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 instructions/andrelyl/memkin/claude-mdgit clone --depth 1 https://github.com/AndreLYL/memkinWrote 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/instructions/andrelyl/memkin/claude-md)<a href="https://agentmods.dev/instructions/andrelyl/memkin/claude-md"><img src="https://agentmods.dev/badge/instructions/andrelyl/memkin/claude-md.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 | $0.00394 | $0.00394 |
| Opus 5 | $0.00197 | $0.00197 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
memkin CLAUDE.md 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.
What it actually says
Memkin — Agent Guide
Memkin is a personal memory layer. It stores and retrieves signals (decisions, tasks, knowledge, preferences, references) as pages anchored to entities (people, projects, tools) via a graph.
Session Start
At the beginning of every session, call get_session_context to load working memory:
get_session_context() # last 7 days (default)
get_session_context(days=14) # extend window if needed
Tool Priority
Prefer high-level tools first:
| Tool | Use for |
|---|---|
get_session_context |
Session bootstrap — what's active, what's pending |
query("...") |
Semantic search — main retrieval entry point |
get_entity_profile("entities/alice") |
Full profile: signals + timeline for a person/project |
list_signals_by_entity("entities/alice") |
List all signals anchored to an entity |
search("exact keyword") |
Keyword / full-text search (use when query is too broad) |
Low-level tools (get_page, put_page, add_link, list_pages, …) are available for precise CRUD when high-level tools aren't enough.
Saving Signals
When you make a significant decision or discovery, save it:
put_page(
slug="decisions/<kebab-slug>",
content="---\ntitle: <title>\ntype: decision\n---\n<reasoning>"
)
Signal types: decision, task, knowledge, preference, reference, entity, person, project, organization, tool, concept.
Memory Tiers
Pages move through tiers automatically (hot → warm → cold). Query results weight hot pages higher. Use memkin consolidate --hot to run tier rotation manually.
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 · 44 lines · 394 tokens per session scan A 7cee3cfedd49
memkin CLAUDE.md is an instructions file published in the GitHub repository AndreLYL/memkin (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 394 tokens to every session, about $0.0020 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 instructions, from other repositories
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
engraphis AGENTS.md
AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.
shodh-memory CLAUDE.md
Claude Code instructions for varun29ankuS/shodh-memory, covering shodh-memory project instructions, must rules, code standards, persistent memory (shodh-memory mcp) and codebase map.
neurostack CLAUDE.md
Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.
wenlan AGENTS.md
AGENTS.md instructions for 7xuanlu/wenlan, covering agents.md, start here, build and verification, repository invariants and git and release.
superlocalmemory copilot-instructions.md
Copilot instructions for qualixar/superlocalmemory, covering superlocalmemory (slm) — agent rules, session start, remember, recall and optimize (fail-open).