rewardkit

rewardkit is a skill for Claude Code, Codex from pku-liang/hwe-bench. It costs 46 tokens per session (2,322 once invoked), scanned A, a copy of rewardkit, Apache-2.0.

A Python package for turning test criteria into reward scores for Harbor tasks. Harbor is a system for running and evaluating agent tasks.

In plain words
What is it for?
Writing programmatic verifiers, configuring judge criteria, setting grading requirements, and producing reward files from a task's tests directory.
Why use it?
It provides a standard way to check whether a task was completed and record the result, including optional checks judged by another language model or agent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Writing programmatic verifiers, configuring judge criteria, setting grading requirements, and producing reward files from a task's tests directory.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pku-liang/hwe-bench/rewardkit
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 pku-liang/hwe-bench --skill rewardkit
Clone the repo
git clone --depth 1 https://github.com/pku-liang/hwe-bench

Made for: Claude Code, Codex.

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 rewardkit

README.md
[![agentmods](https://agentmods.dev/badge/skills/pku-liang/hwe-bench/rewardkit/github.svg)](https://agentmods.dev/skills/pku-liang/hwe-bench/rewardkit)
Your own site
<a href="https://agentmods.dev/skills/pku-liang/hwe-bench/rewardkit"><img src="https://agentmods.dev/badge/skills/pku-liang/hwe-bench/rewardkit/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 rewardkit

Your own site · 80×15
<a href="https://agentmods.dev/skills/pku-liang/hwe-bench/rewardkit"><img src="https://agentmods.dev/badge/skills/pku-liang/hwe-bench/rewardkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,322 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.
Origin 91% 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 5.1 $0.00046 $0.02322
Opus 5 $0.00023 $0.01161
Sonnet 5 $0.00009 $0.00464
Haiku 4.5 $0.00005 $0.00232

Measured 11d ago against content hash 4d2af48d018c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rewardkit 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 11d 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.

Origin

This is a copy

91% identical to rewardkit — 53 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.

deps/harbor/skills/rewardkit/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Help the user write task verifiers with Reward Kit. Reward Kit is a lightweight Python package that turns a directory of criteria files into a reward score. Each criterion is a Python function call or a TOML judge file; folders become separate rewards.

Setup in a Harbor task

Put criteria alongside test.sh in the task's tests/ directory:

tests/
├── test.sh
├── checks.py         # programmatic criteria
└── judge.toml        # optional LLM/agent judge

tests/test.sh:

#!/bin/bash
uvx --from 'harbor-rewardkit==0.1.*' rewardkit /tests

This runs all criteria in /tests/ against the workspace at /app and writes /logs/verifier/reward.json. Defaults match Harbor's conventions — no extra config needed.

If judge criteria need API keys, pass them through task.toml:

[verifier.env]
ANTHROPIC_API_KEY = "${ANTHROPIC_API_KEY}"

Ask whether Reward Kit should run in the agent's shared environment or in a separate verifier environment. Prefer a separate verifier environment when judge prompts, grading dependencies, API keys, or clean-room checks should not be available to the agent:

[environment]
network_mode = "no-network"   # Agent env baseline — offline during agent.run()

[verifier]
environment_mode = "separate"

[verifier.environment]
network_mode = "public"     # Verifier env baseline — LLM judge API calls
docker_image = "python:3.12-slim"

In shared mode, the verifier runs in the agent container and inherits [environment].network_mode. Put [verifier].network_mode only when verify() needs different network access than the agent phase (a phase override, not a baseline). If agent and verifier need different baselines without runtime switching, use environment_mode = "separate" and set [verifier.environment].network_mode.

Judge criteria that call external APIs need a public baseline or allowlist on the verifier environment. Programmatic checks that only read local files can use no-network.

In separate mode, tests/ is the verifier image build context and must provide /tests/test.sh at runtime; Harbor does not upload tests/ into the running verifier container.

Read the full file on GitHub · 272 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. 11d ago First seen · 272 lines · 46 tokens per session scan A 4d2af48d018c

Subscribe to this mod's changes

rewardkit is a skill published in the GitHub repository pku-liang/hwe-bench (55 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 2,322 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to rewardkit, differing in 53 lines, and is treated as a copy.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens