agentmods.dev

[object Object]

[object Object] is a skill for Claude Code, Codex from kngwyc3/Agent-Learning-Hub. It costs 8 tokens per session (316 once invoked), scanned A, original, MIT.

A workflow for testing and reviewing AI agents with task lists, execution traces, and pass-or-fail rules. It produces a report about correctness, tool use, speed, cost, and failure patterns.

In plain words
What is it for?
Building or running evaluation suites, collecting CSV and JSONL results, measuring success and tool usage, rendering reports, and classifying failures.
Why use it?
Agent behavior is difficult to judge from a single result, so repeatable tasks and recorded traces make regressions easier to find.

Skill for Claude CodeCodex

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

not rated 147repo +1 4mo ago A scan 8 tokens original MIT

Good fit Building or running evaluation suites, collecting CSV and JSONL results, measuring success and tool usage, rendering reports, and classifying failures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kngwyc3/agent-learning-hub/eval-skill
View source ↗ kngwyc3/Agent-Learning-Hub datawhalechina.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 kngwyc3/Agent-Learning-Hub --skill eval-skill
Clone the repo
git clone --depth 1 https://github.com/kngwyc3/Agent-Learning-Hub

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 [object Object]

README.md
[![agentmods](https://agentmods.dev/badge/skills/kngwyc3/agent-learning-hub/eval-skill/github.svg)](https://agentmods.dev/skills/kngwyc3/agent-learning-hub/eval-skill)
Your own site
<a href="https://agentmods.dev/skills/kngwyc3/agent-learning-hub/eval-skill"><img src="https://agentmods.dev/badge/skills/kngwyc3/agent-learning-hub/eval-skill/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 [object Object]

Your own site · 80×15
<a href="https://agentmods.dev/skills/kngwyc3/agent-learning-hub/eval-skill"><img src="https://agentmods.dev/badge/skills/kngwyc3/agent-learning-hub/eval-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 316 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 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 $0.00008 $0.00316
Opus 5.5 $0.00003 $0.00126
Sonnet 5.5 $0.00002 $0.00063
Haiku 4.5 $0.00001 $0.00032

Measured 2mo ago against content hash 1c96d66f9c78, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

[object Object] 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.

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.

stage-5/my-skill/templates/eval-skill/SKILL.md · 40 lines

What it actually says

Agent Eval Runner

Use this skill when designing, running, or reviewing agent evaluation suites with trace logs and pass/fail rules.

When To Use

  • The user asks to create eval tasks, run regression tests on an agent, or compare eval baselines.
  • Input includes task CSV, expected behaviors, must_have / must_not rules, or trace JSONL files.
  • Output should be a structured eval report with success rate and failure taxonomy.

When Not To Use

  • The user only wants unit tests for pure functions without agent behavior.
  • There is no eval harness, task list, or measurable acceptance criteria.

Steps

  1. Confirm eval dimensions: correctness, tool use, safety, latency, cost.
  2. Load or draft tasks with columns: id, input, expected_behavior, must_have, must_not, risk_level, judge.
  3. Run the eval runner and capture results CSV + trace JSONL.
  4. Render HTML report for human review.
  5. Classify failures using failure_taxonomy.md and propose fixes.

Output

  • Summary table: total, passed, success_rate, avg_tool_calls, avg_latency_ms.
  • Top failure types with example task IDs.
  • Action items tied to changed code or prompts.

Verification

  • Every failing task has a concrete note (missing / forbidden / permission).
  • Report paths exist: evals/results.csv, evals/report.html, traces/*.jsonl.
  • No fabricated pass rates — numbers must match the CSV.
Files

What ships with it

1 file 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 · 40 lines · 8 tokens per session scan A 1c96d66f9c78

Subscribe to this mod's changes

[object Object] is a skill published in the GitHub repository kngwyc3/Agent-Learning-Hub (147 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 316 once invoked, about $0.0000 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.

Building agentsTesting
Related

[object Object] compared with skills from other repositories

[object Object] next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
[object Object]kngwyc3/Agent-Learning-HubSkill1474mo agoMITA8Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code