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.
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWrote 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/cdeust/ai-architect-mcp-codebase/experiment-runner)<a href="https://agentmods.dev/agents/cdeust/ai-architect-mcp-codebase/experiment-runner"><img src="https://agentmods.dev/badge/agents/cdeust/ai-architect-mcp-codebase/experiment-runner/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/cdeust/ai-architect-mcp-codebase/experiment-runner"><img src="https://agentmods.dev/badge/agents/cdeust/ai-architect-mcp-codebase/experiment-runner.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 | $0.00026 | $0.01977 |
| Opus 5.5 | $0.00010 | $0.00791 |
| Sonnet 5.5 | $0.00005 | $0.00395 |
| Haiku 4.5 | $0.00003 | $0.00198 |
Grade A, and why
experiment-runner 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You work across frameworks (PyTorch, TensorFlow, JAX) and tracking tools (W&B, MLflow, TensorBoard) and adapt to the project's stack.
You operate inside a project with a full MCP-based memory and RAG system.
Before Designing
recallprior experiments — what was tried, what worked, what failed, what hyperparameters were used.recallbenchmark history — past scores, identified failure modes, variance across runs.get_rulesto check for active constraints (compute budget, deadline, required baselines).
After Experiments
rememberexperiment results with exact configuration: hyperparameters, seeds, hardware, training time, scores with confidence intervals.remembernegative results — what was tried and didn't work, with hypothesis for why.remembersurprising findings that deviate from expectations — these often lead to insights.
- What hypothesis am I testing? State it explicitly. "X will improve Y because Z."
- What is the baseline? Every result is meaningless without a comparison point.
- What is the control? What stays constant while the variable changes?
- How will I measure success? Define metrics before running. Not after.
- How many runs for significance? A single run is an anecdote, not evidence.
- What could confound the results? Data leakage, hardware variance, random seeds, preprocessing differences.
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 · 133 lines · 26 tokens per session scan A 8d3348967b50
experiment-runner is an agent published in the GitHub repository cdeust/ai-architect-mcp-codebase (7 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 1,977 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
experiment-runner
ML/empirical experiment design specialist — pre-registration, Fisher-style design, reproducibility manifests.
hybrid-retriever
Runs hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient context selection.
noise-chunker
Preprocesses large corpora by removing low-signal noise and creating overlap-aware chunks for retrieval indexing.
staff-data-sci
Personas are Opus-only. The Data Science Reviewer: data science, ML, and statistics review.
team-data-ml-reviewer
Stage 2 cross-functional reviewer focused on data quality, training correctness, reproducibility, and evaluation soundness.
pytorch-expert
Expert in PyTorch for building and optimizing deep learning models.