agentmods.dev

Evaluating Agent Behavior

Evaluating Agent Behavior is a skill for Claude Code, Codex from build-with-dhiraj/ai-workflow-framework-portability-kit. It costs 28 tokens per session (239 once invoked), scanned A, original, MIT.

A process for testing an AI agent's behaviour, including which tools it chooses, whether it follows constraints, and whether it can be directed. These evaluations, often called evals, run checks against expected decisions or actions.

In plain words
What is it for?
Use it to set up behavioural tests, define expected tool calls or other markers, run the test suite, and inspect failures after prompt or tool changes.
Why use it?
It helps catch changes that make an agent choose the wrong tool, ignore instructions, or become harder to control, even when its final text looks acceptable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Gemini CLI.

not rated 5repo 16d ago A scan 28 tokens original MIT

Good fit Use it to set up behavioural tests, define expected tool calls or other markers, run the test suite, and inspect failures after prompt or tool changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/build-with-dhiraj/ai-workflow-framework-portability-kit/evaluating-agent-behavior
View source ↗ build-with-dhiraj/ai-workflow-framework-portability-kit
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 build-with-dhiraj/ai-workflow-framework-portability-kit --skill evaluating-agent-behavior
Clone the repo
git clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kit

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 Evaluating Agent Behavior

README.md
[![agentmods](https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/evaluating-agent-behavior/github.svg)](https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/evaluating-agent-behavior)
Your own site
<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/evaluating-agent-behavior"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/evaluating-agent-behavior/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 Evaluating Agent Behavior

Your own site · 80×15
<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/evaluating-agent-behavior"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/evaluating-agent-behavior.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 239 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 $0.00028 $0.00239
Opus 5.5 $0.00011 $0.00096
Sonnet 5.5 $0.00006 $0.00048
Haiku 4.5 $0.00003 $0.00024

Measured 1mo ago against content hash 6ee5766ab52a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Evaluating Agent Behavior 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 1mo 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.

Skills/evaluating-agent-behavior/SKILL.md · 25 lines

What it actually says

Evaluating Agent Behavior

Behavioral evaluations (evals) validate the agent's decision-making, such as tool choice and steerability.

Workflow Decision Tree

  1. Does it need validation?: If a prompt or tool change affects decision-making, it requires an eval.
  2. Choosing the Rig:
    • appEvalTest (AppRig): For UI-heavy or complex interactive flows.
    • evalTest (TestRig): For logic-focused behavior.
  3. Policy Setting:
    • USUALLY_PASSES: For new tests.
    • ALWAYS_PASSES: For established tests to lock in regressions.

Checklist

  • Setup Workspace: Initialize the test environment.
  • Write Assertions: Define the expected tool calls or behavioral markers.
  • Verify: Run the eval suite and analyze failures.

google-gemini/gemini-cli

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. 1mo ago First seen · 25 lines · 28 tokens per session scan A 6ee5766ab52a

Subscribe to this mod's changes

Evaluating Agent Behavior is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 16d ago), licensed MIT. It adds 28 tokens to every session and 239 once invoked, about $0.0001 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 2026-09-21.

Building agentsClaude CodeTestingai-agentsanthropicdeveloper-experiencellm-toolsportability
Related

Other skills, from other repositories

semgrep-rule-variant-creator

Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.

waybarrios/opencode-power-pack · 50 tokens

openspec-verify-change

Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.

ValorVie/custom-skills · 32 tokens

tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

ValorVie/custom-skills · 33 tokens

write-bdd

Convert plain English requirements into Gherkin BDD scenarios.

RealManage/dx-training · 15 tokens

javascript-testing-patterns

Implement comprehensive testing strategies using Jest, Vitest, and Testing Library for unit tests, integration tests, and end-to-end testing with mocking, fixtures, and test-driven development. Use when writing JavaScript/TypeScript tests, setting up test infrastructure, or implementing TDD/BDD workflows.

ValorVie/custom-skills · 63 tokens

systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

NousResearch/hermes-agent · 16 tokens