What is real-components?

A rule for checking that a pipeline stage really runs the component it claims to run. A pipeline is a sequence of processing steps, while a stub is a placeholder that produces no real component output.

Use it when authoring or reviewing pipelines that advertise tools such as Cosmos, FiftyOne, or visual-language-model evaluation, and verify their outputs during live runs.

It prevents a pipeline from appearing successful while only writing a manifest or echoing text instead of creating the promised video, frames, report, or other result.

real-components — Skill for Claude Code and Codex by nebius

Install

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.

Any agent

npx skills add nebius/nebius-physical-ai --skill real-components

Clone the repo

git clone --depth 1 https://github.com/nebius/nebius-physical-ai

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/real-components/github.svg)](https://agentmods.dev/skills/nebius/nebius-physical-ai/real-components)

Your own site

<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/real-components"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/real-components/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/real-components"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/real-components.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,210 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.01210
Opus 5	$0.00034	$0.00605
Sonnet 5	$0.00013	$0.00242
Haiku 4.5	$0.00007	$0.00121

Measured 9d ago against content hash ebe373aa7aaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

real-components 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 9d 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.

skills/atomic/real-components/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Real Components As Advertised

A pipeline that advertises a component (e.g. "Cosmos Transfer 2.5", "FiftyOne curation") MUST actually run it. A stub that only echos or writes a contract_ready manifest while the spec advertises real output is a correctness bug: it looks green in validate/plan/smoke but produces no real artifacts, and downstream stages that consume them fail (or silently pass on fake data).

Rule

Every advertised stage invokes the real component and writes real artifacts.
A stage may be a stub ONLY if the spec description says so explicitly; never advertise a stub as the real capability.
Verify on a live run that each stage's output artifact is real (a real video/frames/report), not a manifest or an echoed string.

Audit method

For each toolRef, inspect its argv in npa/src/npa/orchestration/npa_workflow/catalog.py:

argv[0] == "echo" → stub (e.g. workbench.fiftyone.launch_app).
a Python one-liner that writes "status": "contract_ready" or a fixed write_decision → stub / demo (e.g. workbench.sim2real.write_decision).
invokes a real CLI (npa workbench <tool> ... with real flags) or a real module function → real.

Known stub toolRefs (do NOT advertise as real output):

Stub	Real replacement
`workbench.fiftyone.launch_app` (echo)	real `npa workbench fiftyone load-dataset`, or a real `run.shell` curation function
`workbench.sim2real.write_decision` (demo)	real `run.shell` module decision function for the advertised pipeline

run.shell stages count as real when they invoke a real npa workbench ... command or import a real, tested module (e.g. npa.workflows.data_factory_stages, npa.workflows.data_factory_viz). Put the logic in a tested module, not inline.

workbench.cosmos2.transfer_execute is the real Config-Gen-aware execution toolRef used by the Data Factory and the standalone procedural-input smoke. workbench.cosmos2.transfer_conditioned_execute is the real input-conditioned execution toolRef for workflows that do not carry a Config-Gen manifest. Both include --execute and --condition-on-input, so a missing runtime or input video fails closed. The direct workbench.cosmos2.transfer / npa workbench cosmos2 transfer surface retains reference/local augmentation behavior and must not be used by an advertised real Cosmos stage.

Read the full file on GitHub · 96 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.

9d ago First seen · 96 lines · 67 tokens per session scan A ebe373aa7aaf

Subscribe to this mod's changes

real-components is a skill published in the GitHub repository nebius/nebius-physical-ai (27 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 1,210 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 2026-08-30.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

real-components