A plan for testing an agent prompt, skill, plugin, or workflow. It defines expected behavior, test cases, scoring, and pass or fail rules.

Validating how an agent add-on behaves before or after changes, while recording what requires actual runtime testing.

It turns vague prompt testing into repeatable checks, including normal use, unusual inputs, security risks, and regressions.

eval-plan — Skill for Claude Code by cembasaranoglu

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 cembasaranoglu/crafting-system-claude --skill eval-plan

Clone the repo

git clone --depth 1 https://github.com/cembasaranoglu/crafting-system-claude

Made for: Claude Code.

Or install crafting-system, the plugin that ships this one along with the rest of its 81 skills, 32 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cembasaranoglu/crafting-system-claude/eval-plan.svg)](https://agentmods.dev/skills/cembasaranoglu/crafting-system-claude/eval-plan)

Your own site

<a href="https://agentmods.dev/skills/cembasaranoglu/crafting-system-claude/eval-plan"><img src="https://agentmods.dev/badge/skills/cembasaranoglu/crafting-system-claude/eval-plan.svg" alt="Measured on agentmods" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 196 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.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.00196
Opus 5	$0.00013	$0.00098
Sonnet 5	$0.00005	$0.00039
Haiku 4.5	$0.00003	$0.00020

Measured 7d ago against content hash dfa8b1f93448, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

eval-plan 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 7d 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.

cowork/skills/eval-plan/SKILL.md · 34 lines

What it actually says

Evaluation Plan

Create an eval plan for: $ARGUMENTS

Instructions

Define success criteria.
Create normal, edge, blocking-gap, high-risk, source-first, adversarial, and regression cases.
Define scoring dimensions.
Define pass/fail thresholds.
Identify what cannot be validated without runtime execution.

Output

eval_plan:
 target_name: ""
 target_type: "prompt | skill | plugin | subagent | mcp_workflow"
 success_criteria: []
 cases:
 - id: "CASE-001"
 category: "happy_path | edge | blocking_gap | high_risk | source_first | adversarial | regression"
 input: ""
 expected_behavior: ""
 scoring: []
 pass_thresholds: {}
 not_validated_here: []

Files

What ships with it

5 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.

7d ago First seen · 34 lines · 26 tokens per session scan A dfa8b1f93448

Subscribe to this mod's changes

eval-plan is a skill published in the GitHub repository cembasaranoglu/crafting-system-claude (5 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 196 once invoked, about $0.0001 per session on Opus 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 2026-08-31.

Building agents Testing

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

eval-plan