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.
npx skills add ishandutta2007/Awesome-Agent-Skills --skill eval-driven-developmentgit clone --depth 1 https://github.com/ishandutta2007/Awesome-Agent-SkillsWrote 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.
[](https://agentmods.dev/skills/ishandutta2007/awesome-agent-skills/eval-driven-development)<a href="https://agentmods.dev/skills/ishandutta2007/awesome-agent-skills/eval-driven-development"><img src="https://agentmods.dev/badge/skills/ishandutta2007/awesome-agent-skills/eval-driven-development.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00028 | $0.00402 |
| Opus 5 | $0.00014 | $0.00201 |
| Sonnet 5 | $0.00006 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
eval-driven-development 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 8d 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.
What it actually says
Eval-Driven Development
Overview
Eval-Driven Development ensures that AI features behave deterministically and predictably by testing them against a golden dataset using automated evaluators.
When to Use
- Building an AI-powered feature
- Tuning prompts or changing underlying models
- Implementing RAG pipelines
Process
- Curate Golden Dataset: Create diverse test cases including edge cases.
- Define Metrics: Choose appropriate evaluators (e.g., exact match, semantic similarity, LLM-as-a-judge).
- Run Pipeline: Execute the AI feature over the dataset and collect results.
- Analyze Failures: Inspect low-scoring examples and update prompts or logic.
- Establish Baseline: Set a minimum threshold for CI/CD checks.
Common Rationalizations
| Rationalization | Why It Is Wrong |
|---|---|
| "Manual spot checks are enough." | Spot checks miss regressions across prompts, model versions, and edge cases. |
| "We can add evals after launch." | Without a baseline, you cannot tell whether a later prompt or model change improved behavior. |
| "The judge model says it is good." | LLM judges need criteria, calibration examples, and failure review before they are trustworthy. |
Red Flags
- No golden dataset exists
- Metrics are vague or not tied to user-visible quality
- Low-scoring examples are ignored instead of inspected
- The baseline threshold is chosen after seeing the desired result
Verification
Before finishing, confirm:
- The golden dataset includes normal, edge, and known-failure cases
- Metrics and evaluator prompts are committed or otherwise reproducible
- The current model/prompt has a recorded baseline
- Failure examples have been reviewed and categorized
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.
- 8d ago First seen · 46 lines · 28 tokens per session scan A 6e86feb37e2d
eval-driven-development is a skill published in the GitHub repository ishandutta2007/Awesome-Agent-Skills (21 stars, last pushed 29d ago), licensed MIT. It adds 28 tokens to every session and 402 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 2026-08-30.
Other skills, from other repositories
llm-testing
Use this skill when you need to test LLM behavior, failure modes, and evidence-based quality boundaries; triggers include llm testing.
prompt-testing
Use this skill when you need to test prompt behavior, regression risk, and output boundaries across versions; triggers include prompt testing.
bailian-train-deploy
A workflow for using Alibaba Cloud’s Bailian command-line tool to fine-tune or directly deploy AI models as callable services. It covers text, speech-synthesis, image-generation, and video-generation models.
happyhorse-prompt-studio
Interactive prompt studio for HappyHorse 1.0 video generation. Guides users through scenario discovery with vivid examples, then assembles production-ready prompts in JP/CN/EN. Use when someone wants to create AI video content with HappyHorse but doesn't know where to start, or when they have a specific scenario and…
autoresearch
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill…
hunt-race-condition
Hunting skill for race condition vulnerabilities. Built from 3 public bug bounty reports. Use when hunting race condition on any target.