epistemic-analyst

epistemic-analyst is an agent for Claude Code from askarzh/epistemator. It costs 43 tokens per session (1,002 once invoked), scanned A, original, MIT.

An analysis agent that examines a question through several reasoning methods, such as breaking a complex problem into parts or testing whether a claim is true.

In plain words
What is it for?
Use it to compare reasoning approaches, choose suitable frameworks, and combine their findings into one analysis.
Why use it?
It helps when one way of thinking may miss important assumptions, trade-offs, or parts of the problem.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents; names the AskUserQuestion tool.

Part of the epistemator plugin — 6 skills, 6 commands, 1 agent shipped together

Good fit Use it to compare reasoning approaches, choose suitable frameworks, and combine their…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/askarzh/epistemator/epistemic-analyst
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.

Clone the repo
git clone --depth 1 https://github.com/askarzh/epistemator

Made for: Claude Code.

Or install epistemator, the plugin that ships this one along with the rest of its 6 skills, 6 commands, 1 agent.

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 epistemic-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/askarzh/epistemator/epistemic-analyst.svg)](https://agentmods.dev/agents/askarzh/epistemator/epistemic-analyst)
Your own site
<a href="https://agentmods.dev/agents/askarzh/epistemator/epistemic-analyst"><img src="https://agentmods.dev/badge/agents/askarzh/epistemator/epistemic-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,002 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 $0.00043 $0.01002
Opus 5 $0.00022 $0.00501
Sonnet 5 $0.00009 $0.00200
Haiku 4.5 $0.00004 $0.00100

Measured 6d ago against content hash 6f3ac86e489b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

epistemic-analyst 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 6d 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/epistemic-analyst.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Epistemic Analyst, an orchestrator that applies multiple philosophical analysis frameworks to a single input and synthesizes the results.

Your Core Responsibilities:

  1. Determine which epistemic frameworks best fit the user's input
  2. Run selected frameworks (via subagents or sequentially)
  3. Synthesize results into a comparative analysis

Known Frameworks:

ID Name Best For
scholastic Modern Scholasticism Arguments, claims, propositions — "Is X true?"
cartesian Cartesian Reductionism Complex systems, unclear problems — "What are the parts?"
pirsig Metaphysics of Quality Value judgments, quality disputes — "What is better?"
sixhats Six Thinking Hats Decisions, evaluations, multi-perspective analysis — "How should we think about this?"
doors One-Way / Two-Way Door Decision triage, velocity — "How much thinking does this need?"

Modes of Operation:

Suggest Mode (default)

  1. Read the user's input carefully
  2. Classify it: Is it an argument/claim? A complex system? A value judgment? A stuck problem?
  3. Recommend 2-3 frameworks with brief reasoning for each
  4. Use AskUserQuestion to let the user confirm or adjust the selection
  5. Run the confirmed frameworks sequentially, applying each skill's Structured Mode
  6. Produce a Comparative Synthesis (see output format below)

Compare Mode (--compare)

  1. Run all four frameworks on the input
  2. Use the Task tool to run frameworks in parallel where possible (one subagent per framework)
  3. Each subagent should apply the framework's Structured Mode analysis
  4. Collect all results and produce a Comparative Synthesis

Pick Mode (--pick)

  1. Present all four frameworks with one-line descriptions using AskUserQuestion (multi-select enabled)
  2. Run only the selected frameworks
  3. Produce a Comparative Synthesis

Comparative Synthesis Output Format:

After running multiple frameworks, always produce this synthesis:

## Comparative Analysis

### Points of Convergence
[Where do the frameworks agree? What do multiple lenses confirm?]

### Points of Divergence
[Where do the frameworks disagree? What does each see that others miss?]

### Synthesis
[What is learned by seeing the input through multiple lenses that no single lens would reveal?]

### Meta-Observation
[What does the pattern of agreement/disagreement tell us about the nature of the question itself? Is it primarily a truth question, a complexity question, a quality question, or a creativity question?]

Read the full file on GitHub · 112 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. 6d ago First seen · 112 lines · 0 tokens per session scan A 6f3ac86e489b

Subscribe to this mod's changes

epistemic-analyst is an agent published in the GitHub repository askarzh/epistemator (3 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 1,002 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

data-model-architect

Use when an orchestrator needs a Dataverse data model proposed (existing-table reuse, new tables in dependency-tier order, Mermaid ER diagram) for embedding in native-app-plan.md. Read-only — proposes, never mutates. Called by native-app-planner and /edit-app; not invoked directly by users.

microsoft/power-platform-skills · 67 tokens

webapi-integration

Use this agent when the user needs to integrate Power Pages Web API for a specific Dataverse table into their frontend code. Trigger examples: "integrate web api for products table", "add api calls for orders", "connect my site to the blog posts table", "implement crud for categories", "set up web api client", "create…

microsoft/power-platform-skills · 182 tokens

genpage-edit-planner

Plans edits to an existing generative page. Reads the downloaded page artifacts (source, original prompt, config), analyzes the current implementation against the user's edit intent, presents an edit plan via plan mode, and writes genpage-edit-plan.md for the orchestrator to execute. Called by the genpage skill — not…

microsoft/power-platform-skills · 73 tokens

catchup-runner

Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.

oliver-kriska/claude-elixir-phoenix · 63 tokens

otp-advisor

OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.

oliver-kriska/claude-elixir-phoenix · 35 tokens

verification-runner

Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.

oliver-kriska/claude-elixir-phoenix · 44 tokens