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 Rockielab/rockie-claude --skill papergit clone --depth 1 https://github.com/Rockielab/rockie-claudeWrote 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/rockielab/rockie-claude/paper)<a href="https://agentmods.dev/skills/rockielab/rockie-claude/paper"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/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/rockielab/rockie-claude/paper"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/paper.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 | $0.00189 | $0.02639 |
| Opus 5 | $0.00095 | $0.01319 |
| Sonnet 5 | $0.00038 | $0.00528 |
| Haiku 4.5 | $0.00019 | $0.00264 |
Grade A, and why
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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- paper — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper — submission-grade research writing for a Rockie lab
This skill turns a lab's evidence (experiment logs, result Notes, a corpus of
sources) into a paper that survives hostile review. It is agent-instruction
driven: you, the Rockie agent, follow this procedure and dispatch your own
fresh-context subagents for the review gauntlet and the detector gate. There is
no heavy runtime here. The single code artifact, templates/figure-gen.py.tmpl,
is a template a figure agent fills in and runs on Rockie compute — this skill
never executes it.
The method this skill reproduces is documented in references/method.md. It is
the same pipeline that produced a real ICML MI-workshop submission: a hard
styleguide, a five-stage adversarial gauntlet, and a detector loop that does not
stop until two consecutive rounds of fresh judges call the prose "100% human".
Do not invent a lighter method. The whole point is that ordinary LLM drafting
produces filler; this procedure filters it out.
Routing
Pick the entry point from the user's intent. The three are a pipeline but each runs independently — a user can lit-review without drafting, or publish a draft that was gauntleted in an earlier session.
| Entry point | Trigger intent | What it does | Reference |
|---|---|---|---|
/lit-review |
"lit review", "survey the literature on X", "what's the prior work" | Rank a candidate corpus; persist a human reading-list Note + a machine-readable index Note | references/lit-review.md |
/paper-draft |
"write the paper", "draft section N", "run the gauntlet", "review my draft" | Brief → page-budgeted outline → per-section drafts → gauntlet → detector gate → accept-ready draft | references/method.md, references/styleguide.md, references/adversarial-gauntlet.md, references/detector-gate.md |
/publish |
"publish", "submit to ", "export to GitHub/HF" | Assemble bundle → land as Note + downloadable artifact → optional GitHub/HF export → Rock-Collection stub | references/publish.md |
What ships with it
15 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.
- prompts/attack-agent.md 3.8 KB
- prompts/defense-agent.md 3.6 KB
- prompts/detector-judge.md 3.4 KB
- prompts/format-auditor.md 4.4 KB
- prompts/rebuttal-agent.md 4.1 KB
- prompts/style-judge.md 3.6 KB
- references/adversarial-gauntlet.md 5.8 KB
- references/detector-gate.md 7.4 KB
- references/lit-review.md 6.1 KB
- references/method.md 11 KB
- references/publish.md 9.9 KB
- references/styleguide.md 7.3 KB
- templates/brief.md 3.6 KB
- templates/figure-gen.py.tmpl 3.9 KB
- templates/outline.md 2.6 KB
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.
- 12d ago First seen · 171 lines · 189 tokens per session scan A 94e5e079ae16
paper is a skill published in the GitHub repository Rockielab/rockie-claude (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 189 tokens to every session and 2,639 once invoked, about $0.0009 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
auto-run
Autonomous personalized research loop. Use when the user wants to research a topic autonomously, run a research loop, start adaptive research, or use presets like technique-scout or cross-domain. Triggers on: 'auto run', 'research loop', 'autonomous research', 'run research', 'start research', 'adaptive research'.
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…
git-commit
A guided Git commit workflow that examines changes and creates a commit message using the Conventional Commits format, a shared style for labeling changes such as features, fixes, tests, or documentation.
pi-sync
Daily upstream-sync job for the pi Go port — fetch upstream pi, triage every change since the recorded pin, port what's in scope, verify idiomatic + parity via independent reviews, update the ledger, and push. Use for "sync with upstream", "porting job", or as the scheduled daily run.
pi-triage
Decide whether an upstream pi change needs porting to the Go port. Use when assessing upstream commits/PRs ("should we port X?"), or as the triage stage of /pi-sync. Outputs a WHY/WHAT/SCOPE verdict per change.
pi-parity-review
Adversarially verify that a ported change is faithful to the original pi implementation (TS source + published npm build). Use after porting upstream pi changes, or standalone on any area of this repo ("is X faithful to pi?").