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 commands/onourimpram/mneme/recallgit clone --depth 1 https://github.com/OnourImpram/mnemeWhat 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 | $0.00000 | $0.00236 |
| Opus 5 | $0.00000 | $0.00118 |
| Sonnet 5 | $0.00000 | $0.00047 |
| Haiku 4.5 | $0.00000 | $0.00024 |
Grade A, and why
recall 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 2d 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:recall
Retrieve a specific past session by id or by date range.
Usage
/mneme:recall session=<session_id>
/mneme:recall from=<YYYY-MM-DD> to=<YYYY-MM-DD>
/mneme:recall # most recent sessions
What it does
Calls the mneme_recall MCP tool. The tool reads only the FTS5 index
and the on-disk markdown files. No LLM call is made. Returns matching
sessions ranked by mtime descending with full markdown bodies when
the include_body argument is true (default).
Use cases
- "What did we decide about authentication last Thursday?"
- "Pull up the session where I sketched the migration plan."
- "List the last five sessions, no bodies, just titles."
Tips
- Combine with
/mneme:primewhen you want a curated bundle instead of raw session text. - The session_id format follows your vault's frontmatter convention.
If you do not know it, prefer
from/todate ranges.
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.
- 2d ago First seen · 32 lines · 0 tokens per session scan A 5de818693f18
recall is a command published in the GitHub repository OnourImpram/mneme (2 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 236 tokens. 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 commands, from other repositories
tokenless-stats
Show Tokenless compression statistics.
arrecall
AgentRecall on-demand recall — surface past fixes, decisions, and patterns mid-session without leaving your flow.
evolve-lite-subscribe
Add a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.
image-node-intake
Parse a visual brief into the Image Node Factory intake JSON.
video-research
Build the research dossier (facts, derived design, reference images) for a URL or theme via the framework research module.
execute
Execute an implementation plan.