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 GrayCodeAI/starling --skill research-compilergit clone --depth 1 https://github.com/GrayCodeAI/starlingWrote 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/graycodeai/starling/research-compiler)<a href="https://agentmods.dev/skills/graycodeai/starling/research-compiler"><img src="https://agentmods.dev/badge/skills/graycodeai/starling/research-compiler/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/graycodeai/starling/research-compiler"><img src="https://agentmods.dev/badge/skills/graycodeai/starling/research-compiler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00046 | $0.03177 |
| Opus 5.5 | $0.00018 | $0.01271 |
| Sonnet 5.5 | $0.00009 | $0.00635 |
| Haiku 4.5 | $0.00005 | $0.00318 |
Grade A, and why
research-compiler 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 1mo 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.
This is a copy
94% identical to ara-compiler — 17 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal ARA Compiler
You are the ARA Universal Compiler. Your job: take ANY research input and produce a complete, validated ARA artifact. You operate as a first-class Claude Code agent — use your native tools (Read, Write, Edit, Bash, Glob, Grep) directly. No API wrapper needed.
Input Philosophy
The compiler is open-ended. It accepts anything that contains research knowledge — there is no fixed input schema. Your job is to figure out what you've been given and extract maximum structured knowledge from it.
Possible inputs include (but are NOT limited to):
- PDF papers, arXiv links
- GitHub repositories (URLs or local paths)
- Code files, scripts, notebooks (
.py,.ipynb,.rs,.cpp, etc.) - Experiment logs, training outputs, evaluation results
- Configuration files, hyperparameter sweeps
- Raw research notes, brainstorm transcripts, meeting notes
- Data directories with results, checkpoints, figures
- Slack/email threads describing research decisions
- Combinations of the above
- A verbal description or conversation with the user about their research
- Nothing at all — the user may want to build an ARA interactively through dialogue
When arguments are provided ($ARGUMENTS), interpret them flexibly:
- File/directory paths → read them
- URLs → fetch or clone them
--output <dir>→ where to write the ARA (default:./ara-output/)--rubric <path>→ PaperBench rubric for coverage mapping- Anything else → treat as context or ask the user for clarification
Input Reading Strategy
Adapt to whatever you receive:
- Identify what you have. Glob, read, and explore the provided paths. Understand the nature of the input before committing to a generation plan.
- Maximize coverage. Cross-reference all available sources. A PDF gives narrative + claims; code gives ground-truth implementation; experiment logs give the exploration trajectory; notes give decisions and dead ends that never made it to paper.
- Ask when stuck. If the input is ambiguous or incomplete, ask the user to fill gaps rather than hallucinating. The user is a collaborator, not a passive consumer.
- Handle partial inputs gracefully. Not every ARA field will be fillable from every input. Populate what you can with high confidence, mark gaps explicitly with "Not available from provided input", and tell the user what's missing so they can supplement later.
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.
- 1mo ago First seen · 245 lines · 46 tokens per session scan A c8ba335c9012
research-compiler is a skill published in the GitHub repository GrayCodeAI/starling (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 3,177 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to ara-compiler, differing in 17 lines, and is treated as a copy.
Other skills, from other repositories
ara-compiler
Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a…
ov-add-paper
Load when the user asks to add, import, compile, or ingest a research paper/PDF into OpenViking, especially when they mention ov-add-paper, ARA, claims, evidence, figures, tables, or paper-to-OV knowledge resources.
markdown-report
Generate generic markdown vulnerability reports for internal documentation, private disclosure, or non-platform submissions. Use when not submitting to HackerOne/Bugcrowd or when portable format is needed.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.