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 agentmods add skills/graycodeai/starling/research-compilernpx skills add GrayCodeAI/starling --skill research-compilergit clone --depth 1 https://github.com/GrayCodeAI/starlingWhat 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 | $0.00046 | $0.03177 |
| Opus 5 | $0.00023 | $0.01588 |
| Sonnet 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 yesterday.
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.
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.
- yesterday 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 2d ago), licensed MIT. It adds 46 tokens to every session and 3,177 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…
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.
mb-ads
Create and review ads, and prepare provider-safe launch plans/checks. Flexible entry points: full pipeline (copy + images), copy only, images only, creative variations (hook library), video scripts, long-form video ads/VSL-style paid creative, video repurpose, compliance review, launch-plan, instrumentation, check, or…
mb-think
Combined research, decision, and codification workflow. Use when: (1) Exploring a question before committing (2) Making a decision that needs documentation (3) User says research, decide, figure out, explore, codify, enrich, retire stale source, sharpen this offer, improve the offer, add context, keyword gate, analyze…
mb-end
Session-closing skill that helps users wrap up intentionally. Use when: user says done, wrapping up, end my day, closing out, call it a day, goodnight, that's it for today, checkpoint, pause. Bookend to /mb-start. Scans git activity, surfaces what happened, spawns a crystallize agent for deep analysis, offers to save…
mb-organic
CREATE organic content scripts (Reels, TikTok, carousels, static posts) and repurpose sales videos/VSLs into short clips or creator-style excerpts. Use when user wants to GENERATE new scripts from concepts or make short clips from a sales video. NOT for research/mining competitor content - that's /mb-think. NOT for…