linksee-memory

linksee-memory is a skill for Claude Code from michielinksee/linksee-memory-plugin. It costs 503 tokens per session (2,003 once invoked), scanned A, original, MIT.

A memory and project-consistency toolkit for coding agents. It saves information between sessions, maps product documents to code, and reports when they no longer match.

In plain words
What is it for?
Use it to save and recall project facts, read files efficiently, look up where features live, and check product decisions and documentation against specific files and lines.
Why use it?
It reduces the need to repeat project context after a session ends and helps catch decisions or documentation that have drifted away from the code.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the linksee-memory plugin — 1 skill, 1 MCP server shipped together

Good fit Use it to save and recall project facts, read files efficiently, look up where features live, and check product decisions and documentation against specific files and lines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/michielinksee/linksee-memory-plugin/cross-session-memory
Install

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.

Any agent
npx skills add michielinksee/linksee-memory-plugin --skill cross-session-memory
Clone the repo
git clone --depth 1 https://github.com/michielinksee/linksee-memory-plugin

Made for: Claude Code.

Or install linksee-memory, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

agentmods badge for linksee-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/michielinksee/linksee-memory-plugin/cross-session-memory.svg)](https://agentmods.dev/skills/michielinksee/linksee-memory-plugin/cross-session-memory)
Your own site
<a href="https://agentmods.dev/skills/michielinksee/linksee-memory-plugin/cross-session-memory"><img src="https://agentmods.dev/badge/skills/michielinksee/linksee-memory-plugin/cross-session-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 503 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,003 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00503 $0.02003
Opus 5 $0.00251 $0.01001
Sonnet 5 $0.00101 $0.00401
Haiku 4.5 $0.00050 $0.00200

Measured 7d ago against content hash 712e0ad3b031, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

linksee-memory 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 7d 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.

skills/cross-session-memory/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Linksee Memory — 11 Tools, Cross-Agent Brain + Product Map + Drift Detection

Core Principle

This skill bridges two gaps no other tool fills:

  1. Memory gap: Claude Code forgets everything when a session ends. linksee-memory is the "memory that doesn't disappear" device.
  2. Drift gap: Decisions get made but nothing checks if reality still matches. A product map (map.yaml, git source of truth) reconciles your README, docs, and code, and the drift detector catches silent divergence — with file:line evidence.

Writes are handled automatically by the Stop hook. Reads, map lookups, and drift checks require the agent to actively pull — this skill instills that habit.


The 11 Tools

Memory tools (cross-agent brain)

Tool When to use
remember Save / update / delete memories. Caveat layer is auto-protected from forgetting. Importance >= 0.9 pins forever.
recall 3 modes: search (query), file history (path), entity overview (no params). CALL BEFORE every new task.
read_smart Token-saving file reads. Use INSTEAD of Read for all files. 50-99% savings on re-reads.

Map tool (where am I in the product)

Tool When to use
where_am_i Locate the current file in the product map. Four questions: where am I, what did this file promise, what does the code actually do, what else must change with it (graded blast radius). Call when opening or switching files.

Drift tools (decision integrity)

Tool When to use
drift_status "What needs my attention?" — truth map with drift/review/held/aligned states, reconciled against the product map. Call at session start.
check_decision Deep-dive into one anchor — premises, edges, candidates. Call before resolving.
declare_anchor User makes a decision/constraint/prohibition → declare it. declare-don't-mine: only explicit human declaration.
resolve_drift Close the loop: fix / supersede / acknowledge / dismiss.
flag_proposals Surface proposed anchors/drifts awaiting your decision.
resolve_proposal Accept or reject a proposed anchor/drift.
dream Background consolidation — synthesize learnings and surface latent drift.

Read the full file on GitHub · 184 lines

Changes

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.

  1. 7d ago First seen · 184 lines · 503 tokens per session scan A 712e0ad3b031

Subscribe to this mod's changes

linksee-memory is a skill published in the GitHub repository michielinksee/linksee-memory-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 503 tokens to every session and 2,003 once invoked, about $0.0025 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens