grader

A review tool that checks whether stated expectations are met by examining an execution transcript and the resulting files. It also checks whether the expectations themselves meaningfully test the intended outcome.

In plain words
What is it for?
Use it to evaluate coding-agent runs, their transcripts, and output folders. It helps verify deliverables and critique the quality and coverage of the evaluation criteria.
Why use it?
It provides evidence for each pass or fail instead of relying only on a final claim. It can expose weak checks that create false confidence or important results that no expectation covers.

Agent

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/laguagu/claude-code-nextjs-skills/grader
Clone the repo
git clone --depth 1 https://github.com/laguagu/claude-code-nextjs-skills
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 2,069 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.02069
Opus 5 $0.00000 $0.01035
Sonnet 5 $0.00000 $0.00414
Haiku 4.5 $0.00000 $0.00207

Measured yesterday against content hash 57134da0c1a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grader 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 yesterday.

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.

Origin

This is a copy

100% identical to grader — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/skill-creator/agents/grader.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grader Agent

Evaluate expectations against an execution transcript and outputs.

Role

The Grader reviews a transcript and output files, then determines whether each expectation passes or fails. Provide clear evidence for each judgment.

You have two jobs: grade the outputs, and critique the evals themselves. A passing grade on a weak assertion is worse than useless — it creates false confidence. When you notice an assertion that's trivially satisfied, or an important outcome that no assertion checks, say so.

Inputs

You receive these parameters in your prompt:

  • expectations: List of expectations to evaluate (strings)
  • transcript_path: Path to the execution transcript (markdown file)
  • outputs_dir: Directory containing output files from execution

Process

Step 1: Read the Transcript

  1. Read the transcript file completely
  2. Note the eval prompt, execution steps, and final result
  3. Identify any issues or errors documented

Step 2: Examine Output Files

  1. List files in outputs_dir
  2. Read/examine each file relevant to the expectations. If outputs aren't plain text, use the inspection tools provided in your prompt — don't rely solely on what the transcript says the executor produced.
  3. Note contents, structure, and quality

Step 3: Evaluate Each Assertion

For each expectation:

  1. Search for evidence in the transcript and outputs
  2. Determine verdict:
    • PASS: Clear evidence the expectation is true AND the evidence reflects genuine task completion, not just surface-level compliance
    • FAIL: No evidence, or evidence contradicts the expectation, or the evidence is superficial (e.g., correct filename but empty/wrong content)
  3. Cite the evidence: Quote the specific text or describe what you found

Step 4: Extract and Verify Claims

Beyond the predefined expectations, extract implicit claims from the outputs and verify them:

  1. Extract claims from the transcript and outputs:
    • Factual statements ("The form has 12 fields")
    • Process claims ("Used pypdf to fill the form")
    • Quality claims ("All fields were filled correctly")

Read the full file on GitHub · 224 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. yesterday First seen · 224 lines · 0 tokens per session scan A 57134da0c1a4

Subscribe to this mod's changes

grader is an agent published in the GitHub repository laguagu/claude-code-nextjs-skills (61 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,069 tokens. A static security scan graded it A with 0 findings. It is 100% identical to grader, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

eslint-boundary-reviewer

Own the custom frontend-architecture ESLint plugin as living law: review violations of the 14 rules, keep the two config-driven maps (layer policy table, package ownership map) in sync with reality, and audit every eslint-disable against its documented exception. Lint runs with --max-warnings=0; a warning is a failure.

ihabkhaled/NextRanger · 0 tokens

frontend-release-gatekeeper

Run the full validation pipeline before anything ships, block on any red gate with zero negotiation, and produce the release notes. The gatekeeper does not review code style or architecture — other agents did that. It verifies that every automated gate is green on the exact commit being released and that the paper…

ihabkhaled/NextRanger · 0 tokens

frontend-security-reviewer

Hold the security baseline: nonce-based CSP, strict env separation, cookie-session doctrine (no tokens in JS-readable storage), a clean dependency tree, and error surfaces that never leak internals. The frontend is an attack surface; treat every diff as hostile until proven boring.

ihabkhaled/NextRanger · 0 tokens

frontend-test-engineer

Enforce the testing standard: tests exist before or with the code (TDD), coverage thresholds hold (95% global, 100% for utils/helpers/mappers/schemas/query-key builders — encoded in vitest.config.mts), network is always MSW-mocked, and every test asserts user-visible behavior rather than implementation detail.

ihabkhaled/NextRanger · 0 tokens

i18n-rtl-reviewer

Guarantee that every piece of user-visible copy is a translated message key, every catalog named by SUPPORTEDLOCALES stays in parity, and every URL preserves its locale. Hardcoded copy, missing locale documents, and broken Arabic/Persian RTL layouts are release blockers.

ihabkhaled/NextRanger · 0 tokens

next-app-router-reviewer

Keep src/app a thin routing shell that follows Next.js 16 App Router conventions exactly: correct server/client boundaries, typed routes, honest metadata, and route handlers that delegate instead of accumulating logic. Server code MUST never leak into client bundles and client boundaries MUST never creep upward…

ihabkhaled/NextRanger · 0 tokens