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 RBraga01/builder-ai --skill eval-before-shipgit clone --depth 1 https://github.com/RBraga01/builder-aiWrote 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/rbraga01/builder-ai/eval-before-ship)<a href="https://agentmods.dev/skills/rbraga01/builder-ai/eval-before-ship"><img src="https://agentmods.dev/badge/skills/rbraga01/builder-ai/eval-before-ship.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 | $0.00046 | $0.01357 |
| Opus 5 | $0.00023 | $0.00678 |
| Sonnet 5 | $0.00009 | $0.00271 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
eval-before-ship 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 6d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval Before Ship
The Law
AN LLM FEATURE IS NOT READY UNTIL NUMBERS EXIST.
"It looked good when I tested it" is not an eval.
"I ran a few examples and it worked" is not an eval.
A named suite, a defined metric, a pass rate, a failure analysis,
and a baseline comparison IS an eval. All five. Not four.
When to Use
Trigger before any of these:
- Merging a PR that adds or modifies a prompt
- Deploying an LLM feature to any environment users can reach
- Switching models or providers on an existing feature
- Changing retrieval logic, rerankers, or chunk strategy in a RAG pipeline
- Updating few-shot examples or system prompt structure
When NOT to Use
- Exploratory prototypes that will not reach users (note it: "eval required before production")
- Config-only changes that cannot affect model output (timeouts, logging, env vars)
What Counts as an Eval
An eval must have all five components:
| Component | What It Means | What Does NOT Count |
|---|---|---|
| Named test suite | File with labelled examples in evals/ |
"I tested it manually" |
| Defined metric | Accuracy %, faithfulness score, task pass rate | "It seemed accurate" |
| Pass threshold | Explicit minimum (e.g., ≥ 85%) | No threshold = no standard |
| Failure analysis | ≥ 5 failures examined and categorised | "There were a few errors" |
| Baseline comparison | This version vs. previous version or control | First release exempt; all subsequent require it |
The Process
Step 1 — Define the Eval Before Writing the Prompt
Answer these before touching the prompt:
- What does a correct output look like for this task?
- What metric will you use to measure it?
- What is the minimum acceptable score for production?
If you cannot answer these before building, the task is not well enough specified to build.
Step 2 — Build a Representative Test Set
evals/
<feature-name>/
test-set.jsonl ← labelled examples, one JSON object per line
harness.py ← eval runner
results-<date>.md ← documented results
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.
- 6d ago First seen · 141 lines · 46 tokens per session scan A 7e1f6ffe5219
eval-before-ship is a skill published in the GitHub repository RBraga01/builder-ai (2 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,357 once invoked, about $0.0002 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.
Other skills, from other repositories
recipe-eval-prompt
Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.
llm-evaluation
LLM evaluation — automated metrics, human feedback, benchmarking. Use when testing performance, measuring AI quality, or establishing evaluation frameworks.
fetch-llm-papers
Workflow for updating the LLM landscape paper pool (section/xllmpapers.md) using fetchllmpapers.py. Covers full re-fetch, resume from checkpoint, and adding new topics. USE FOR: Refreshing citation counts, expanding topic coverage. DO NOT USE FOR: Adding hand-curated entries to section files (use…
eval-harness
Professional Eval Harness Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
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
6 production-ready 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.