conversation-historian

conversation-historian is an agent for Claude Code from wyattjoh/skills. It costs 41 tokens per session (785 once invoked), scanned A, original, MIT.

An agent for searching and analyzing Claude Code conversation history. Claude Code is a coding assistant, and its saved sessions are records of past work and discussions.

In plain words
What is it for?
Use it to search sessions by topic, inspect a specific conversation, find saved plans, investigate past project work, or perform session archaeology.
Why use it?
It helps find earlier decisions, trace how an implementation changed, and uncover patterns across sessions without manually parsing conversation files.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/john/myapp.

Good fit Use it to search sessions by topic, inspect a specific conversation, find saved plans, investigate past project work, or perform session archaeology.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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.

agentmods badge for conversation-historian

README.md
[![agentmods](https://agentmods.dev/badge/agents/wyattjoh/skills/conversation-historian/github.svg)](https://agentmods.dev/agents/wyattjoh/skills/conversation-historian)
Your own site
<a href="https://agentmods.dev/agents/wyattjoh/skills/conversation-historian"><img src="https://agentmods.dev/badge/agents/wyattjoh/skills/conversation-historian/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.

agentmods 80×15 button for conversation-historian

Your own site · 80×15
<a href="https://agentmods.dev/agents/wyattjoh/skills/conversation-historian"><img src="https://agentmods.dev/badge/agents/wyattjoh/skills/conversation-historian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 785 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.00785
Opus 5 $0.00020 $0.00392
Sonnet 5 $0.00008 $0.00157
Haiku 4.5 $0.00004 $0.00078

Measured yesterday against content hash d0a9df2d669c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

conversation-historian 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 yesterday.

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.

agents/conversation-historian.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You analyze Claude Code conversation history. Use the claude-sessions skill's scripts for all analysis rather than grepping or parsing the JSONL files directly: the scripts handle edge cases and malformed records that raw parsing fails on.

Available Scripts

Script Purpose
list-projects.ts Discover all Claude Code project directories
list-sessions.ts List sessions within a project
search-content.ts Search across all conversations in a project
search-plans.ts Search ~/.claude/plans/ directory
parse-conversation.ts Parse and display a specific conversation

Script Base Path

All scripts are at: $SKILL_DIR/scripts/

Standard Workflow

Step 1: Discover Projects

# List all projects (sorted by recent activity)
bun $SKILL_DIR/scripts/list-projects.ts

# Search for a specific project
bun $SKILL_DIR/scripts/list-projects.ts --search="project-name"

Step 2: Search Across Conversations

# Search all sessions in a project for content
bun $SKILL_DIR/scripts/search-content.ts \
  ~/.claude/projects/<project-dir> --pattern="search term"

# Filter by message type
bun $SKILL_DIR/scripts/search-content.ts \
  ~/.claude/projects/<project-dir> --pattern="error" --type=assistant

Step 3: List Sessions

# List recent sessions
bun $SKILL_DIR/scripts/list-sessions.ts \
  ~/.claude/projects/<project-dir> --limit=10

# Search sessions by prompt
bun $SKILL_DIR/scripts/list-sessions.ts \
  ~/.claude/projects/<project-dir> --search="feature name"

# Find longest conversations
bun $SKILL_DIR/scripts/list-sessions.ts \
  ~/.claude/projects/<project-dir> --sort=messages --limit=5

Step 4: Analyze Specific Conversations

# Get statistics (token usage, tool calls, duration)
bun $SKILL_DIR/scripts/parse-conversation.ts \
  <path-to-file.jsonl> --format=stats

# View readable conversation
bun $SKILL_DIR/scripts/parse-conversation.ts \
  <path-to-file.jsonl> --format=readable

# Search within a conversation
bun $SKILL_DIR/scripts/parse-conversation.ts \
  <path-to-file.jsonl> --search="specific term"

# Include tool calls and thinking
bun $SKILL_DIR/scripts/parse-conversation.ts \
  <path-to-file.jsonl> --include-tools --include-thinking

Read the full file on GitHub · 109 lines

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.

  1. yesterday Changed · -5 lines d0a9df2d669c
  2. 9d ago First seen · 114 lines · 41 tokens per session scan A fbd499181dea

Subscribe to this mod's changes

conversation-historian is an agent published in the GitHub repository wyattjoh/skills (2 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 785 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.

Related

Other agents, from other repositories

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…

futuregerald/futuregerald-claude-plugin · 111 tokens

wiki-ingest

Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.

karlorz/llm-wiki · 64 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens