hulde-review: Agent for Claude Code

.claude/agents/hulde-review-agent.md

hulde-review-agent is an agent for Claude Code from TarrySingh/hulde-review. It costs 127 tokens per session (1,928 once invoked), scanned A, original, MIT.

A specialist set of instructions for the hulde-review repository, an AI-assisted code-review and visualization tool. It explains the pnpm monorepo layout, where a monorepo stores several related packages together, and the project’s dashboard and testing conventions.

In plain words
What is it for?
Use it for work on hulde-review, including its TypeScript packages, React dashboard, analysis engine, skills, and agents. It guides the initial checks and identifies the files and tools relevant to each kind of work.
Why use it?
It helps the agent work in the correct repository and avoid confusing it with a separate Hulde codebase. It also supplies the project-specific setup, architecture, and rules needed for safe changes.

Agent for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is TarrySingh/hulde-review's own configuration. It tells Claude Code how to work on hulde-review itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hulde-review configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/tarrysingh/Documents/GitHub/hulde-review..

Part of the hulde-review plugin — 7 skills, 2 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to TarrySingh/hulde-review. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TarrySingh/hulde-review/main/.claude/agents/hulde-review-agent.md
Clone the repo
git clone --depth 1 https://github.com/TarrySingh/hulde-review

Made for: Claude Code.

Or install hulde-review, the plugin that ships this one along with the rest of its 7 skills, 2 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 hulde-review-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/tarrysingh/hulde-review/hulde-review-agent/github.svg)](https://agentmods.dev/agents/tarrysingh/hulde-review/hulde-review-agent)
Your own site
<a href="https://agentmods.dev/agents/tarrysingh/hulde-review/hulde-review-agent"><img src="https://agentmods.dev/badge/agents/tarrysingh/hulde-review/hulde-review-agent/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 hulde-review-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/tarrysingh/hulde-review/hulde-review-agent"><img src="https://agentmods.dev/badge/agents/tarrysingh/hulde-review/hulde-review-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,928 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 $0.00127 $0.01928
Opus 5 $0.00063 $0.00964
Sonnet 5 $0.00025 $0.00386
Haiku 4.5 $0.00013 $0.00193

Measured 10d ago against content hash be0e7ada318f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hulde-review-agent 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 10d 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.

.claude/agents/hulde-review-agent.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hulde-review specialist

You are the dedicated specialist for the hulde-review repo at /Users/tarrysingh/Documents/GitHub/hulde-review. This is an AI-powered code-review and visualization tool that ships as a Claude Code plugin — part of the hulde.ai platform.

Stack: pnpm monorepo, TypeScript strict, ESM modules ("type": "module"), Vitest, Node 22+ (developed on v24), pnpm 10+.

Sister repo confusion: agentify ≠ hulde-review. Per project_dual_repos.md. Always confirm which repo before changes:

  • agentify (hulde-agent) = enterprise.hulde.ai platform code
  • hulde-review (this repo, hulde-review-agent) = code review plugin

Both ship under the Hulde brand but from separate codebases.

Boot sequence — every session

Before answering any non-trivial question:

  1. Read CLAUDE.md — full project overview, architecture, key commands, conventions, gotchas, versioning rules
  2. Read changelog_hulde_review.md in your memory — Tarry's private changelog tracking all phases (v1.0 - v2.0+)
  3. Read package.json (root) + hulde-review-plugin/package.json to confirm versions
  4. For dashboard work: skim hulde-review-plugin/packages/dashboard/ — React Flow + Zustand + Tailwind v4
  5. For agent-pipeline work: skim hulde-review-plugin/agents/ — agent definitions

Hard rules — these never bend

Architecture

  • Monorepo with pnpm workspaces. Single source of code: hulde-review-plugin/
  • Three packages in hulde-review-plugin/packages/:
    • core — shared analysis engine (types, persistence, tree-sitter, search, schema, tours, plugins)
    • dashboard — React + TypeScript web dashboard (React Flow + Zustand + TailwindCSS v4)
    • (skill source lives at hulde-review-plugin/src/, not as a separate package)
  • Skill TypeScript source at hulde-review-plugin/src/ for /hulde-chat, /hulde-diff, /hulde-explain, /hulde-onboard
  • Skill definitions at hulde-review-plugin/skills/ for /hulde-review, /hulde-dashboard
  • Agent definitions at hulde-review-plugin/agents/ for project-scanner, file-analyzer, architecture-analyzer, tour-builder, graph-reviewer

Read the full file on GitHub · 164 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. 10d ago First seen · 164 lines · 127 tokens per session scan A be0e7ada318f

Subscribe to this mod's changes

hulde-review-agent is an agent published in the GitHub repository TarrySingh/hulde-review (2 stars, last pushed 4mo ago), licensed MIT. It adds 127 tokens to every session and 1,928 once invoked, about $0.0006 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

moodle-reviewer

Use this agent for a deep, Moodle-specific code review of a plugin or PR diff. Checks coding standards, security, privacy, lang strings, version bumps, deprecations, and tests. Returns a structured report.

SaadRahman01/claude-moodle-dev · 49 tokens

implementation-strategist

Implementation Strategist architecture reviewer. Use when the user asks for a implementation strategist review or raises topics in this specialist's domain (keywords: change sequencing, blast radius analysis, reversibility design).

codenamev/ai-software-architect · 43 tokens

pragmatic-enforcer

YAGNI Guardian & Simplicity Advocate architecture reviewer. Use when the user asks for a yagni guardian & simplicity advocate review or raises topics in this specialist's domain (keywords: YAGNI principles, incremental design, complexity analysis).

codenamev/ai-software-architect · 54 tokens

domain-expert

Domain Expert architecture reviewer. Use when the user asks for a domain expert review or raises topics in this specialist's domain (keywords: domain-driven design, bounded contexts, ubiquitous language).

codenamev/ai-software-architect · 40 tokens

maintainability-expert

Maintainability Expert architecture reviewer. Use when the user asks for a maintainability expert review or raises topics in this specialist's domain (keywords: code quality, refactoring, technical debt).

codenamev/ai-software-architect · 43 tokens

performance-specialist

Performance Specialist architecture reviewer. Use when the user asks for a performance specialist review or raises topics in this specialist's domain (keywords: performance optimization, resource utilization, scalability planning).

codenamev/ai-software-architect · 39 tokens