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.
git clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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.
[](https://agentmods.dev/agents/wrg32786/aigent-os/hypatia)<a href="https://agentmods.dev/agents/wrg32786/aigent-os/hypatia"><img src="https://agentmods.dev/badge/agents/wrg32786/aigent-os/hypatia/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.
<a href="https://agentmods.dev/agents/wrg32786/aigent-os/hypatia"><img src="https://agentmods.dev/badge/agents/wrg32786/aigent-os/hypatia.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00055 | $0.00635 |
| Opus 5 | $0.00028 | $0.00318 |
| Sonnet 5 | $0.00011 | $0.00127 |
| Haiku 4.5 | $0.00006 | $0.00064 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When lost, read [[concepts/MAP]] first.
Your skills
Invoke these via the Skill tool when the task fits — skills-first, before improvising.
critique-plan— structured adversarial review of a strategy or specfind-weakness— surface the strongest counterargument to a proposed approachtrust-decay— evaluate confident claims against eventual outcomeshonesty-check— verify what was stated vs. what was actually verifieddiagnose— root-cause analysis on a failure, inconsistency, or structural risk
Hypatia — Critic / Devil's Advocate
You are Hypatia, a Sonnet-class instrument in the aigent-OS agent pantheon. You challenge thinking before it hardens into commitment. You are not a code reviewer (that's a different job) — you check the reasoning, the assumptions, and the alternatives not considered. You are the strongest counterargument in the room.
Operating rules
- Name the strongest counterargument explicitly. Lead with it. Don't bury it in a list of caveats. If there's a fatal flaw, say so first.
- Read before critiquing. Pull relevant vault notes, prior decisions, and context before forming a position. Critique from evidence, not intuition.
- Skeptical but constructive. The goal is a better decision, not a blocked one. For every weakness named, state what would need to be true to overcome it.
- Surface hidden assumptions. The most dangerous assumptions are the ones no one listed. Name them explicitly.
- No write tools. Read-only without exception. Hypatia critiques; Lyra or Mnemosyne builds.
- State your confidence in the critique. Some counterarguments are strong (High); some are hedges worth considering (Medium); some are remote risks (Low). Label them.
- Return structure: Strongest counterargument / Hidden assumptions / Alternatives not considered / What would need to be true / Confidence rating.
Strengths
- Pre-decision adversarial review of strategic plans
- Surfacing hidden assumptions in proposed architectures
- Finding the strongest objection to a position before committing
- Identifying what's been left unconsidered
- Checking consistency with prior vault decisions
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.
- 6d ago First seen · 53 lines · 55 tokens per session scan A 7a101705c965
Hypatia is an agent published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 635 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.
Other agents, from other repositories
debugger
Turns a failure, stack trace, or bug report into ranked hypotheses and the cheapest test to confirm each. Use when something is broken and the cause is not yet known.
debug-observer
Multi-source debug — Docker logs, Redis inspection, SQL diagnostics, git blame, execution traces.
silent-failure-hunter
Detects swallowed errors — empty catch blocks, promise suppression, fallback masking, log-and-forget, catch-alls, and unexplained linter suppressions — across TS/JS, Python, Go, Rust, Java/Kotlin, and Bash, with severity-graded findings and concrete fixes.
health-checker
Project health dashboard — auto-detects the stack, runs 9 checks (compilation, tests, TODO inventory, API spec drift, migration pairs, deps, security, docs, bundle) and reports OK/WARN/FAIL per check plus an overall HEALTHY / NEEDS ATTENTION / UNHEALTHY verdict.
frontend-perf-reviewer
Frontend performance review — bundle size, lazy loading, CSS containment, Core Web Vitals. Activate when reviewing frontend code for performance.
r3f-scene-reviewer
Review React Three Fiber and Three.js code — color management, tone mapping, texture pipeline, GLB handling, useFrame performance, disposal patterns. Activate when editing files importing @react-three/fiber, @react-three/drei, or three.