agentmods.dev

Forge: Agent for Claude Code

.claude/agents/ml-cv.md

ml-cv is an agent for Claude Code from lionshilov/Forge. It costs 49 tokens per session (390 once invoked), scanned A, original, MIT.

A machine-learning and computer-vision specialist for model development, training data, and real-time inference. Computer vision means software that works with images or video.

In plain words
What is it for?
It is for PyTorch or TensorFlow work, dataset preparation, embeddings, audio or vision pipelines, Core ML export, and reporting evaluation metrics.
Why use it?
It helps manage model quality, data privacy, reproducible training, and the limits of an inference interface.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; names the NotebookEdit tool.

This is lionshilov/Forge's own configuration. It tells Claude Code how to work on Forge 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 Forge configures →

not rated 5repo 1mo ago A scan 49 tokens original MIT
View source ↗ lionshilov/Forge
Reuse

Borrowing it

Nothing to install: this file belongs to lionshilov/Forge. 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/lionshilov/Forge/main/.claude/agents/ml-cv.md
Clone the repo
git clone --depth 1 https://github.com/lionshilov/Forge

Made for: Claude Code.

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 ml-cv

README.md
[![agentmods](https://agentmods.dev/badge/agents/lionshilov/forge/ml-cv/github.svg)](https://agentmods.dev/agents/lionshilov/forge/ml-cv)
Your own site
<a href="https://agentmods.dev/agents/lionshilov/forge/ml-cv"><img src="https://agentmods.dev/badge/agents/lionshilov/forge/ml-cv/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 ml-cv

Your own site · 80×15
<a href="https://agentmods.dev/agents/lionshilov/forge/ml-cv"><img src="https://agentmods.dev/badge/agents/lionshilov/forge/ml-cv.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 390 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.
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 $0.00049 $0.00390
Opus 5.5 $0.00020 $0.00156
Sonnet 5.5 $0.00010 $0.00078
Haiku 4.5 $0.00005 $0.00039

Measured today against content hash 2ae15b962438, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ml-cv 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.

.claude/agents/ml-cv.md · 31 lines

What it actually says

You are the ML/CV specialist in the Forge agent system.

Your full operating instructions

Before writing any code, read agents/ml-cv/CLAUDE.md in the project root — that is your complete prompt (responsibilities, rules, Before-Submitting checklist, anti-patterns). Treat it as authoritative.

Shared context you MUST read first

  1. project_context/PRODUCT.md
  2. project_context/ARCHITECTURE.md
  3. project_context/CONVENTIONS.md
  4. project_context/INTERFACES.md — how the model is called and by whom
  5. project_context/SECURITY.md — data handling, PII, model-input trust
  6. project_context/ANALYTICS.md — inference/model-quality events
  7. project_context/ERRORS_LOG.md

Invariants (never violate)

  • Every training run pinned: seed, versioned data, versioned code
  • No PII in training sets without explicit sign-off in SECURITY.md
  • Inference contract in INTERFACES.md — input/output shapes and latency budget are a commitment
  • Report honest eval metrics (held-out set), not train-set scores
  • Large weights / datasets do not live in git — use the storage noted in ARCHITECTURE.md

Reporting back

Return a compact summary: files/models changed, eval metrics with baseline, self-assessed confidence (1–5), known issues / TODOs. QA will review your output next.

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. today First seen · 31 lines · 49 tokens per session scan A 2ae15b962438

Subscribe to this mod's changes

ml-cv is an agent published in the GitHub repository lionshilov/Forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 390 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 2026-11-07.

Data and AILLMMulti-AgentScientificai-agentsanthropicclaude
Related

ml-cv compared with agents from other repositories

ml-cv next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ml-cvlionshilov/ForgeAgent51mo agoMITA49Claude Code
mle-revieweraffaan-m/ECCAgent299ktodayMITA55Claude Code, Kiro
rag-pipeline-revieweraffaan-m/ECCAgent299ktodayMITA58Claude Code
scg-mapperbearlike/AssistantAgent437d agoMITA48Claude Code
wiki-qa-probebearlike/AssistantAgent437d agoMITA43Claude Code
bioinformaticianK-Dense-AI/scientific-agentsAgent2391mo agoMITA74Claude Code
Specjalista od efektów specjalnychTheJacksonCode/Agent-ArchitectureAgent1101mo agoMITA82Claude Code