SessionStart
01Hook Claude Code
One of 5 in hooks.json
Runs when a session starts on startup, resume, clear and compact, running recall-codex-hooks. From GiulioDER/RE-call.
Hook Claude Code
One of 5 in hooks.json
Runs when a session starts on startup, resume, clear and compact, running recall-codex-hooks. From GiulioDER/RE-call.
Hook Claude Code
One of 5 in hooks.json
Runs before the agent uses a tool for Bash, Write, Edit, MultiEdit, NotebookEdit and BashOutput tool calls, running recall-codex-hooks. From GiulioDER/RE-call.
Hook Claude Code
One of 5 in hooks.json
Runs before the context is compacted for manual and auto tool calls, running recall-codex-hooks. From GiulioDER/RE-call.
Hook Claude Code
One of 5 in hooks.json
Runs when a session ends, running recall-codex-hooks. From GiulioDER/RE-call.
Skill Claude CodeCodex
Search this project's own memory before doing something it may already have opinions about. Use before running a build/test/deploy command, before choosing a library or approach, before changing configuration or CI, and before re-opening a decision that may already have been settled. Also use when a task resembles…
Skill Claude CodeCodex
Load this project's memory when you start, and write back what you learned before you stop. Use at the beginning of a work session, when finishing a task or about to end a session, after debugging something non-obvious, after a decision that took argument to reach, and whenever you catch yourself thinking "I should…
MCP server Claude CodeCodexCursor +2
Trustworthy retrieval for an AI agent's own memory — verdict, confidence and provenance per hit, or an explicit abstention. Runs locally from the recall-rag Python package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "recall" as configured in GiulioDER/RE-call. Launched with recall-codex-mcp.
Hook Claude Code
One of 5 in hooks.json
Runs when you submit a prompt, before the agent sees it, running recall-codex-hooks. From GiulioDER/RE-call.
Skill Claude CodeCodex
Give an AI agent trusted persistent memory across sessions. Use before planning or answering when earlier runs may contain relevant decisions, failures, experiments, user corrections, unresolved work, or lessons that should influence the current task, and after learning a durable fact that future runs should inherit.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: