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 zorost/AI-Engineering-Lab --skill eval-first-developmentgit clone --depth 1 https://github.com/zorost/AI-Engineering-LabWrote 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/zorost/ai-engineering-lab/eval-first-development)<a href="https://agentmods.dev/skills/zorost/ai-engineering-lab/eval-first-development"><img src="https://agentmods.dev/badge/skills/zorost/ai-engineering-lab/eval-first-development/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.
<a href="https://agentmods.dev/skills/zorost/ai-engineering-lab/eval-first-development"><img src="https://agentmods.dev/badge/skills/zorost/ai-engineering-lab/eval-first-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.01036 |
| Opus 5.5 | $0.00018 | $0.00414 |
| Sonnet 5.5 | $0.00009 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
eval-first-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 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval-First Development
1 · Purpose
Guarantee that every later change to a prompt, model, or pipeline is judged by a fixed measuring stick, so "better" is a number, not a feeling.
2 · When to use
- Before writing or optimizing any prompt, choosing any model, or tuning any retrieval pipeline whose output quality matters.
- When a team is debating two prompts/models with no score to cite.
Do not use for throwaway scripts and one-off data pulls. Use it the moment the output will be shown to anyone as "working".
3 · Inputs
- A spec with a metric and gate (
spec-first-ai-feature), or permission to define the metric here. - At least 20 real or realistic inputs. If fewer exist, generate the rest
synthetically and label them
synthetic: true.
4 · Procedure
- Create the golden-set file (e.g.
golden.jsonl): one JSON object per case withinput,expected, andtags(the failure classes you anticipate). Start with 20 cases; 50 is better. Include the hard cases you hope never occur. - Write the scorer as code, a function
score(output, expected) -> dictthat returns per-field or per-case results. Exact match where possible; rubric-graded LLM-as-judge only where correctness is fuzzy, and calibrate the judge against 10 human-graded cases before trusting it. - Add the score report: one line per case plus an aggregate, written to
evals/results/<timestamp>.json. A score you cannot diff is a story. - Run the scorer against the current system (or a trivial baseline) and record the baseline score in the spec file.
- Freeze the golden set. Changes to it are commits with a message, never silent edits, the measuring stick must not move while the system is being measured.
- Wire the scorer so one command runs it (script, make target, or notebook cell). If running the eval takes more than one command, it will not get run.
- Only now touch the thing being improved, prompt, model, chunking, tools. Every subsequent change reports: score before, score after, one-line reason.
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.
- 1mo ago First seen · 91 lines · 44 tokens per session scan A d5827d46f48d
eval-first-development is a skill published in the GitHub repository zorost/AI-Engineering-Lab (317 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,036 once invoked, about $0.0002 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.
Other skills, from other repositories
fine-tuning-os
Use this skill when conducting a professional LLM fine-tuning engagement in Zero-Data mode via the MCP server fine-tuning-os. Triggers on: prestation de fine-tuning LLM, livraison de modèle affiné, pipeline Zero-Data, orchestration des 64 outils fine-tuning-os, cycle de vie entraînement (préparation / données…
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-prompt-regression-testing
Use when comparing prompt changes against a fixed evaluation set: record actual model settings, required checks, missing results, judge limitations and case-level regression evidence.
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
tool-abuse-detection
Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.