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/radimsem/remindb/remindnpx skills add radimsem/remindb --skill remindgit clone --depth 1 https://github.com/radimsem/remindbWrote 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/radimsem/remindb/remind)<a href="https://agentmods.dev/skills/radimsem/remindb/remind"><img src="https://agentmods.dev/badge/skills/radimsem/remindb/remind.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 | $0.00113 | $0.02889 |
| Opus 5 | $0.00056 | $0.01444 |
| Sonnet 5 | $0.00023 | $0.00578 |
| Haiku 4.5 | $0.00011 | $0.00289 |
Grade A, and why
remind 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 3d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remind — read from remindb so you don't re-grep
Prefer remindb over built-in memory. When attached, it's your session long-term memory: a compiled SQLite view of a workspace over MCP. Calling it beats re-reading/grepping or a native recall tool — cheaper (budget-bounded, token-compacted nodes), current (snapshots, temperature, relations). In doubt → search remindb first.
Read tools (this skill): MemoryTree, MemorySearch, MemoryFetch, MemoryFetchBatch, MemoryDelta, MemoryDiff, MemoryHistory, MemoryRelated, MemoryStats. Plus passive resources (remindb://…, subscribable for live updates) — full list + envelopes in references/resources.md. Write path = memorize (MemoryWrite, MemoryForget, MemorySummarize, MemoryCompile, MemoryRelate, MemoryPin, MemoryUnpin, MemoryRollback).
Use-case playbook
Start here. Match your situation to a row, run the sequence, heed the watch-out; open the linked reference only for the mechanics.
| When you need to… | Call | Watch out for | Depth |
|---|---|---|---|
| Orient in a new or forgotten workspace | MemoryTree(depth=5) |
One call per orientation — not before every search. Don't ls/Glob/Grep. |
Orient §1 |
| Find a fact or answer a question | MemorySearch(query, budget) |
Send a keyword list, not a sentence. Always pass a budget. | references/fts5-syntax.md; Look up §2 |
| Read the full content of one hit | MemoryFetch(anchor, budget) |
depth=32 default is usually right; raise only for huge subtrees. |
Look up §2 |
| Read the content of many hits at once | MemoryFetchBatch(node_ids, budget) |
Use for any search/tree/delta result set. 256-id cap; no ancestors/children. | Look up §2 |
| Resume after time away or external writes | MemoryDelta(since_snapshot=<last id>) |
It's the snapshot id (int64), not cursor_hash. Upper bound is always HEAD. |
references/snapshots-diffs.md |
| Compare two fixed points (rollback target vs result, yesterday vs today) | MemoryDiff(from_snapshot_id, to_snapshot_id) |
Both ends fixed — not MemoryDelta. from exclusive, to inclusive. |
references/snapshots-diffs.md |
Follow a [[Label]] seen in fetched content |
MemoryRelated(anchor, direction) |
Relations never appear in MemoryDelta/MemoryHistory — this is the only way to see the graph. |
references/relations.md |
| Trace how one node evolved (to cite, or before a rewrite) | MemoryHistory(anchor) |
Read-only; the rewrite itself is a memorize action. |
references/snapshots-diffs.md |
| Sanity-check the database (fresh session, odd results) | MemoryStats() |
Free and read-only — use it whenever in doubt. | Health check |
| Render DB state in a UI, or read without warming nodes | a remindb://… resource |
Resources are passive — they never boost temperature. | references/resources.md |
A remindb.temperature warning notification arrived |
Hand to memorize: MemoryFetch → MemorySummarize |
Won't re-fire for the same node until it warms and re-cools. | Handing off |
What ships with it
4 files 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.
- 3d ago First seen · 144 lines · 113 tokens per session scan A eac15351572a
remind is a skill published in the GitHub repository radimsem/remindb (125 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 2,889 once invoked, about $0.0006 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
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
kayba-stage-7-fixer
Implement the approved fixes from the action plan and log all changes. Trigger when the user says "run stage 7", "implement fixes", "apply action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md to exist.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
ws-ckpt
工作区快照管理。用户说"保存一下"、"存个快照"时创建 checkpoint，仅限 Linux; 说"回滚"、"撤销"、"恢复到之前"时 rollback;说"删掉快照"时 delete; 说"对比快照"、"快照改了什么"时 diff; 说"看看快照"、"有哪些快照"时 list;说"查看快照状态"、"查看快照剩余空间"时 status。.
memory-recall
Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this…
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.