A command for finding and browsing saved research, video notes, and analyses from earlier research commands. It can search local memory files and, when configured, a semantic knowledge store that finds related meaning rather than only exact words.

Use it to locate previous research, inspect saved analyses, review video notes, or find related visual artifacts.

It avoids repeating earlier research and brings results from different project memory locations into one overview. It also checks for associated diagrams and screenshots.

recall — Command for Claude Code by Galbaz1

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.

Clone the repo

git clone --depth 1 https://github.com/Galbaz1/video-research-mcp

Made for: Claude Code.

Or install gr, the plugin that ships this one along with the rest of its 12 skills, 17 commands, 7 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/galbaz1/video-research-mcp/recall/github.svg)](https://agentmods.dev/commands/galbaz1/video-research-mcp/recall)

Your own site

<a href="https://agentmods.dev/commands/galbaz1/video-research-mcp/recall"><img src="https://agentmods.dev/badge/commands/galbaz1/video-research-mcp/recall/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/galbaz1/video-research-mcp/recall"><img src="https://agentmods.dev/badge/commands/galbaz1/video-research-mcp/recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,182 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00011	$0.02182
Opus 5	$0.00005	$0.01091
Sonnet 5	$0.00002	$0.00436
Haiku 4.5	$0.00001	$0.00218

Measured 10d ago against content hash e0c2866c3952, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

recall scanned grade C with 1 finding 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

If the user asks to delete a result, confirm first, then note the directory path so they can remove it manually: `rm -rf <path>`. Commands cannot delete memory files.

commands/recall.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recall: $ARGUMENTS

Browse saved results from previous /gr:* commands and search the knowledge store.

Find the Memory Directory

Use Glob on ~/.claude/projects/*/memory/gr/ to find saved results. There may be results across multiple project directories — check all of them.

Check Knowledge Store

Call knowledge_stats() first. If it returns collection counts, Weaviate is available — use semantic search for keyword queries. If it returns an error, use filesystem-only mode.

knowledge_stats() returns immediately when Weaviate is not configured (no network call). No performance impact for non-Weaviate users.

Behavior

If no arguments given (`$ARGUMENTS` is empty):

Call knowledge_stats() (reuse availability check result)
Use Glob with pattern ~/.claude/projects/*/memory/gr/**/analysis.md to find all saved results
For each result, read the first 5 lines to get the title and check for visualization artifacts:
- Check if concept-map.html, evidence-net.html, or knowledge-graph.html exists alongside analysis.md
- Check if screenshot.png exists
Present unified overview:

Knowledge Store (if available) X objects across 12 collections ResearchFindings: N | VideoAnalyses: N | ContentAnalyses: N | ...

Project Memory (filesystem) Group by category with visualization indicators:

Research (gr/research/)
- topic-slug — 📊 (has evidence network)
Video Notes (gr/video/)
- video-slug — 📊 (has concept map)
Video Chats (gr/video-chat/)
- chat-slug — 📊 (has concept map)
Analyses (gr/analysis/)
- source-slug — 📊 (has knowledge graph)
Legend: 📊 = interactive visualization available
Invite user to search, browse by category, filter by knowledge state, or ask a question

If arguments match a category (`research`, `video`, `video-chat`, `analysis`):

Category-to-collection mapping:

research → ResearchFindings, ResearchPlans
video → VideoAnalyses, VideoMetadata
video-chat → SessionTranscripts
analysis → ContentAnalyses

Read the full file on GitHub · 192 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.

10d ago First seen · 192 lines · 11 tokens per session scan C e0c2866c3952

Subscribe to this mod's changes

recall is a command published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 2,182 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Memory and context Research ai-tools gemini mcp mcp-server

recall

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Recursive force deletehighDestructive command

How it starts

Recall: $ARGUMENTS

Find the Memory Directory

Check Knowledge Store

Behavior

If no arguments given (`$ARGUMENTS` is empty):

If arguments match a category (`research`, `video`, `video-chat`, `analysis`):

What this file has done since we first saw it

Other commands, from other repositories

mem-prune

mem-last

mem-search

mem-status

context

setup-video-vision

recall

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Recursive force deletehighDestructive command

How it starts

Recall: $ARGUMENTS

Find the Memory Directory

Check Knowledge Store

Behavior

If no arguments given ($ARGUMENTS is empty):

If arguments match a category (research, video, video-chat, analysis):

What this file has done since we first saw it

Other commands, from other repositories

mem-prune

mem-last

mem-search

mem-status

context

setup-video-vision

If no arguments given (`$ARGUMENTS` is empty):

If arguments match a category (`research`, `video`, `video-chat`, `analysis`):