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.
npx skills add ARA-Labs/Agent-Native-Research-Artifact --skill submit-aragit clone --depth 1 https://github.com/ARA-Labs/Agent-Native-Research-ArtifactWrote 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/skills/ara-labs/agent-native-research-artifact/submit-ara)<a href="https://agentmods.dev/skills/ara-labs/agent-native-research-artifact/submit-ara"><img src="https://agentmods.dev/badge/skills/ara-labs/agent-native-research-artifact/submit-ara/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/skills/ara-labs/agent-native-research-artifact/submit-ara"><img src="https://agentmods.dev/badge/skills/ara-labs/agent-native-research-artifact/submit-ara.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 136 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00194 | $0.02543 |
| Opus 5 | $0.00097 | $0.01272 |
| Sonnet 5 | $0.00039 | $0.00509 |
| Haiku 4.5 | $0.00019 | $0.00254 |
Grade C, and why
submit-ara scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
directory, or the hosted mirror: `curl -fsSL https://www.agenticresearch.sh/s/submit-ara.py | python3 - <ara-dir>`. A re-run on the same directory updates it; the script prints the revision Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read, Write, Edit, Glob, Grep, Bash(gh *|git *|python3 *|curl *|cat *|ls *|find *|mkdir *|cp *|rm *|test *|basename *|jq *|open *) How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARA Submitter
You take a research directory and get it published, viewable, and updatable: validate (or
build) the ARA, guarantee it has a visualization, publish it, and hand back the link. You are a
first-class agent — use your native tools directly, and invoke the compiler /
research-visualizer skills when the steps below call for them.
What changed, and why it matters
A submission is not a one-shot event. The same artifact gets revised — a reviewer asks for
another ablation, a number changes the night before a deadline — and the failure this skill
exists to prevent is four near-identical entries on the Hub, none of them obviously the current
one. So every submission writes an .ara_env into the artifact directory, and every later
run reads it and updates the same artifact rather than creating a new one.
The other thing that changed: publishing no longer requires a GitHub account. A conference that accepts ARA as a submission format cannot ask its authors to be repo maintainers first. When the user has GitHub auth, GitHub stays the data layer and the Hub points at it; when they do not, the Hub stores the artifact itself. Both paths end at the same kind of Hub URL, and both are public on the Hub landing page. Say so before you upload, every time — an author who thought they were submitting privately has been badly served.
Set expectations FIRST
Before running any step, output the time notice — publishing is slow when it has to compile and/or visualize:
⏳ Publishing an ARA can take ~15 minutes. I may need to (1) compile your input into the ARA format, (2) generate the interactive visualization (figure rendering can be slow), and (3) upload it. The artifact will be publicly listed on the ARA Hub. I'll report progress at each step — please keep this session open.
Then announce each step as you start it (▶ Step 3/5: …).
Arguments
- First positional path → the ARA directory (or raw research input). Default: the ARA most
recently referenced in context, else the single dir under
./ara-output/, else ask. --title <t>→ artifact title. Default:PAPER.md's title.--hosted/--github→ force a route instead of auto-detecting (Step 4).--new→ submit as a separate artifact even though.ara_envexists. Rare; say why.--no-viz→ skip visualization (only if the dir already has one).--dry-run→ show what would be uploaded and stop.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 183 lines · 194 tokens per session scan C 1a866582fe44
submit-ara is a skill published in the GitHub repository ARA-Labs/Agent-Native-Research-Artifact (676 stars, last pushed 15d ago), licensed MIT. It adds 194 tokens to every session and 2,543 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…