's question in natural language.top_k: 5 by default. Raise to 10 only when the user asks for a broad sweep.- Optional
filters.date_from/filters.date_towhen the user scopes their question to a specific time window.
Inspect the returned hits. Each has path, title, snippet, and
a relevance score. Read the snippets first. If they answer the
question, cite the path and reply. If they only partially answer,
follow up with mneme_recall on the most promising paths to pull the
full body.
What not to do
- Do not invoke this for the user's first hello or for questions whose answer is general knowledge.
- Do not search for the same query twice in a row. If the first pass returned nothing useful, refine the query terms or change the filter window.
- Do not present raw snippets in your reply unless the user explicitly asks for them. Summarize and link.
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 · 43 lines · 69 tokens per session scan A 1113b0eeda71
mneme-search is a skill published in the GitHub repository OnourImpram/mneme (3 stars, last pushed 4d ago), licensed Apache-2.0. It adds 69 tokens to every session and 380 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 2026-08-31.
Other skills, from other repositories
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
engraphis-memory
Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
wenlan-capture
Save a memory to Wenlan in flow, or save something from this conversation as one note when the user asks for a note. Use proactively when the user states a preference, makes a decision, corrects you, or shares a durable fact. Invoked as /wenlan-capture .
wenlan-handoff
End a work session. Stores durable captures, writes a narrative session log, and automatically applies typed item-level deltas to the current Space Brief. Invoked as /wenlan-handoff.
curate
Power-user audit of Wenlan's pending surfaces: accept or dismiss pending revisions (conflicts/merges), or audit pending captures (not yet confirmed). Most users want /brief for revisions; that handles the daily flow. Use /wenlan curate only for explicit deep-walk audits after bulk imports, or to walk the full queue…