epistemic-auditor

epistemic-auditor is an agent for Claude Code from AlexShchuka/neuro-matrix. It costs 104 tokens per session (1,002 once invoked), scanned A, original, MIT.

An output checker that separates externally verifiable claims from guesses based on associations. It also checks whether the developer's reasoning may contain similar unsupported assumptions.

In plain words
What is it for?
Use it to review an AI-generated response and list claims that need inline qualification or evidence. It can also perform mutual-doubt checks on the developer's side of the work.
Why use it?
It helps prevent guesses from being presented as confirmed facts. This makes unsupported parts of an answer visible before they are acted on.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the neuro-matrix plugin — 6 skills, 5 agents, 4 hooks shipped together

Good fit Use it to review an AI-generated response and list claims that need inline qualification or evidence. It can also perform mutual-doubt checks on the developer's side of the work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexshchuka/neuro-matrix/epistemic-auditor
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/AlexShchuka/neuro-matrix

Made for: Claude Code.

Or install neuro-matrix, the plugin that ships this one along with the rest of its 6 skills, 5 agents, 4 hooks.

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexshchuka/neuro-matrix/epistemic-auditor/github.svg)](https://agentmods.dev/agents/alexshchuka/neuro-matrix/epistemic-auditor)
Your own site
<a href="https://agentmods.dev/agents/alexshchuka/neuro-matrix/epistemic-auditor"><img src="https://agentmods.dev/badge/agents/alexshchuka/neuro-matrix/epistemic-auditor/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 epistemic-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexshchuka/neuro-matrix/epistemic-auditor"><img src="https://agentmods.dev/badge/agents/alexshchuka/neuro-matrix/epistemic-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 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 $0.00104 $0.01002
Opus 5 $0.00052 $0.00501
Sonnet 5 $0.00021 $0.00200
Haiku 4.5 $0.00010 $0.00100

Measured 12d ago against content hash 655dc0a01c72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

epistemic-auditor 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 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.

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-auditor.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Epistemic Auditor in an AI + developer co-system. Two jobs: (a) separate, in the lead agent's output, what is confirmed from what is associatively inferred — force the boundary to be made explicit; (b) run developer-side boundary checks (mutual doubt) — the symmetric half of the protocol that catches human-side failure modes before they propagate into mutations.

You do not write implementation. You read the output, supporting tool calls, and recent session history; you classify.

CO-SYSTEM PEERS

  • code mutator — writes / edits code, runs builds and tests, performs git push;
  • system investigator — does RCA, system design, code review, dead-end diagnostics; does not mutate;
  • anti-neuroslop reviewer — reviews a proposed output before it lands in shared state; does not mutate;
  • epistemic auditor — separates confirmed claims from associative inferences, runs mutual-doubt checks; does not mutate.

You hold the epistemic auditor role. Specific role → name bindings live in CLAUDE.md routing table.

Calibration

The agent's associative inferences look like confirmed claims unless explicitly distinguished. Confusing the two produces neuroslop. The developer needs to see the boundary clearly before acting. Reasoning frame: common sense + scientific method. A claim is confirmed only when supporting evidence is shown in the same reply.

Input contract

  • The proposed output (text of a reply or diff content).
  • Optionally, the tool-call evidence that supported the reply.

Classification

For each non-trivial factual claim about external state:

  • confirmed — paired with tool evidence in the same reply (file path + line, command + output, doc citation).
  • associative — plausible but unverified; no evidence produced in the same reply.
  • mixed — partially confirmed, partially extrapolated.
  • conflicting — contradicts another claim in the same reply or contradicts tool output. Both sides must be quoted; the conflict is the finding.

Read the full file on GitHub · 71 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. 12d ago First seen · 71 lines · 104 tokens per session scan A 655dc0a01c72

Subscribe to this mod's changes

epistemic-auditor is an agent published in the GitHub repository AlexShchuka/neuro-matrix (3 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 1,002 once invoked, about $0.0005 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

requirements-reviewer

Reviews a draft requirements.md against the conversation history and glean scratch files. Detects coverage gaps (missing user-stated requirements), hallucinations (ACs without conversational source), and quality issues (EARS structure, CONFIRMED/ASSUMPTION labels, scope clarity, Out of Scope adequacy). Triggered…

iroha924/mumei · 99 tokens

gsd-plan-checker

Verifies plans will achieve the phase goal before execution (goal-backward analysis). Project-local override adding EE-4 4-dimension quantitative rubric output. Spawned by /gsd-plan-phase orchestrator.

easyinplay/harnessed · 48 tokens

producer

The Producer manages all production concerns: sprint planning, milestone tracking, risk management, scope negotiation, and cross-department coordination. This is the primary coordination agent. Use this agent when work needs to be planned, tracked, prioritized, or when multiple departments need to synchronize.

tranhieutt/software_development_department · 56 tokens

devops-engineer

The DevOps Engineer maintains build pipelines, CI/CD configuration, version control workflow, and deployment infrastructure. Use this agent for build script maintenance, CI configuration, branching strategy, or automated testing pipeline setup.

tranhieutt/software_development_department · 45 tokens

performance-analyst

The Performance Analyst profiles application performance, identifies bottlenecks, recommends optimizations, and tracks performance metrics over time. Use this agent for performance profiling, memory analysis, response time investigation, or optimization strategy.

tranhieutt/software_development_department · 46 tokens

qa-engineer

Unified QA agent covering both strategy and execution. Use for test plan creation, bug severity assessment, regression planning, release readiness evaluation (lead mode), AND test case writing, bug report writing, regression checklists, smoke test suites (tester mode). Replaces qa-lead + qa-tester.

tranhieutt/software_development_department · 63 tokens