What is claude-history?

A command that searches and recalls information from earlier Claude Code conversations, including project context, session summaries, past solutions and recurring patterns.

Use it to search past discussions, find solutions to earlier errors, summarise the last session, recover project context, discover repeated patterns or list projects with saved history.

Important decisions and fixes can be buried in old conversations, making previous work hard to find or repeat. This provides a way to retrieve that context when it is needed.

claude-history — Command for Claude Code by jhammant

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/jhammant/ClaudeHistoryMCP

Made for: Claude Code.

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/jhammant/claudehistorymcp/claude-history/github.svg)](https://agentmods.dev/commands/jhammant/claudehistorymcp/claude-history)

Your own site

<a href="https://agentmods.dev/commands/jhammant/claudehistorymcp/claude-history"><img src="https://agentmods.dev/badge/commands/jhammant/claudehistorymcp/claude-history/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/jhammant/claudehistorymcp/claude-history"><img src="https://agentmods.dev/badge/commands/jhammant/claudehistorymcp/claude-history.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 430 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00000	$0.00430
Opus 5	$0.00000	$0.00215
Sonnet 5	$0.00000	$0.00086
Haiku 4.5	$0.00000	$0.00043

Measured 12d ago against content hash 5fca5613a37f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claude-history scanned grade A with 0 findings 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 12d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/claude-history.md · 55 lines

What it actually says

Claude History Search

Search and recall context from past Claude Code conversations.

Usage

/claude-history <query>              # General search
/claude-history --solutions <error>  # Find past error fixes
/claude-history --summary            # Summarize last session for current project
/claude-history --patterns           # Discover recurring patterns
/claude-history --context            # Get full project context
/claude-history --projects           # List all projects with history

Your Task

Parse the user's arguments and use the appropriate MCP tool from claude-history-mcp:

If --solutions flag: Use find_solutions tool with the remaining text as error_or_problem
If --summary flag: Use get_session_summary tool with the current project
If --patterns flag: Use find_patterns tool, optionally scoped to current project
If --context flag: Use get_project_context tool with current project
If --projects flag: Use list_projects tool
Otherwise: Use search_history tool with the full text as the query

Presentation

Present results clearly:

For search results: show project, date, and relevant excerpt
For solutions: highlight the error → fix pattern
For summaries: use structured format with sections
For patterns: group by pattern type

If no results are found, suggest alternative search terms or broader queries.

Examples

# Search for Docker networking discussions
/claude-history docker network configuration

# Find how you fixed a specific error before
/claude-history --solutions ECONNREFUSED port 3000

# Get a summary of the last coding session
/claude-history --summary

# Find patterns in your React project
/claude-history --patterns project:react-app

# Search with date filter
/claude-history authentication after:7d

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.

12d ago First seen · 55 lines · 0 tokens per session scan A 5fca5613a37f

Subscribe to this mod's changes

claude-history is a command published in the GitHub repository jhammant/ClaudeHistoryMCP (66 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 430 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Memory and context claude conversation-history mcp model-context-protocol search

claude-history

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Claude History Search

Usage

Your Task

Presentation

Examples

What this file has done since we first saw it

Other commands, from other repositories

screenshot

add-memory

remember-this

sessions

save-session

timeline