AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Chat History

skill-ay-bh-chat-history-chat-history · by ay-bh

Search, inspect, and export Claude Code, Cursor, and Codex conversation history. Use when the user asks about past conversations, wants to find a previous session, needs to search chat history, wants a summary of what they worked on, or asks to resume a session. Also use when the user says "what did I work on", "find that conversation where I...", "show me my recent sessions", or "search my histo…

↗ Website ↗ Repository
— No reviews yet
0 installs
19 views
0.0% view→install

Install

$ agentstack add skill-ay-bh-chat-history-chat-history

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README — it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-ay-bh-chat-history-chat-history)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Chat History? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

chat-history

Repo: https://github.com/ay-bh/chat-history

Install

cargo install chat-history

This installs both chat-history and ch (short alias) into ~/.cargo/bin/.

When to use

  • User asks about past conversations or sessions
  • User wants to find something they discussed before
  • User needs a summary of recent work / accomplishments
  • User wants to search across all Claude Code or Cursor history
  • User wants to resume or export a previous session

Commands

# List sessions
chat-history                               # all sessions, newest first
chat-history --from yesterday -s           # grouped by day
chat-history --from "3 days ago"           # natural language dates
chat-history --source claude               # Claude Code only
chat-history --source cursor               # Cursor only
chat-history --source codex                # Codex only
chat-history -L                            # current workspace only
chat-history --branch feature-xyz          # filter by branch
chat-history -k "auth" -v                  # keyword filter, show IDs

# Search (always use --deep --json for best results from agents)
chat-history search "auth error" --deep --json   # full transcript search, structured output
chat-history search "fix" --scope errors --deep  # error patterns only
chat-history search "trade" --scope similar      # similar past queries
chat-history search                   # direct UUID lookup

# Inspect (session summary)
chat-history inspect --last                # accomplishments, tools, model, tokens
chat-history inspect 

# View / Export / Resume / Find
chat-history view --last --plain           # pipe-friendly plain text
chat-history view  --tools             # show tool call names
chat-history export  -o session.md     # export as markdown
chat-history resume                    # resume Claude Code or Codex session
chat-history find                      # print file path for scripting

The short alias ch works identically: ch search "auth", ch inspect --last, etc.

Search behavior

  • Always use --deep --json when calling from an agent for thorough results and structured output.
  • Deep search (--deep): Searches full transcript content across all messages in parallel.
  • Snippets show context around the match, not the first N characters of the message.
  • JSON output (--json): Returns structured JSON with session_id, score, snippet, tools, files.

Interpreting output

  • CC = Claude Code session, CR = Cursor session
  • Score (★ N.N) = relevance score (higher = better match)
  • [summary], [first_prompt], [branch] = which field matched in index search
  • inspect shows: duration, message count, model name, token count, tools used, files touched, accomplishments, key decisions

Date formats accepted

YYYY-MM-DD, today, yesterday, "3 days ago", "last week", "last month"

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in AI & ML