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 research-foresightgit 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/research-foresight)<a href="https://agentmods.dev/skills/ara-labs/agent-native-research-artifact/research-foresight"><img src="https://agentmods.dev/badge/skills/ara-labs/agent-native-research-artifact/research-foresight/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/research-foresight"><img src="https://agentmods.dev/badge/skills/ara-labs/agent-native-research-artifact/research-foresight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00211 | $0.00645 |
| Opus 5 | $0.00105 | $0.00322 |
| Sonnet 5 | $0.00042 | $0.00129 |
| Haiku 4.5 | $0.00021 | $0.00064 |
Grade A, and why
research-foresight 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 11d 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.
What it actually says
research-foresight — the ARA World Model
You (the coding agent) are the LLM that runs the engine — no SDK, no API key, no network call. The
engine is three reference contracts under this skill's references/ directory (quote every path;
it may contain spaces):
references/CONTRACT.md— the foundation both contracts bind to; if documents disagree, it wins.references/RETRIEVE.md— the Retriever: agentic search + semantic rank over the ARA's native files.references/PREDICT.md— the Predictor: grounded, honest answering of the question asked.
Inputs
From the user's message (or $ARGUMENTS): an <ara_dir> (the ARA in scope) and a free-text
query. If <ara_dir> turns out not to be an ARA (a plain paper, repo, or notes folder),
compile it into one first with /compiler <path>, then rerun this skill.
Procedure
- Retrieve — adopt
references/RETRIEVE.md. Read it now and follow it exactly against<ara_dir>. - Answer — adopt
references/PREDICT.md. Read it now and follow it exactly, consuming the retrieval from Step 1.
Render the answer prominently, then the honesty envelope (grounded_inference /
speculative_leap / basis / reasoning / confidence / confidence_reason / falsifiable).
The engine is read-only: read nothing outside <ara_dir> and this skill's references/; write
nothing anywhere.
What ships with it
3 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.
- 11d ago First seen · 50 lines · 211 tokens per session scan A 393195faf08f
research-foresight is a skill published in the GitHub repository ARA-Labs/Agent-Native-Research-Artifact (678 stars, last pushed 16d ago), licensed MIT. It adds 211 tokens to every session and 645 once invoked, about $0.0011 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.
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…