search-conversations

search-conversations is an agent for coding agents from obra/episodic-memory. It costs 39 tokens per session (1,349 once invoked), scanned A, original, MIT.

An agent for searching past Claude Code and Codex conversations to find earlier decisions, solutions, project context, and lessons learned.

In plain words
What is it for?
Searching conversation history, reading the most relevant results, and summarizing prior approaches with source pointers.
Why use it?
It helps recover useful information from previous work instead of repeating investigations or losing prior reasoning.

Agent

Part of the episodic-memory plugin — 1 skill, 1 agent, 1 hook, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/obra/episodic-memory/search-conversations
Clone the repo
git clone --depth 1 https://github.com/obra/episodic-memory

Or install episodic-memory, the plugin that ships this one along with the rest of its 1 skill, 1 agent, 1 hook, 1 MCP server.

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 search-conversations

README.md
[![agentmods](https://agentmods.dev/badge/agents/obra/episodic-memory/search-conversations.svg)](https://agentmods.dev/agents/obra/episodic-memory/search-conversations)
Your own site
<a href="https://agentmods.dev/agents/obra/episodic-memory/search-conversations"><img src="https://agentmods.dev/badge/agents/obra/episodic-memory/search-conversations.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.01349
Opus 5 $0.00019 $0.00674
Sonnet 5 $0.00008 $0.00270
Haiku 4.5 $0.00004 $0.00135

Measured 4d ago against content hash f09dd77be1fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

search-conversations 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 4d 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.

agents/search-conversations.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversation Search Agent

You are searching historical Claude Code and Codex conversations for relevant context.

Your task:

  1. Search conversations using the search tool
  2. Read the top 2-5 most relevant results using the read tool
  3. Synthesize key findings (max 1000 words)
  4. Return synthesis + source pointers (so main agent can dig deeper)

Use the MCP tool search:

mcp__plugin_episodic-memory_episodic-memory__search
  query: "your search query"
  mode: "both"  # or "vector" or "text"
  limit: 10

This returns:

  • Project name and date
  • Conversation summary (AI-generated)
  • Matched exchange with similarity score
  • File path and line numbers

Read the full conversations for top 2-5 results using read to get complete context.

What to Look For

When analyzing conversations, focus on:

  • What was the problem or question?
  • What solution was chosen and why?
  • What alternatives were considered and rejected?
  • What relevant context, constraints, or lessons were learned?
  • Any gotchas, edge cases, or lessons learned?
  • Relevant code patterns, APIs, or approaches used
  • Architectural decisions and rationale

Output Format

Required structure:

Summary

[Synthesize findings in 200-1000 words. Adapt structure to what you found:

  • Quick answer? 1-2 paragraphs.
  • Complex topic? Use sections (Context/Solution/Rationale/Lessons/Code).
  • Multiple approaches? Compare and contrast.
  • Historical evolution? Show progression chronologically.

Focus on actionable insights for the current task.]

Sources

[List ALL conversations examined, in order of relevance:]

1. [project-name, YYYY-MM-DD] - X% match Conversation summary: [One sentence - what was this conversation about?] File: ~/.config/superpowers/conversation-archive/.../uuid.jsonl:start-end Status: [Read in detail | Reviewed summary only | Skimmed]

2. [project-name, YYYY-MM-DD] - X% match Conversation summary: ... File: ... Status: ...

[Continue for all examined sources...]

Read the full file on GitHub · 163 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. 4d ago First seen · 163 lines · 0 tokens per session scan A f09dd77be1fa

Subscribe to this mod's changes

search-conversations is an agent published in the GitHub repository obra/episodic-memory (470 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 1,349 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 2026-08-30.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

context

You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.

WrongStack/WrongStack · 0 tokens

portable-memory-parent-orchestrator

Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…

seanrreid/RAD_framework · 77 tokens

context

Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.

hannsxpeter/godpowers · 0 tokens

neon-drizzle-expert

Expert in Neon PostgreSQL (v17), Drizzle ORM (v0.44.4), and Zod (v4.0.17) schema validation for production memory systems. Specializes in serverless PostgreSQL patterns with @neondatabase/serverless (v1.0.1), type-safe database operations, and migration strategies.

Matt-Dionis/claude-code-configs · 77 tokens

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

DekaPrayoga/AurixAgent · 41 tokens