agentmods.dev

task-verify

task-verify is a skill for Claude Code from FrontisAI/NatureBench. It costs 38 tokens per session (1,273 once invoked), scanned A, original, MIT.

A validation process for a machine-learning benchmark task package. It checks that the files agree with one another and runs a basic solver test to see whether the package works.

In plain words
What is it for?
Use it to check the problem, evaluation, metadata, data folders, and Docker environment across 36 predefined checks.
Why use it?
It catches missing files, inconsistent descriptions, invalid metadata, broken environments, and benchmark problems before the task is used.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; installed under .agents/ (shared by several agents).

not rated 137repo +1 17d ago A scan SkillSpector: pass 38 tokens original MIT

Good fit Use it to check the problem, evaluation, metadata, data folders, and Docker environment across 36 predefined checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/frontisai/naturebench/task-verify
View source ↗ FrontisAI/NatureBench frontisai.github.io
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.

Any agent
npx skills add FrontisAI/NatureBench --skill task-verify
Clone the repo
git clone --depth 1 https://github.com/FrontisAI/NatureBench

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 task-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/frontisai/naturebench/task-verify/github.svg)](https://agentmods.dev/skills/frontisai/naturebench/task-verify)
Your own site
<a href="https://agentmods.dev/skills/frontisai/naturebench/task-verify"><img src="https://agentmods.dev/badge/skills/frontisai/naturebench/task-verify/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 task-verify

Your own site · 80×15
<a href="https://agentmods.dev/skills/frontisai/naturebench/task-verify"><img src="https://agentmods.dev/badge/skills/frontisai/naturebench/task-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,273 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
SkillSpector: 1 finding, up to low

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • low Excessive Agency · line 109
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
How audits are shown
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 $0.00038 $0.01273
Opus 5.5 $0.00015 $0.00509
Sonnet 5.5 $0.00008 $0.00255
Haiku 4.5 $0.00004 $0.00127

Measured 2mo ago against content hash c6a659440fa1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task-verify 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run_baseline_test.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

naturegym/.agents/skills/task-verify/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task-Verify Skill

Verify that a task package built by task-build is valid, consistent, and usable as a benchmark.

Input Requirements

User provides:

  • task_package_path: Path to task package directory containing problem/, evaluation/, metadata.json

Optional:

  • filter_result.json: If present in task package, used for algorithm name verification (C2.3, C2.4)

Verification Workflow

Execute 5 phases with 36 checks total. If Phase 0 fails, terminate immediately. The check count MUST be exactly 36. Do not skip, merge, or invent checks beyond this list.

Phase 0: File Completeness & Structure (5 checks)

Fast-fail validation. See references/verification_rules.md for detailed rules.

  • C0.1: Required files exist
  • C0.2: Instance directories match between problem/data/ and evaluation/ground_truth/
  • C0.3: metadata.json is valid JSON with required fields
  • C0.4: evaluator.py has valid Python syntax
  • C0.5: Dockerfile.v3 dependency viability (compatibility, availability, API compatibility)

Phase 1: Cross-File Consistency (9 checks)

Ensure all documents agree on key information. See references/verification_rules.md.

  • C1.1: Task name matches between README and metadata.json
  • C1.2: Instance names consistent across all files and directories
  • C1.3: Metric names consistent across README, metadata, evaluator
  • C1.4: Metric directions match between README and metadata
  • C1.5: Exactly one primary metric designated in README
  • C1.6: Output format in README matches evaluator expectations
  • C1.7: Ground truth paths in evaluator actually exist
  • C1.8: data_description.md directory structure matches actual files in problem/data/
  • C1.9: data_description.md has required section structure (Directory Structure, Dataset Overview, File Formats & Schemas, Special Notes)

Phase 2: Information Firewall Verification (6 checks)

Prevent paper/algorithm information leakage. See references/verification_rules.md.

Read the full file on GitHub · 119 lines

Files

What ships with it

4 files 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.

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. 2mo ago First seen · 119 lines · 38 tokens per session scan A c6a659440fa1

Subscribe to this mod's changes

task-verify is a skill published in the GitHub repository FrontisAI/NatureBench (137 stars, last pushed 17d ago), licensed MIT. It adds 38 tokens to every session and 1,273 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Testing
Related

task-verify compared with skills from other repositories

task-verify next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
task-verifyFrontisAI/NatureBenchSkill13717d agoMITA38Claude Code
research-engineerdavila7/claude-code-templatesSkill33ktodayMITA43Claude Code, Codex
tika-eval-compareapache/tikaSkill4.1kyesterdayApache-2.0A50Claude Code, Codex
cua-driverdavidondrej/skillsSkill4.3k3d agoMITA68Claude Code, Codex
jetson-validate-imageNVIDIA/skillsSkill3.9kyesterdayApache-2.0B50Claude Code, Codex
atmos-validationcloudposse/atmosSkill1.4kyesterdayApache-2.0A31Claude Code
tddcodewithmukesh/dotnet-claude-kitSkill8052d agoMITA81Claude Code