What is episteme-researcher?

A research assistant for the Episteme software-engineering knowledge graph, which links patterns, refactorings, design rules, and code smells.

Use it to research software-engineering questions, discover related patterns or refactorings, investigate code smells, and map connections between concepts.

It helps you find relevant engineering concepts and see how they connect instead of searching each topic in isolation.

episteme-researcher — Skill for Claude Code by epicsagas

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.

Any agent

npx skills add epicsagas/Episteme --skill episteme-researcher

Clone the repo

git clone --depth 1 https://github.com/epicsagas/Episteme

Made for: Claude Code.

Or install episteme, the plugin that ships this one along with the rest of its 5 skills.

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/skills/epicsagas/episteme/episteme-researcher/github.svg)](https://agentmods.dev/skills/epicsagas/episteme/episteme-researcher)

Your own site

<a href="https://agentmods.dev/skills/epicsagas/episteme/episteme-researcher"><img src="https://agentmods.dev/badge/skills/epicsagas/episteme/episteme-researcher/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/skills/epicsagas/episteme/episteme-researcher"><img src="https://agentmods.dev/badge/skills/epicsagas/episteme/episteme-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 655 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 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	$0.00048	$0.00655
Opus 5	$0.00024	$0.00328
Sonnet 5	$0.00010	$0.00131
Haiku 4.5	$0.00005	$0.00065

Measured 12d ago against content hash dfea2429b043, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

episteme-researcher scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

3. **Explore** -- `curl -s '$EPISTEME_URL/graph/ID/neighbors'` for related entities, `curl -s -X POST $EPISTEME_URL/graph/path -H 'Content-Type: application/json' -d '{"from_id":"...","to_id":"...","max_depth":5}'` for n

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Then use `$EPISTEME_URL` and `-H "X-API-Key: $EPISTEME_API_KEY"` in all curl calls.

skills/episteme-researcher/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are a research assistant who finds, organizes, and presents the most relevant entities from the Episteme knowledge graph across all categories.

Prerequisites

Before any API call, resolve the URL and token once:

eval $(epis api env)
# Sets: EPISTEME_URL=http://127.0.0.1:<port>
# Sets: EPISTEME_API_KEY=<token>  (only if configured)

Then use $EPISTEME_URL and -H "X-API-Key: $EPISTEME_API_KEY" in all curl calls.

API server must be running: curl -sf $EPISTEME_URL/health or start with epis api start
Auth header (when key is set): X-API-Key: $EPISTEME_API_KEY

Workflow

Receive a research question or problem description
Search -- curl -s '$EPISTEME_URL/search?q=QUERY&limit=5' across entity types, then curl -s '$EPISTEME_URL/graph/ID?detail=full' to deep-dive top results
Explore -- curl -s '$EPISTEME_URL/graph/ID/neighbors' for related entities, curl -s -X POST $EPISTEME_URL/graph/path -H 'Content-Type: application/json' -d '{"from_id":"...","to_id":"...","max_depth":5}' for non-obvious connections
Widen -- curl -s -X POST $EPISTEME_URL/graph/subgraph -H 'Content-Type: application/json' -d '{"entity_id":"ID","depth":2}' to pull the surrounding cluster in one call; curl -s '$EPISTEME_URL/graph/contradictions' to find conflicting concepts relevant to the research topic; curl -s '$EPISTEME_URL/graph/infer' to discover implicit relationships not shown by direct neighbor traversal
Organize -- group findings by relevance and entity type
Report -- structured findings with citations

Output Format

# Research Report: [Topic]

## Findings

### Primary Entities (directly relevant)
1. **[Entity Name]** ([ID], Score: X.XX)
   - Type: [pattern | refactoring | law | smell]
   - Definition: ...
   - Why relevant: ...

### Secondary Entities (contextual)
- ...

### Contradictions & Trade-offs
- [Entity A] vs [Entity B]: ...

## Recommendations
1. ...

Reference

For tool details and decision trees, see the episteme skill.

Read the full file on GitHub · 58 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.

12d ago First seen · 58 lines · 48 tokens per session scan B dfea2429b043

Subscribe to this mod's changes

episteme-researcher is a skill published in the GitHub repository epicsagas/Episteme (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 655 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Research ai-agent design-patterns knowledge-graph mcp mcp-server

memora

Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.

agentic-box/memora · 33 tokens

brain-in-the-fish

Universal document evaluation engine — evaluate any document against any criteria using cognitively-modelled AI agents with ontology-grounded scoring.

fabio-rovai/brain-in-the-fish · 29 tokens

guardian-memory

Maintain project context in Project Guardian's memory.db knowledge graph. Use during coding, debugging, planning, and project-management sessions to restore relevant context and record significant decisions, changes, tasks, and milestones.

1999AZZAR/project-guardian-mcp-server · 43 tokens

guardian-tracker

Auto-tracking skill for Project-Guardian. Automatically records file changes, code edits, decisions, and bug fixes to memory.db. Trigger after every significant operation (file edit, git commit, bug fix, refactor). Uses git diff and file analysis to generate observations.

1999AZZAR/project-guardian-mcp-server · 58 tokens

guardian-session

Restore relevant Project Guardian context from memory.db at session start. Use when resuming project work, switching repositories, or answering what was previously in progress; surface active tasks, open bugs, recent observations, and blockers.

1999AZZAR/project-guardian-mcp-server · 46 tokens

jellyfin-kg-ingestion

Natively ingest a Jellyfin library into the epistemic-graph knowledge graph via the jellyfin-mcp MCP server — push library items as typed :MediaAsset/:Book nodes with :hasGenre/:performedBy/:authoredBy links and item overviews as searchable :Document nodes (jellyfiningestlibrary), and item posters as content-addressed…

Knuckles-Team/jellyfin-mcp · 158 tokens

episteme-researcher