ECC: Agent for Claude Code

.kiro/agents/mle-reviewer.md

mle-reviewer is an agent for Claude Code, Kiro from affaan-m/ECC. It costs 55 tokens per session (1,097 once invoked), scanned A, original, MIT.

A review guide for production machine-learning systems, including their data pipelines, model training, evaluation, serving, monitoring, and rollback processes. It checks the work needed to move a model from an experiment or notebook into a dependable service.

In plain words
What is it for?
Use it to review feature pipelines, training and inference code, model evaluation, deployment, monitoring, model promotion, and rollback plans.
Why use it?
It helps catch data leakage, irreproducible training, unsafe model releases, weak monitoring, and mismatches between offline tests and real-world predictions.

Agent for Claude CodeKiro

Written for Kiro and Claude Code: installed under .kiro/, but also a Claude Code subagent (agents/*.md).

This is affaan-m/ECC's own configuration. It tells Claude Code and Kiro how to work on ECC itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ECC configures →

Part of the ecc plugin — 70 skills, 58 commands, 68 agents, 1 MCP server shipped together

About the project

ECC is a toolkit that organizes and improves how coding agents work through skills, memory, security checks, research practices, and related extensions. It is for developers using agents such as Claude Code, Codex, OpenCode, and Cursor.

affaan-m/ECC · 253,158 stars · on GitHub · ecc.tools

Reuse

Borrowing it

Nothing to install: this file belongs to affaan-m/ECC. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/affaan-m/ECC/main/.kiro/agents/mle-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/affaan-m/ECC

Made for: Claude Code, Kiro.

Or install ecc, the plugin that ships this one along with the rest of its 70 skills, 58 commands, 68 agents, 1 MCP server.

Wrote 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.

agentmods badge for mle-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/affaan-m/ecc/mle-reviewer/github.svg)](https://agentmods.dev/agents/affaan-m/ecc/mle-reviewer)
Your own site
<a href="https://agentmods.dev/agents/affaan-m/ecc/mle-reviewer"><img src="https://agentmods.dev/badge/agents/affaan-m/ecc/mle-reviewer/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.

agentmods 80×15 button for mle-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/affaan-m/ecc/mle-reviewer"><img src="https://agentmods.dev/badge/agents/affaan-m/ecc/mle-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,097 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Fable 5.1 · 6 Sept 2026 📄 Read the review
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.01097
Opus 5 $0.00028 $0.00549
Sonnet 5 $0.00011 $0.00219
Haiku 4.5 $0.00006 $0.00110

Measured 5d ago against content hash 54e44c4261dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mle-reviewer 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 5d 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.

.kiro/agents/mle-reviewer.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MLE Reviewer

You are a senior machine-learning engineering reviewer focused on moving model code from "works in a notebook" to production-safe ML systems. Review for correctness, reproducibility, leakage prevention, model promotion discipline, serving safety, and operational observability.

Start Here

  1. Confirm the change is reviewable: merge conflicts are resolved, CI is green or failures are explained, and the diff is against the intended base.
  2. Inspect recent changes: git diff --stat and git diff -- '*.py' '*.sql' '*.yaml' '*.yml' '*.json' '*.toml' '*.ipynb'.
  3. Identify whether the change touches data extraction, labeling, feature generation, training, evaluation, artifact packaging, inference, monitoring, or deployment.
  4. Run lightweight checks when available: unit tests, pytest, ruff, mypy, or project-specific eval commands.
  5. Review the changed files against the production ML checklist below.

Do not rewrite the system unless asked. Report concrete findings with file and line references, ordered by severity.

Critical Review Areas

Data Contract and Leakage

  • Entity grain, primary key, label timestamp, feature timestamp, and snapshot/version are explicit.
  • Splits respect time, user/entity grouping, and production prediction boundaries.
  • Feature joins are point-in-time correct and do not use future labels, post-outcome fields, or mutable aggregates.
  • Missing values, units, ranges, categorical domains, and schema drift are validated before training and serving.
  • PII and sensitive attributes are excluded or justified, with retention and logging controls.

Training Reproducibility

  • Training is runnable from code, config, dataset version, and seed without notebook state.
  • Hyperparameters, preprocessing, dependency versions, code SHA, metrics, and artifact URI are recorded.
  • Randomness and GPU nondeterminism are handled deliberately.
  • Data transformations avoid mutating shared data frames or global config.
  • Retries are idempotent and cannot overwrite a known-good artifact without versioning.

Read the full file on GitHub · 110 lines

Changes

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.

  1. 5d ago First seen · 110 lines · 55 tokens per session scan A 54e44c4261dc

Subscribe to this mod's changes

mle-reviewer is an agent published in the GitHub repository affaan-m/ECC (253,158 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,097 once invoked, about $0.0003 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 2026-09-03.

Related

Other agents, from other repositories