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 airas-org/airas --skill preregister-papergit clone --depth 1 https://github.com/airas-org/airasWrote 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/airas-org/airas/preregister-paper)<a href="https://agentmods.dev/skills/airas-org/airas/preregister-paper"><img src="https://agentmods.dev/badge/skills/airas-org/airas/preregister-paper/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/airas-org/airas/preregister-paper"><img src="https://agentmods.dev/badge/skills/airas-org/airas/preregister-paper.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 | $0.00121 | $0.03336 |
| Opus 5.5 | $0.00048 | $0.01334 |
| Sonnet 5.5 | $0.00024 | $0.00667 |
| Haiku 4.5 | $0.00012 | $0.00334 |
Grade A, and why
preregister-paper 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preregister the paper
You write the paper before the pilot and full runs, from the hypothesis and experimental design. The experiment code and its platform sanity run come first, so the freeze commit contains the code the design was written against; sanity outputs are never imported and are not evidence. The commit that adds this paper is the preregistration record: every claim, criterion and expected result is frozen in git history before any result exists, so nothing can be quietly rewritten to fit the data later. Pilot and full runs are expected to descend from this commit.
main.tex lives in .research/latex/{template}/, where {template} is
one of the bundled template directories (iclr2024, mdpi,
agents4science_2025) — the name the verification tools address the
paper by. The directory is only a slot: use the bundled style or your
own preamble, keeping the usual structure (title, abstract, numbered
sections, figures, bibliography). Write in the user's working
language; a CJK paper needs a LuaTeX preamble (luatexja-fontspec —
pdflatex silently drops non-Latin text from the PDF), and with the mdpi
class also \RequirePackage{luatex85} before \documentclass (drop its
pdftex option), since the class uses pdfTeX primitives LuaTeX no longer
has. This skill only changes when the paper is written and how Results
are stated.
Preconditions
- A local clone of the experiment repository.
- Hypothesis and experimental design exist as
.research/design.json— the exactliteratureandhypothesesarguments ofpreregister_record, committed byhypothesize-and-design— or are supplied by the user. The design must fix the run ids (e.g.proposed,baseline) and the metrics; if it does not, settle those with the user first, because the placeholders below are named after them. - The papers the hypothesis rests on, each by the id of the
.research/sources/<id>/CI fetched it into, and the passages (page and verbatim quote) picked while reading. Nothing is in the record yet. - The experiment code is committed and one platform sanity run passed
(
write-experiment-code): everything that run read and called is covered by the design'sparams. - No pilot or full run has executed. Only sanity runs precede the freeze; pilot and full runs come after it.
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.
- 22d ago Changed · -1 lines 21fa0befd63a
- 23d ago Changed · -1 lines a2a93092f1a2
- 1mo ago Changed · +10 lines 6b23cd197fcc
- 1mo ago Changed · +19 lines · +4 tokens per session bcb5e368b1f6
- 1mo ago Changed · +1 lines b9f78f248c57
- 1mo ago Changed · -37 lines 372f93298097
- 1mo ago Changed · +26 lines 601f1adb18a0
- 1mo ago Changed · +9 lines db9566f3ccc4
- 1mo ago Changed · +7 lines e12ab6074154
- 1mo ago First seen · 208 lines · 117 tokens per session scan A 57d487ab183a
preregister-paper is a skill published in the GitHub repository airas-org/airas (39 stars, last pushed 21d ago), licensed MIT. It adds 121 tokens to every session and 3,336 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-04.
preregister-paper compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| preregister-paperairas-org/airas | Skill | 39 | 21d ago | MIT | A | 121 | Claude Code |
| research-prooftonyblu331/research-proof | Skill | 52 | 5mo ago | MIT | A | 101 | Claude Code |
| proof-checkerwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 87 | Claude Code |
| auto-paper-improvement-loopwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 67 | Claude Code |
| paper-writewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 50 | Claude Code |
| research-litwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 48 | Claude Code |
| paper-illustrationwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 67 | Claude Code |