Skip to main content
command CX Codex

remember — Claude Code command: add a note to a finding

remember — a slash command to manually add a note to a bug report or target system. The automatic capture during autopilot runs works on its own; this is for details the engine would miss.

MIT ★ 16,193 updated 2026-10-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add elementalsouls/Claude-BugHunter
/plugin install claude-bughunter@elementalsouls
Open on GitHub

What remember does

The /remember command supplements the automatic ledger that Claude-BugHunter maintains during autopilot runs. Every confirmed finding is written to ~/.claude/bughunter/memory/findings.jsonl without your intervention. /remember lets you append context by hand — a technique detail, a follow-up idea, or a note the automatic capture would overlook.

Invoke the command and describe your note; it is added to the target's rollup. This is not the primary way findings enter memory, so use it selectively for human context the engine cannot see.

What it helps with

  • attach a manual note to a confirmed vulnerability
  • record a technique or follow-up idea for later review
  • add session details to an automated report

Example prompts for the agent

  • /remember
  • /remember Tested via Burp, found pattern in response headers
  • /remember Revisit this target after framework upgrade

How to install remember

1Plugin marketplace

/plugin marketplace add elementalsouls/Claude-BugHunter
/plugin install claude-bughunter@elementalsouls

2Manually: put the files in place

.claude/commands/remember.md

Call it with /remember. For all projects use ~/.claude/commands/

Questions about remember

How do I install remember in Claude Code?

Add the plugin with /plugin marketplace add elementalsouls/Claude-BugHunter, then install it: /plugin install claude-bughunter@elementalsouls. The command is also available in .claude/commands/remember.md.

What does remember do?

It lets you manually add a note to a bug report or target system. Automatic finding capture happens during autopilot runs; this command is for extra context you want to record.

Where are the notes I add stored?

Automatic findings are written to ~/.claude/bughunter/memory/findings.jsonl. Notes added via /remember are appended to the target's rollup in the same storage.

Source text

remember.md · MIT
---
name: remember
description: Optional manual note on a target or the last confirmed finding. Capture is automatic during autopilot; this is for extra context. Usage: /remember
---

# /remember

> **Capture is automatic.** During an engine/autopilot run, every confirmed finding is
> written to the ledger (`~/.claude/bughunter/memory/findings.jsonl`) with no action from you.
> `/remember` is only for adding an **optional manual note** — a technique detail or
> follow-up idea — that the automatic capture would not include.

## Usage

```
/remember   # then describe the note; it is appended to the target's rollup
```

## What It Is Not

This is no longer the primary way findings enter memory — the engine captures those
deterministically. Use it sparingly for human context.

© Sachin Sharma · MIT · elementalsouls/Claude-BugHunter

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

From the same set92

The whole set →
offensive-osint The offensive-osint skill gives Claude Code technical references for external reconnaissance, from subdomain discovery to secret triage. Use it for authorized red-team or bug-bounty work. CX Codex +1 ★ 16,193repo stars pickup pickup pulls previous target recon from the Claude-BugHunter ledger to inspect tested endpoints, tech stack, and confirmed findings. CX Codex +1 ★ 16,193repo stars memory-gc The memory-gc command checks the autopilot’s JSONL ledgers and rotates files that exceed a size cap. Use it when findings.jsonl or negatives.jsonl keeps growing. CX Codex +1 ★ 16,193repo stars surface Shows a ranked attack surface for a target from its recon manifest and hunt memory. CX Codex +1 ★ 16,193repo stars intel Fetches target intelligence on demand: scans NVD and GitHub advisories, checks HackerOne reports, and flags untested endpoints from hunt memory. CX Codex +1 ★ 16,193repo stars scope scope is a Claude Code command that checks hosts and URLs before active testing. It blocks assets outside engagement rules during security work. CX Codex +1 ★ 16,193repo stars hunt-exceptional-conditions The hunt-exceptional-conditions skill reveals when an app leaks stack traces, server paths, or library versions through unhandled exceptions triggered by malformed input. Effective for testing APIs and web endpoints. CX Codex +1 ★ 16,193repo stars triage triage evaluates security findings through a 7-question gate before you write a bug report. It helps bug bounty hunters discard invalid submissions immediately. CX Codex +1 ★ 16,193repo stars

More in the catalog

Project sponsors

Companies that keep this analytics open