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/jessinra/lorekeeper/lorekeeper-searchnpx skills add Jessinra/Lorekeeper --skill lorekeeper-searchgit clone --depth 1 https://github.com/Jessinra/LorekeeperWrote 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/jessinra/lorekeeper/lorekeeper-search)<a href="https://agentmods.dev/skills/jessinra/lorekeeper/lorekeeper-search"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/lorekeeper-search.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 | $0.00061 | $0.01835 |
| Opus 5 | $0.00030 | $0.00918 |
| Sonnet 5 | $0.00012 | $0.00367 |
| Haiku 4.5 | $0.00006 | $0.00184 |
Grade A, and why
lorekeeper-search 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 6d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lorekeeper Search with Feedback
Lorekeeper is a persistent memory store exposed via MCP tools (lore_search, lore_update, lore_insert). It uses hybrid semantic + keyword search to surface relevant knowledge.
Critical rule: Every lore_search MUST be followed by a lore_update feedback call once the task is complete. This feedback loop — including confidence ratings — keeps the knowledge base accurate and self-correcting.
Workflow
Fresh-news / time-sensitive searches
When the task is about news, releases, or anything that must be recent:
- Search with explicit date anchors and primary-source domains.
- Verify the publish date on every candidate before using it.
- Skip anything older than the requested cutoff or whose date cannot be confirmed.
- Treat aggregators as discovery only; prefer official blogs, docs, GitHub releases, arXiv, and government pages.
- If nothing meets the cutoff, returning nothing is correct.
See references/news-freshness.md for a compact checklist.
Step 1: Search
Call lore_search with a specific natural language query.
lore_search({ query: "voucher stacking rules in checkout", limit: 10, min_score: 0.1 })
- Use natural language questions, not single keywords
- Raise
min_score(e.g. 0.3) if results are noisy; lowerlimitif you need fewer results - Soft-deleted memories (flagged as unreliable) are excluded by default.
- Filter by recency:
created_after/updated_afteraccept ISO 8601 UTC strings (naive = UTC; non-UTC offsets raise an error). Use to scope searches to a time window, e.g.created_after: "2026-06-01T00:00:00". - Change sort order:
sort_byaccepts"relevance"(default, by hybrid score),"recent"(byupdated_at DESC), or"frequent"(byusage_count DESC). Composes with timestamp filters andlimit.
Step 2: Use the results and verify
Each result contains memory.id, memory.title, memory.content, relevance.combined_score, and links. Each link has its own id, relation_type, reason, source_memory_id, and target_memory_id.
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.
- 6d ago First seen · 142 lines · 61 tokens per session scan A 7a59815ccb98
lorekeeper-search is a skill published in the GitHub repository Jessinra/Lorekeeper (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,835 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
hindsight-architect
Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…
memory-audit
记忆审计入口。当我主动决定审视记忆质量时，先读此文件判断应使用哪个子技能。.
memory-audit-discoverability
可发现性审计。当disclosure写法有问题、parent放错、alias缺失、子节点过多时使用。.
memory-audit-pattern-extraction
模式提取与失效解药分析。当发现多条记忆在讲同一个教训，或发现自己在一而再再而三地犯同样的错误时使用。.