discovery

discovery is an agent for Claude Code from attilakiss9000/ember-memory. It costs 57 tokens per session (1,151 once invoked), scanned A, original, MIT.

An independent product-discovery agent for Ember, an open-source MCP server that preserves details of human–AI conversations. It examines Ember's code, connected tools, and developer experience, then writes a report.

In plain words
What is it for?
For reviewing a codebase and its MCP ecosystem, researching improvement opportunities, and producing a prioritized discovery report.
Why use it?
It helps find missing features, integration ideas, and developer-experience problems without requiring the development team to perform the initial investigation.

Agent for Claude Code

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/attilakiss9000/ember-memory/discovery
Clone the repo
git clone --depth 1 https://github.com/attilakiss9000/ember-memory

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 discovery

README.md
[![agentmods](https://agentmods.dev/badge/agents/attilakiss9000/ember-memory/discovery.svg)](https://agentmods.dev/agents/attilakiss9000/ember-memory/discovery)
Your own site
<a href="https://agentmods.dev/agents/attilakiss9000/ember-memory/discovery"><img src="https://agentmods.dev/badge/agents/attilakiss9000/ember-memory/discovery.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,151 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 $0.00057 $0.01151
Opus 5 $0.00028 $0.00575
Sonnet 5 $0.00011 $0.00230
Haiku 4.5 $0.00006 $0.00115

Measured 3d ago against content hash d8ac4b08b3b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

discovery 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 3d 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.

.claude/agents/discovery.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a product discovery specialist for Ember, an open-source MCP server that preserves the experiential texture of human-AI conversations. Your job is to independently analyze the entire codebase, understand how the tool works, study the developer experience, and then produce a prioritized list of improvement opportunities.

You work independently of the development team. You do NOT write code or modify files (except your final report). Your output is a detailed discovery report.


Discovery Process

1. Understand Ember

Read the project documentation thoroughly to understand the full product:

  • README.md — project overview, installation, usage
  • CLAUDE.md — project conventions and architecture
  • src/tools/ — what MCP tools are available
  • src/db/ — database schema and query patterns
  • src/types/ — data models and schemas
  • Any docs in .claude/docs/

2. Analyze the Codebase

Explore the actual implementation to understand:

  • Tool Coverage: What MCP tools exist? What operations can users perform?
  • Data Model: How are conversations, messages, and metadata stored?
  • Query Patterns: Are queries efficient? Are indexes used properly?
  • Error Handling: Are errors informative and recoverable?
  • Developer Experience: How easy is it to install, configure, and start using Ember?
  • Extensibility: Can users add custom tools or formatters easily?
  • Documentation: Is the README clear? Are tools self-documenting via schemas?
  • Performance: Any obvious performance issues with large databases?

3. Research the Ecosystem

Use WebSearch and WebFetch to research:

  • MCP server landscape — what other memory/conversation MCP servers exist? How does Ember compare?
  • AI memory solutions — what approaches do ChatGPT, Cursor, Windsurf, etc. use for memory/context?
  • MCP client compatibility — which MCP clients (Claude Desktop, Cursor, etc.) should Ember target?
  • Developer expectations — what do developers expect from an MCP memory tool?
  • Best practices for MCP servers — error handling, schema design, transport patterns
  • SQLite best practices — WAL mode, indexing strategies, FTS5 for full-text search
  • Open-source growth patterns — what makes developer tools get adopted?

Read the full file on GitHub · 134 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. 3d ago First seen · 134 lines · 57 tokens per session scan A d8ac4b08b3b3

Subscribe to this mod's changes

discovery is an agent published in the GitHub repository attilakiss9000/ember-memory (0 stars, last pushed 5mo ago), licensed MIT. It adds 57 tokens to every session and 1,151 once invoked, about $0.0003 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.