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/onebrain-ai/onebrain/memory-reviewnpx skills add onebrain-ai/onebrain --skill memory-reviewgit clone --depth 1 https://github.com/onebrain-ai/onebrainWrote 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/onebrain-ai/onebrain/memory-review)<a href="https://agentmods.dev/skills/onebrain-ai/onebrain/memory-review"><img src="https://agentmods.dev/badge/skills/onebrain-ai/onebrain/memory-review.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 | $0.00081 | $0.02610 |
| Opus 5 | $0.00041 | $0.01305 |
| Sonnet 5 | $0.00016 | $0.00522 |
| Haiku 4.5 | $0.00008 | $0.00261 |
Grade A, and why
memory-review 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 5d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Review
Interactive review session for pruning and updating memory entries.
Data Source
Read the entry list from MEMORY-INDEX.md (already in context after session startup). Before
displaying the first entry, read the frontmatter of every active and needs-review
file in memory/ to fetch conf and verified — these fields are not in MEMORY-INDEX.md.
Only read the full file body when user picks update and needs to modify content.
Edge Case: Empty MEMORY-INDEX
If memory/ is empty or has no active/needs-review entries → display "No memory files to review." and stop.
Entry Ordering
Sort all entries by verified date (ascending — oldest first) before starting:
needs-reviewentries firstactiveentries seconddeprecated— skipped entirely
Display Per Entry
Print this header as plain text output before making the first AskUserQuestion call. Do not repeat it per entry and do not embed it inside any question string: ────────────────────────────────────────────────────────────── 🔬 Memory Review — {N} files to review ──────────────────────────────────────────────────────────────
Per-entry: use a single AskUserQuestion with entry details embedded in the question text.
When constructing the AskUserQuestion tool call, the question parameter must contain
actual newline characters in the JSON string — not backslash-n (\n) escape sequences.
Primary menu (shown for every entry):
- question (use real newlines — the lines below are separate lines in the string):
Status emoji: 🟢 active, 🟡 needs-review, ⚫ deprecated[{n}/{N}] "{1-line description}" {status_emoji} {status} · conf: {level} · 📅 {X} days ago 🏷️ {topics} ────────────────────────────────────────────────────────────── `{filename}.md` What would you like to do? - header: "Memory Review [{n}/{N}]"
- multiSelect: false
- options:
- label: "keep", description: "Bump verified date to today, no changes"
- label: "update", description: "Edit confidence, type, or description"
- label: "manage...", description: "Flag, deprecate, or delete this entry"
- label: "stop", description: "Exit review, leave remaining entries unchanged"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 215 lines · 81 tokens per session scan A 0589a035bb32
memory-review is a skill published in the GitHub repository onebrain-ai/onebrain (26 stars, last pushed 7d ago), licensed Apache-2.0. It adds 81 tokens to every session and 2,610 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.
lint-brain
Run health checks over the brain vault - find orphan notes, broken wikilinks, missing frontmatter, stale projects, and missing cross-links. Use when asked to "lint the brain", "health check", "vault hygiene", or "/lint-brain".