Router9
All skills
MemoryAgent Memory

Agent Memory Kit

r9-agent-memory-kit

Give your agent a memory worth reading back.

Recall before acting, save only what is durable, and supersede what turns out to be wrong — so the next session starts where this one ended instead of re-deriving it.

r9-agent-memory-kit-v2.zipSKILL.md

v2published Jul 29, 20261 install

Use it when

What the skill answers to, in the words someone would actually say. The catalog search matches these.

  • “remember this for next time”
  • “why do you keep forgetting what we decided”
  • “set up long-term memory for my agent”
  • “pick up where we left off last session”

What it tells the agent

The body of the skill, exactly as it is handed over — no summary in between.

Agent Memory Kit

Give an agent a memory worth reading back.

Task: {{task}} Scope: {{scope}}

Procedure

  1. Search before you write. Call memory.search on the topic of the task, not on its full text — a long query matches nothing. The failure this pack exists to fix is an agent re-deriving a conclusion it already reached last week.

  2. Read the hits; do not trust the snippets. A search result is a pointer. Call memory.get on anything that looks relevant before acting on it — a half-remembered constraint is worse than no memory at all.

  3. Do the task. Everything above happens first, because the point is that the work is informed by what came before rather than annotated after.

  4. Decide what is durable. Save conclusions, constraints, corrections, and stated preferences. Do not save transcripts, intermediate reasoning, file contents, anything you could re-derive in a second, or anything whose shelf life is shorter than this session.

  5. One entry per idea, keyed as a claim. memory.save with a key that states the thing: staging-db-resets-nightly, not staging-db. Search matches claims; a topic-shaped key returns everything and distinguishes nothing. Prefix the key with {{scope}} so one project's conclusions stay out of another's results.

  6. Supersede; never accrete. When something you learn contradicts something stored, save the correction, name the entry it replaces, and memory.delete the old one. A store holding both sides of a contradiction is worse than an empty one — it will confidently hand back the wrong half.

  7. Audit occasionally. Every several sessions, walk memory.list and delete what has gone stale. Nobody else is going to.

Output

What you recalled and used, then what you saved and why — one line each.

Notes

  • The failure mode is not forgetting. It is remembering at the wrong granularity: a hundred entries about one afternoon and nothing about the decision that afternoon produced.
  • If you would not want it read back to you verbatim in three months, do not save it.
  • Saving nothing is a valid outcome. A session that produced no durable conclusion should leave no trace.