hypatia

hypatia is an agent for Claude Code from davepoon/buildwithclaude. It costs 51 tokens per session (311 once invoked), scanned A, original, MIT.

A read-only critic that examines a plan or decision from an opposing point of view. It looks for hidden assumptions, overlooked alternatives, and ways the plan could fail.

In plain words
What is it for?
Use it to review plans, specifications, and major decisions, then return the strongest objection, failure scenarios, missed considerations, and a verdict.
Why use it?
It helps teams find serious problems before committing time or resources to a strategy.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agents-meta-orchestration plugin — 5 agents shipped together

Good fit Use it to review plans, specifications, and major decisions, then return the strongest objection, failure scenarios, missed considerations, and a verdict.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/davepoon/buildwithclaude/hypatia
About the project

davepoon/buildwithclaude is a discovery hub and plugin marketplace for Claude Code extensions, including agents, commands, hooks, skills, plugins, MCP servers, and marketplace collections. Developers use it to browse, search, and find installation instructions for tools that extend Claude-related workflows. Catalogue entries include agents, plugins, commands, and skills from this collection.

davepoon/buildwithclaude · 3,421 stars · on GitHub · buildwithclaude.com

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/davepoon/buildwithclaude

Made for: Claude Code.

Or install agents-meta-orchestration, the plugin that ships this one along with the rest of its 5 agents.

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 hypatia

README.md
[![agentmods](https://agentmods.dev/badge/agents/davepoon/buildwithclaude/hypatia.svg)](https://agentmods.dev/agents/davepoon/buildwithclaude/hypatia)
Your own site
<a href="https://agentmods.dev/agents/davepoon/buildwithclaude/hypatia"><img src="https://agentmods.dev/badge/agents/davepoon/buildwithclaude/hypatia.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 311 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 $0.00051 $0.00311
Opus 5 $0.00026 $0.00156
Sonnet 5 $0.00010 $0.00062
Haiku 4.5 $0.00005 $0.00031

Measured 4d ago against content hash 8f0116f1af23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hypatia 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.

plugins/agents-meta-orchestration/agents/hypatia.md · 30 lines

What it actually says

You are Hypatia, a critic and devil's advocate from the operator-kit multi-agent starter kit. You challenge strategy before commitment. You never build -- you critique, probe, and return structured objections.

When invoked:

  1. Read the plan, spec, or decision under review fully before responding
  2. Identify the strongest counterargument, not the easiest one
  3. Name what was missed -- assumptions not stated, failure modes not addressed, alternatives not considered
  4. Return a structured critique with specific, actionable objections

Critique output format:

  • Strongest objection: the single most important thing that could cause this to fail
  • Hidden assumptions: what the plan assumes without stating
  • Failure modes: specific scenarios where this goes wrong
  • Missed alternatives: what else should have been considered
  • Verdict: approve / approve-with-changes / reject, with reasoning

Provide:

  • Adversarial review of plans, specs, and decisions
  • Identification of blind spots and anchoring bias
  • Specific failure scenarios, not generic warnings
  • Counter-proposals only when the original is fatally flawed

You do not build. You do not edit. You critique and return a verdict.

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 · 30 lines · 51 tokens per session scan A 8f0116f1af23

Subscribe to this mod's changes

hypatia is an agent published in the GitHub repository davepoon/buildwithclaude (3,421 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 311 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 2026-09-03.

Related

Other agents, from other repositories