AkbarDizaji

8 mods across 1 repository, 9 stars between them.

UserPromptSubmit

02

AkbarDizaji/AgentRecall

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, running PATH=$HOME/.dotnet/tools:$PATH agentrecall hook user-prompt-. From AkbarDizaji/AgentRecall.

9 18d ago A tokens not measured original MIT

Stop

03

AkbarDizaji/AgentRecall

Hook Claude Code

Runs when the agent finishes a response, running PATH=$HOME/.dotnet/tools:$PATH agentrecall finalize-turn --h. From AkbarDizaji/AgentRecall.

9 18d ago A tokens not measured original MIT

PreToolUse

04

AkbarDizaji/AgentRecall

Hook Claude Code

Runs before the agent uses a tool for Edit, Write and MultiEdit tool calls, running PATH=$HOME/.dotnet/tools:$PATH agentrecall hook pre-tool-use. From AkbarDizaji/AgentRecall.

9 18d ago A tokens not measured original MIT

AgentRecall

05

AkbarDizaji/AgentRecall

Settings file Claude Code

Agent settings declaring 3 hook events (UserPromptSubmit, Stop, PreToolUse).

9 18d ago A tokens not measured original MIT

AkbarDizaji/AgentRecall

Instructions file

Instructions for AkbarDizaji/AgentRecall, covering memory (agentrecall), semantic capture judge, when the stop hook asks for a judgment, submit one, agentrecall behavior contract and answering capture questions: check status, never guess.

9 18d ago A 4,060 tokens original MIT

agentrecall

07

AkbarDizaji/AgentRecall

Plugin Claude Code

Local-first memory for AI coding agents: captures feedback and failures, turns them into ranked, conflict-resolved technical rules, and injects the relevant ones into Claude Code via MCP. Stays on your machine — no cloud, no API keys.

9 18d ago A tokens not measured original MIT

agentrecall

08

AkbarDizaji/AgentRecall

MCP server Claude CodeCodexCursor +2

MCP server "agentrecall" as configured in AkbarDizaji/AgentRecall. Launched with agentrecall mcp.

9 18d ago A tokens not measured original MIT