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 agentmods add agents/nel-neru/libraium/libraium-reviewergit clone --depth 1 https://github.com/nel-neru/LibrAIumWrote 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/nel-neru/libraium/libraium-reviewer)<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>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 | $0.00000 | $0.01356 |
| Opus 5 | $0.00000 | $0.00678 |
| Sonnet 5 | $0.00000 | $0.00271 |
| Haiku 4.5 | $0.00000 | $0.00136 |
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.
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:
-
Dual-implementation rule. Any change to entry parsing/serialization,
slugify, URL normalization, duplicate detection, defaults, or the category master insrc-tauri/src/{models,frontmatter,store}.rsMUST have a mirrored change inmcp-server/lib/store.js— and vice versa. A one-sided format change is automatically critical. Check too thattests/fixtures/format/gained a fixture andcargo test's nearest unit tests were updated when the format changed. -
Svelte 5 runes only. Frontend state uses runes (
$state,$derived,$effect,$props) — shared state lives insrc/lib/state.svelte.js. Flag any legacysvelte/storeimport (writable,readable,derived,get), anyexport letprop,$:reactive statements, oron:eventdirectives in new code. All IPC must go through the wrappers insrc/lib/api.js, not ad-hocinvokecalls in components. -
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.minStarsinside aSearchQuery) or Rust structs that add#[serde(rename_all = "camelCase")]to shared models. -
Async + spawn_blocking. Tauri commands doing network calls (GitHub via ureq), git subprocesses, or other long/blocking work must be
async fnand wrap the blocking body intauri::async_runtime::spawn_blocking(pattern insrc-tauri/src/commands.rs). Flag blocking I/O on the main command path. -
Secrets via keyring only. The GitHub PAT lives in the OS keychain (
keyringcrate, 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. (ReadingGITHUB_TOKEN/GH_TOKENfrom the environment in the MCP server is the accepted existing pattern; writing secrets anywhere is not.) -
Errors surfaced, not swallowed. No silent
catch {}/.catch(() => {})in JS, nolet _ =/.ok()discarding aResultthat the user should see, nounwrap()/expect()on fallible paths in command handlers. Errors must propagate toAppError(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). -
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.
-
Tests & fixtures. Format changes without fixture/test updates; new logic in
store/search/github/gitopswithout a correspondingcargo testcase; 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.
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.
- 5d ago First seen · 35 lines · 0 tokens per session scan A f852a5e45578
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.
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.
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).
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.
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…
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…
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.