Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add rhoulihan/mneme/plugin install 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/rhoulihan/mneme/index)<a href="https://agentmods.dev/skills/rhoulihan/mneme/index"><img src="https://agentmods.dev/badge/skills/rhoulihan/mneme/index.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 5.1 | $0.00050 | $0.00624 |
| Opus 5 | $0.00025 | $0.00312 |
| Sonnet 5 | $0.00010 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
index scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
The index is built from the working trees of registered repos, and almost every event that changes one belongs to somebody else — a maintainer merging a knowledge pull request most of all, since mneme never merges (PR-only means a human always does). mneme is not running then, so nothing marks the index dirty. Left alone, mneme search keeps answering from the old shape and an agent concludes the organisation does not know something it merged last week. That is the failure this command exists to catch.
The binary is "$CLAUDE_PLUGIN_ROOT/bin/mneme" when installed, else bin/mneme.
- Check first:
mneme index check. It exits 0 when fresh and 2 when stale, naming each repo and why —changed since it was indexed,never indexed,local clone missing, orindexed before freshness tracking. Exit 2 is a report, likemneme verify's, not a crash. - If anything is stale, rebuild only what moved:
mneme index rebuild --stale. Report eachindexed <plugin>: N skills, M facts, K skippedline, and relay everyskipped:line verbatim — a skipped unit is knowledge that will not be retrievable, and the reason names the file. mneme index rebuildwith no flag rebuilds everything. Use it when a fingerprint may be wrong rather than the tree — after upgrading mneme, or when--stalereported nothing but a search still looks short.mneme index statusshows per-repo counts, when each was built, and which are behind.
A repo mneme cannot read is reported, never fatal — a missing clone, or a directory it lacks permission to list. It stays listed as stale until you fix it, which is the honest answer: the index genuinely does not speak for that repo, and --stale cannot make it fresh by trying again. search still answers with everything else it holds.
"Fresh" means checked, not merely unobjectionable. Anything mneme could not determine — no database yet, an unreadable or corrupt one, a rebuild holding the lock — is reported as stale rather than passed over. A check that says fine when it could not look is the failure this command exists to prevent.
mneme does not rebuild on its own during a search. The search path opens the database read-only on purpose, so it tells you the corpus is stale and answers with what it has rather than writing on a read. If a search warned you, run step 2 and ask again — the second answer is the one to trust.
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.
- 8d ago First seen · 21 lines · 50 tokens per session scan A c98fb66de581
index is a skill published in the GitHub repository rhoulihan/mneme (6 stars, last pushed 14d ago), licensed Apache-2.0. It adds 50 tokens to every session and 624 once invoked, about $0.0003 per session on Opus 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
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.