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 skills add Jessinra/Lorekeeper --skill lorekeeper-protocolgit 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-protocol)<a href="https://agentmods.dev/skills/jessinra/lorekeeper/lorekeeper-protocol"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/lorekeeper-protocol/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/skills/jessinra/lorekeeper/lorekeeper-protocol"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/lorekeeper-protocol.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 | $0.00057 | $0.01104 |
| Opus 5.5 | $0.00023 | $0.00442 |
| Sonnet 5.5 | $0.00011 | $0.00221 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
lorekeeper-protocol 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lorekeeper Protocol
Follow this protocol every session to keep your memory store accurate, healthy, and growing.
Inspired by MRAgent (Ji et al., NUS, ICML 2026): memory is reconstructed, not retrieved. Actively explore the memory graph — search, reason, follow links, prune dead ends, repeat.
Phase 1 — Session Start
Trigger: Beginning of every session, before any substantive work.
- Identify the session topic (1–3 keywords).
- Search:
lore_search({ query: "<topic>", min_score: 0.15, include_links: true }) - Read all returned memories — decisions, constraints, patterns.
- Provide feedback:
lore_update({ memory_feedback: [{ id: "<id>", useful: true/false }] }) - If fewer than 3 results, run a broader fallback search.
Do not skip. Working without context causes duplicate inserts and contradictory decisions.
Phase 1.5 — Active Memory Reconstruction
Trigger: After Phase 1, before acting on retrieved memories.
Run the reconstruction loop until the surface is exhausted:
1. READ top results. 2. REASON about what's still unknown. 3. TRAVERSE links from high-value memories. 4. SEARCH for inferred cues. 5. PRUNE dead ends. 6. REPEAT. BREAK when 2 consecutive iterations return no novel results.
Rule: If you've read a memory and still have open questions, run another search — don't settle for the first batch.
Phase 2 — Mid-Session (Topic Shift)
Trigger: Conversation shifts to a new domain, subsystem, or question.
- Run a fresh
lore_searchfor the new topic. - Follow links from already-known relevant memories.
- Provide feedback. If connected to explored topic, run reconstruction at reduced depth (1–2 iterations).
Rule: If you're reasoning about something you haven't searched for, search first.
Phase 3 — Session End
Trigger: End of every session.
- Insert new memories for decisions, root causes, architecture insights, user corrections, patterns.
- Store with cues in mind: insert explicit
referenceslinks to related memories. - Reflect:
lore_reflect({ session_id, summary, topic, task_type, what_was_done, decisions, lessons_learnt, good_patterns, factual_discoveries, memory_ids })
What ships with it
2 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.
- 1mo ago First seen · 93 lines · 57 tokens per session scan A 90b31fedf316
lorekeeper-protocol is a skill published in the GitHub repository Jessinra/Lorekeeper (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,104 once invoked, about $0.0002 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 2026-08-31.
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).
bot-handoff
Keep a durable record of work passed between Bots in the shared Hindsight memory bank. Use when handing work to another Bot, when picking up work another Bot started, and when a finding would help other Bots, including Bots that are not part of the current conversation.
memory-setup
Set up and check Hindsight long-term memory for this Bot. Use the first time a Bot uses Hindsight, when the user asks to connect or check memory, or whenever a Hindsight tool call fails.
memory-context
Load relevant long-term memory from Hindsight before starting work. Use at the start of every task or request, before planning or answering, and whenever the user mentions people, projects, decisions, preferences or anything done before.
routine-memory
Carry state between runs of a scheduled routine using Hindsight memory. Use when creating or editing a routine, to write the recall and retain steps into the routine's own instructions, and at the start and end of every scheduled or event-triggered routine run.