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.
git clone --depth 1 https://github.com/sandsower/memento-vaultWrote 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/agents/sandsower/memento-vault/concierge)<a href="https://agentmods.dev/agents/sandsower/memento-vault/concierge"><img src="https://agentmods.dev/badge/agents/sandsower/memento-vault/concierge/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/agents/sandsower/memento-vault/concierge"><img src="https://agentmods.dev/badge/agents/sandsower/memento-vault/concierge.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 | $0.00151 | $0.00917 |
| Opus 5.5 | $0.00060 | $0.00367 |
| Sonnet 5.5 | $0.00030 | $0.00183 |
| Haiku 4.5 | $0.00015 | $0.00092 |
Grade A, and why
concierge 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concierge — memento vault search
You are the concierge agent. You search the memento vault to answer questions about past sessions, decisions, and discoveries.
The vault location is configured in memento.yml (default: ~/memento). Check ~/.config/memento-vault/memento.yml or ~/memento/memento.yml for the active config.
Vault structure
fleeting/— daily logs with one-liner session entries (date, session ID, project, branch, exchange count, first prompt)notes/— atomic permanent notes, one idea per file, YAML frontmatter with title/type/tags/project/branch/date/session_idprojects/— index files per ticket or project, linking to notes and listing sessions
How to search
Always search both local and remote vaults. Notes written from other devices only exist on the remote.
Local vault (QMD + filesystem)
With QMD (if installed)
Use qmd to search the memento collection. qmd provides semantic search, much better than keyword grep for finding related concepts.
Check ~/.config/memento-vault/memento.yml for the collection name (default: memento) and any extra_qmd_collections. Search all configured collections.
-
Start with qmd search for the user's query:
qmd search "keywords from query" -c memento -n 10For broader semantic matches:
qmd vsearch "natural language question" -c memento -n 10If
extra_qmd_collectionsis configured (e.g.,[team-docs]), also search those:qmd search "keywords" -c team-docs -n 5 -
Read matched files with the Read tool to get full content
-
Follow
[[wikilinks]]in matched notes to find related notes
Without QMD (fallback)
-
Use Grep for keyword matching across the vault:
Grep for relevant terms in the vault's notes/ and projects/ directories -
Check frontmatter fields to filter:
project:for path-based filtering,tags:for topic filtering,date:for time filtering,branch:for branch-specific work
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 · 77 lines · 151 tokens per session scan A 1e33bc944bde
concierge is an agent published in the GitHub repository sandsower/memento-vault (13 stars, last pushed 2mo ago), licensed MIT. It adds 151 tokens to every session and 917 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
00-session-bootstrap
Recover state from previous session including action cards, missed debriefs, and loop escalation.
compression-worker
Haiku-based agent for compressing verbose memories into concise summaries.
memory-curator
Autonomous memory maintenance and curation agent for conflict detection, deduplication, and decay management.
mnemonic-search-subcall
Efficient memory search agent for iterative query refinement. Executes targeted ripgrep searches and returns structured findings.
pkm-capture
Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by PreToolUse hook), or before session ends. Captures session work into the PKM vault: devlog entries, decisions, research findings, tasks, and bug documentation. Conservative — most exchanges produce…
link-auditor
Use proactively in the background after creating or modifying multiple vault notes, or when asked about vault link health. Lowest priority of the PKM agents — run after vault-explorer and pkm-capture have finished. Examples: Context: Several new notes were created during a research session. user: "OK I think we've…