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.
npx skills add TarrySingh/hulde-review --skill hulde-review-codegit clone --depth 1 https://github.com/TarrySingh/hulde-reviewWrote 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/skills/tarrysingh/hulde-review/hulde-review-code)<a href="https://agentmods.dev/skills/tarrysingh/hulde-review/hulde-review-code"><img src="https://agentmods.dev/badge/skills/tarrysingh/hulde-review/hulde-review-code/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/skills/tarrysingh/hulde-review/hulde-review-code"><img src="https://agentmods.dev/badge/skills/tarrysingh/hulde-review/hulde-review-code.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 | $0.00033 | $0.03779 |
| Opus 5 | $0.00016 | $0.01889 |
| Sonnet 5 | $0.00007 | $0.00756 |
| Haiku 4.5 | $0.00003 | $0.00378 |
Grade B, and why
hulde-review-code scanned grade B with 1 finding 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 9d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf $PROJECT_ROOT/.hulde-review/intermediate Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hulde-review-code
Run a production-grade, language-profile-driven code review engine against the current codebase. Each detected language is matched to a Language Profile that defines exactly what deep analysis means for that language — static rules, semantic capabilities, migration targets, and LLM review context.
Options
$ARGUMENTSmay contain:--security-only— Only run security-related rules--legacy— Enable all legacy language rules (Fortran, COBOL, Ada, RPG, etc.)--strict— Treat medium findings as high--language <id>— Only analyze files matching this language profile (e.g.,fortran,typescript,cobol)--deep— Force LLM deep review on ALL files (not just complex ones)--migration— Generate migration plan even for modern languages--profile-status— Just print profile readiness status and exit- A path — Scope to a specific directory or file
Phase 0 — Pre-flight
-
Set
PROJECT_ROOTto the current working directory. -
Load Language Profiles. Import the language profile system from
@hulde-review/core:import { ALL_PROFILES, getProfileForFile, getReadyProfiles, getProfileStatus, } from "@hulde-review/core"; import { checkAllProfiles, getProfileSummary } from "@hulde-review/core"; -
If
--profile-statusis set, runcheckAllProfiles()and print the status table, then exit:╔══════════════════════════════════════════════════════════════╗ ║ LANGUAGE PROFILE STATUS ║ ╠══════════════════════════════════════════════════════════════╣ ║ READY (deep analysis): ║ ║ ✓ FORTRAN IV/77/90 — 12 rules, 5 capabilities, 4 targets║ ║ ✓ TypeScript / JavaScript — 15 rules, 4 capabilities ║ ║ ║ ║ STUB (basic analysis only): ║ ║ ○ COBOL — 0 rules, 0 capabilities ║ ║ ○ C / C++ — 0 rules, 0 capabilities ║ ║ ○ Python — 0 rules, 0 capabilities ║ ║ ○ Java — 0 rules, 0 capabilities ║ ║ ○ Ada — 0 rules, 0 capabilities ║ ║ ○ RPG (AS/400) — 0 rules, 0 capabilities ║ ╚══════════════════════════════════════════════════════════════╝Stop here. Do not proceed to analysis.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 315 lines · 33 tokens per session scan B bc71631739f8
hulde-review-code is a skill published in the GitHub repository TarrySingh/hulde-review (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 3,779 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
system-architect
This skill should be used when the user asks to "design a system", "architect a solution", "review architecture", "plan a refactoring", "evaluate technical trade-offs", or discusses software architecture patterns. Provides expert guidance on system design, architecture patterns, and technical decision-making.
grill
This skill should be used when the user asks to "grill", "interrogate", "stress-test a spec/plan", "adversarially review a proposal", or invokes /craft:grill. Convergent counterpart to brainstorm — interrogates a spec/plan/topic one question at a time to surface gaps, contradictions, and unresolved dependencies before…
architecture-review
Conducts a comprehensive multi-perspective architecture review using ALL architecture team members. Use when the user requests "Start architecture review", "Full architecture review", "Review architecture for version X.Y.Z", "Conduct comprehensive review", or when they want assessment from multiple perspectives. Do…
specialist-review
Conducts a focused review from ONE specific specialist's perspective (e.g., Security Specialist, Performance Expert). Use when the user requests "Ask [specialist role] to review [target]", "Get [specialist]'s opinion on [topic]", "Have [role] review [code/component]", or when they want deep expertise in ONE specific…
understand-diff
Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks.
code-quality-principles
Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or reviewing code for over-engineering.