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 michielinksee/linksee-memory-plugin --skill cross-session-memorygit clone --depth 1 https://github.com/michielinksee/linksee-memory-pluginWrote 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/michielinksee/linksee-memory-plugin/cross-session-memory)<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>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 | $0.00503 | $0.02003 |
| Opus 5 | $0.00251 | $0.01001 |
| Sonnet 5 | $0.00101 | $0.00401 |
| Haiku 4.5 | $0.00050 | $0.00200 |
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.
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:
- Memory gap: Claude Code forgets everything when a session ends. linksee-memory is the "memory that doesn't disappear" device.
- 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. |
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.
- 7d ago First seen · 184 lines · 503 tokens per session scan A 712e0ad3b031
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.
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.
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.…
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…
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.
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…
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.