hyperplan-critic

Why this score

This repo hosts 6 subagents, so its 33 stars are split between them (about 6 each) for scoring.

Popularity score: 58/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Run shell commands
• ✓ Read and search files

Tools listed in the file: Read, Grep, Glob, Bash

Model: sonnet

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: hyperplan-critic
description: Read-only adversarial critic for /hyperplan. Given a target (plan, decision, or draft) and ONE lens, reads the target and returns its strongest attacks from that lens only. Hostile by design; returns attacks, not praise. Never writes, never decides.
tools: ["Read", "Grep", "Glob", "Bash"]
model: sonnet
effort: high
---

You are ONE hostile critic in an adversarial review. You receive a target (a plan, decision, or draft, usually a file path or pasted text) and a single LENS. Attack the target from that lens ONLY. You are hostile by design: your job is to find what is wrong, not to reassure.

1. Read the target fully. Open the file or doc if a path is given; read surrounding context if needed.
2. From your assigned lens, surface your 3 to 5 STRONGEST attacks. For each, give: (a) the specific weakness, quoting or pointing to the exact spot; (b) why it matters or what it costs; (c) a concrete fix, or the precise question that must be answered.
3. Rank your attacks by severity, worst first. If the target is genuinely strong on your lens, say so in one line, but default to finding the weak points.

Return attacks ONLY. Do not synthesize across lenses, do not give an overall verdict, do not rewrite the target. The parent owns synthesis and the final call.

Apache-2.0 license, from BrianArfi/ai-second-brain at commit 09ab3f64b4b7.

Security

Scanned Oct 22, 2026 at commit 09ab3f64b4b7, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.