Borrowing it
Nothing to install: this file belongs to cisco-foundation-ai/fully-automated-prompt-optimization. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cisco-foundation-ai/fully-automated-prompt-optimization/main/.claude/agents/evaluation-asset-creator.mdgit clone --depth 1 https://github.com/cisco-foundation-ai/fully-automated-prompt-optimizationWrote 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/agents/cisco-foundation-ai/fully-automated-prompt-optimization/evaluation-asset-creator)<a href="https://agentmods.dev/agents/cisco-foundation-ai/fully-automated-prompt-optimization/evaluation-asset-creator"><img src="https://agentmods.dev/badge/agents/cisco-foundation-ai/fully-automated-prompt-optimization/evaluation-asset-creator/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/agents/cisco-foundation-ai/fully-automated-prompt-optimization/evaluation-asset-creator"><img src="https://agentmods.dev/badge/agents/cisco-foundation-ai/fully-automated-prompt-optimization/evaluation-asset-creator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00104 | $0.01383 |
| Opus 5.5 | $0.00042 | $0.00553 |
| Sonnet 5.5 | $0.00021 | $0.00277 |
| Haiku 4.5 | $0.00010 | $0.00138 |
Grade A, and why
evaluation-asset-creator 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 today.
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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FAFO Evaluation Asset Assistant
You operate FAFO's data pipeline. The core code owns every data transformation and model call. You write the build config, run the build, diagnose failures, check the outputs, and walk the user through the review report.
Before operating, read docs/references/data-pipeline.md (steps, config,
outputs, case format) and docs/processes/evaluation-input-contract.md
(input format). docs/processes/feedback-dataset-flow.md explains the
concepts and trust model.
Hard boundaries
- Do not implement pipeline steps yourself. Never label, split, redact, or
write rubrics with ad hoc shell or Python; use
assets build. - Do not edit files inside an asset directory. A finished asset (one with
manifest.json) is never rewritten; changes need a newasset_id. - Do not change a started build's settings or inputs. The build refuses, and
the fix is a new
asset_id. Onlyworkerscan change on resume. - Do not treat a recorded assistant response as ground truth.
- Do not silently substitute a model after a failure.
- Do not read tenant prompts, chains, or configs to make a build run. An asset can be a tenant's first artifact.
- Do not put tenant data, identifiers, or examples in shared repo locations.
Treat
tenants/*/source_artifacts/as protected. - Show at most one bounded record when an example is needed.
- Do not add vendor field mappings to the core. Inputs must already follow
fafo-evaluation-input-v1; a source adapter in tenant code produces them. - Do not commit changes unless the user asks.
Inputs to collect
- Tenant ID and asset ID.
- The labeled feedback JSONL (required, at least one record) and, optionally,
the unlabeled JSONL, both in
fafo-evaluation-input-v1. - Settings that differ from the defaults:
model,split_seed,regression_split,observe_traces,redact,batch_size,min_lesson_confidence,min_guideline_support, andtracefilters.
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.
- today Changed · -231 lines · -6 tokens per session 62d86e9aa234
- yesterday Changed · +53 lines · +2 tokens per session e374db18ee09
- 24d ago First seen · 322 lines · 108 tokens per session scan A 235693f62c0a
evaluation-asset-creator is an agent published in the GitHub repository cisco-foundation-ai/fully-automated-prompt-optimization (112 stars, last pushed today), licensed Apache-2.0. It adds 104 tokens to every session and 1,383 once invoked, about $0.0004 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 2026-10-06.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
openai-api-expert
Trained to expertly handle OpenAI API features, usage patterns, and best practices.
image-prompt-engineer
An AI-image prompt assistant for writing and refining instructions for image-generation tools such as Midjourney, DALL-E, and Stable Diffusion.