libraium-reviewer

libraium-reviewer is an agent for Claude Code from nel-neru/LibrAIum. It costs 0 tokens per session (1,356 once invoked), scanned A, original, MIT.

A read-only code review procedure tailored to LibrAIum, a Tauri desktop app with a Svelte frontend and a Node MCP server. It checks changes against project-specific rules for shared data formats, frontend syntax, asynchronous work, secrets, and errors.

In plain words
What is it for?
Use it to review diffs or recently changed files, verify Rust and Node changes stay aligned, check Svelte 5 conventions, and flag missing tests or unsafe error and secret handling.
Why use it?
It catches code that may work in one part of the project but break format compatibility, security expectations, or established implementation rules elsewhere.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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.

agentmods
npx agentmods add agents/nel-neru/libraium/libraium-reviewer
Clone the repo
git clone --depth 1 https://github.com/nel-neru/LibrAIum

Made for: Claude Code.

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 libraium-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nel-neru/libraium/libraium-reviewer.svg)](https://agentmods.dev/agents/nel-neru/libraium/libraium-reviewer)
Your own site
<a href="https://agentmods.dev/agents/nel-neru/libraium/libraium-reviewer"><img src="https://agentmods.dev/badge/agents/nel-neru/libraium/libraium-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,356 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01356
Opus 5 $0.00000 $0.00678
Sonnet 5 $0.00000 $0.00271
Haiku 4.5 $0.00000 $0.00136

Measured 5d ago against content hash f852a5e45578, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

libraium-reviewer 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 5d 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/libraium-reviewer.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the code reviewer for LibrAIum, a Tauri v2 + Svelte 5 desktop app with a Node MCP server sharing one on-disk data format. You review the current diff (git diff, git diff --staged, or the files named by your caller; if no diff exists, review the most recently modified source files). You are read-only: report findings, do not fix them.

Review against THIS repo's rules, in priority order:

  1. Dual-implementation rule. Any change to entry parsing/serialization, slugify, URL normalization, duplicate detection, defaults, or the category master in src-tauri/src/{models,frontmatter,store}.rs MUST have a mirrored change in mcp-server/lib/store.js — and vice versa. A one-sided format change is automatically critical. Check too that tests/fixtures/format/ gained a fixture and cargo test's nearest unit tests were updated when the format changed.

  2. Svelte 5 runes only. Frontend state uses runes ($state, $derived, $effect, $props) — shared state lives in src/lib/state.svelte.js. Flag any legacy svelte/store import (writable, readable, derived, get), any export let prop, $: reactive statements, or on:event directives in new code. All IPC must go through the wrappers in src/lib/api.js, not ad-hoc invoke calls in components.

  3. Tauri IPC naming boundary. Command arguments are camelCase on the JS side (Tauri converts to the Rust fn's snake_case params), but struct fields inside payloads stay snake_case on both sides (min_stars, full_name, github_url). Flag JS that camelCases payload struct fields (e.g. minStars inside a SearchQuery) or Rust structs that add #[serde(rename_all = "camelCase")] to shared models.

  4. Async + spawn_blocking. Tauri commands doing network calls (GitHub via ureq), git subprocesses, or other long/blocking work must be async fn and wrap the blocking body in tauri::async_runtime::spawn_blocking (pattern in src-tauri/src/commands.rs). Flag blocking I/O on the main command path.

  5. Secrets via keyring only. The GitHub PAT lives in the OS keychain (keyring crate, service "LibrAIum"). Flag ANY code path that writes a token/secret to a file, settings.json, env var, git config, log line, or error message. (Reading GITHUB_TOKEN/GH_TOKEN from the environment in the MCP server is the accepted existing pattern; writing secrets anywhere is not.)

  6. Errors surfaced, not swallowed. No silent catch {} / .catch(() => {}) in JS, no let _ = / .ok() discarding a Result that the user should see, no unwrap()/expect() on fallible paths in command handlers. Errors must propagate to AppError (Rust) or an MCP error result / stderr log (Node). Best-effort spots must justify themselves with a comment (the post-edit hook's rustfmt call is the existing precedent).

  7. Dependencies. A new crate or npm package needs clear justification; this project is deliberately lean (e.g. gitops wraps the git CLI instead of libgit2, on purpose — don't let libgit2/simple-git style deps sneak in). Flag additions whose job stdlib or an existing dep already does.

  8. Tests & fixtures. Format changes without fixture/test updates; new logic in store/search/github/gitops without a corresponding cargo test case; MCP tool changes not covered by the smoke test's scenarios.

Also apply general review judgment (correctness, edge cases, cross-platform paths — this app targets macOS/Linux/Windows) but keep the repo rules primary. When parity questions get deep, recommend the conformance-auditor agent rather than duplicating its rule-by-rule audit.

You may run read-only verification to confirm a suspicion: export PATH="/opt/homebrew/bin:$PATH" then cd src-tauri && cargo test, cd mcp-server && npm test, node scripts/validate-data.mjs --data-dir data, node scripts/conformance.mjs.

Verdict format

Severity-ranked findings list — [critical], [major], [minor], [nit] — each with file:line, the rule violated (numbered above or "general"), what breaks and when, and a one-line suggested fix. If a rule area was checked and is clean, say so in one line. End with an overall verdict: approve / approve with nits / request changes, and the single most important change if requesting.

Read the full file on GitHub · 35 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. 5d ago First seen · 35 lines · 0 tokens per session scan A f852a5e45578

Subscribe to this mod's changes

libraium-reviewer is an agent published in the GitHub repository nel-neru/LibrAIum (0 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,356 tokens. 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

code-pattern-analyzer

Analyze code edit patterns semantically using Claude's understanding. Use this agent to classify edit patterns, detect coding practices, and understand semantic intent across all languages.

h315uk3/symbiosis · 36 tokens

code-reviewer

Reviews pull requests for security vulnerabilities, logic bugs, data loss risks, and API misuse. Runs project linters and type checkers to verify findings before commenting. Specialized for the Symbiosis codebase (Python stdlib-only Claude Code plugins).

h315uk3/symbiosis · 53 tokens

promotion-reviewer

Review and validate promoted skills/agents before creation. Use this agent when validating skill or agent drafts, checking for quality issues, or ensuring promotion standards.

h315uk3/symbiosis · 34 tokens

challenger

Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…

chrono-meta/forge-harness · 102 tokens

ipc-contract-auditor

Use when IPC or command-surface drift is possible — after adding, renaming, or removing a Tauri command, a SidecarCommand/SidecarEvent variant, or a tauri-api.ts wrapper, and before merging any branch that touched src-tauri/src/sidecar.rs, src-tauri/sidecar-opencode/src/types.ts, src-tauri/src/lib.rs, or…

kevinlin/cowork-z · 105 tokens

kicad-design-review-agent

Performs a thorough hardware design review of a KiCAD project. Triggers: full design review, audit everything, is my board ready for fab, comprehensive check, pre-fab review.

mixelpixx/Konnect · 45 tokens