Agentmemory Recall

What it does

When your agent uses it

• Finding out what was decided about a topic in an earlier session
• Checking whether the project has hit a problem before
• Pulling context from past sessions before starting related work
• Limiting recalled memories to one repository

Example prompts

• “Recall what we did about JWT refresh token rotation.”
• “Search memory for whether we ever looked at rate limiting in the gateway project.”
• “Check whether we have seen this timeout error before, scoped to this repo.”

Requirements

• The agentmemory server with its memory_smart_search tool

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Call memory_smart_search with the user's text as query and limit: 10.
2. 2Group results by session. Records carry a provenance channel (user, agent,
3. 3For each observation show its type, title, and narrative.
4. 4Lead with the high-signal observations (importance >= 7).
5. 5If zero results, suggest 2-3 alternative search terms and stop. Do not guess.

What it can do on your machine

Read from SKILL.md and the folder at commit df3d4a8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agentmemory Recall loads about 557 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 220 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~65

When it runs · the whole SKILL.md, loaded when a task matches

~557

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from rohitg00/agentmemory at commit df3d4a8, republished under its Apache-2.0 licence (© rohitg00). 220 words, ~557 tokens.

name

recall

description

Search agentmemory for past observations, sessions, and learnings about a topic using hybrid BM25 plus vector plus graph search. Use when the user says "recall", "what did we do about", "did we ever", "have we seen", or needs context from past sessions.

argument-hint

[search query]

user-invocable

true

memory_smart_search { "query": "jwt refresh token rotation", "limit": 10 }

2 results across 2 sessions.
[importance 8] decision · "Rotate refresh tokens on every use" (session 7f3a9c21)
[importance 5] code · "limit.ts counts per-IP" (session b21d004e)

© rohitg00, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugin/skills/recall of rohitg00/agentmemory.

• SKILL.md
• EXAMPLES.md

Open the folder on GitHubat commit df3d4a8