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 roomi-fields/paper-trail --skill paper-writergit clone --depth 1 https://github.com/roomi-fields/paper-trailWrote 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/roomi-fields/paper-trail/paper-writer)<a href="https://agentmods.dev/skills/roomi-fields/paper-trail/paper-writer"><img src="https://agentmods.dev/badge/skills/roomi-fields/paper-trail/paper-writer/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/roomi-fields/paper-trail/paper-writer"><img src="https://agentmods.dev/badge/skills/roomi-fields/paper-trail/paper-writer.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 | $0.00115 | $0.01690 |
| Opus 5 | $0.00057 | $0.00845 |
| Sonnet 5 | $0.00023 | $0.00338 |
| Haiku 4.5 | $0.00012 | $0.00169 |
Grade A, and why
paper-writer 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 9d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill : Paper Writer
Role
Write research articles in IMRaD structure (Introduction, Methods, Results, and Discussion) for conferences and journals, with every citation rigorously verified against the actual source.
Workflow
Like sota-writer, this skill enforces an inverted workflow :
sources are built / verified before writing, not after. The
difference with sota-writer is that paper-writer assumes the SOTA
corpus already exists in the registry (it consumes audited SOTAs to
build the Related Work section) and focuses on producing the IMRaD
sections + their citations.
A. SOTA CONSUMPTION
├─ Identify the SOTAs in the vault relevant to the paper's topic
├─ Verify they're audited (no ref in candidate / blocked_human)
└─ → corpus of refs in `sota_cited_confirmed` available
B. STRUCTURE
├─ Choose target venue (ISMIR, SMC, NeurIPS, ACL, etc.)
├─ Adapt IMRaD to venue conventions (page limit, abstract length)
└─ Outline each section with bullet points
C. WRITE PER SECTION
├─ Methods & Results : new content from the user's research
├─ Related Work : draw from audited SOTAs, no new claims
├─ Each citation passes citation-receipts protocol
└─ → draft with placeholder citations (e.g., \cite{author2020topic})
D. PRE-SUBMISSION AUDIT
├─ /paper-trail:audit-article <paper.tex> [--warn]
├─ Fix all INVALID and ADJUST citations
├─ Decide on UNVERIFIABLE (enable shadow libs or remove claim)
└─ → submittable draft
Standard IMRaD structure
- Abstract — 150–250 words
- Introduction — context, problem, contribution
- Related Work — based on existing SOTAs in the registry
- Methods — formalism, algorithms, model
- Results — experiments, evaluations
- Discussion — interpretation, limitations
- Conclusion — summary of contributions, future work
- References — BibTeX
Venue adaptation
Common venue conventions to respect :
| Venue | Pages | Template | Notes |
|---|---|---|---|
| ISMIR | 6 | ISMIR LaTeX | Music information retrieval |
| SMC | 8 | SMC template | Sound and music computing |
| NeurIPS | 8 + appendix | NeurIPS LaTeX | Machine learning |
| ACL | 8 | ACL LaTeX | Computational linguistics |
| ICASSP | 4–5 | ICASSP LaTeX | Signal processing |
| Generic journal | varies | Journal-specific | Refer to author guide |
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.
- 9d ago First seen · 186 lines · 115 tokens per session scan A 385f38bf1f8d
paper-writer is a skill published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 5d ago), licensed MIT. It adds 115 tokens to every session and 1,690 once invoked, about $0.0006 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
draft
Use to produce a first draft, or to revise one from an upstream verdict artifact's open-defect count, emitting a draft@1 artifact. The target node of a bounded back-edge. Single tool. Reusable standalone.
qiongli
Qiongli version: v1.17.0. Cross-platform academic research workflow for Codex, Claude / Claude Code, and CLI. Use for academic research lifecycle work: paper planning, literature review, paper reading, gap finding, study design, manuscript writing, statistics, analysis code, reproducibility, proofread, rebuttal…
x-bug2rag
A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.
x-cr
A software-correctness investigation skill for finding why code behaves differently from what was expected. It uses evidence from code paths, specifications, tests, logs, and changes to assess possible causes.
x-spec2
A compact system-design guide for turning vague or cross-module requests into a small, structured specification package. It defines requirements, acceptance scenarios, module boundaries, and—when needed—data flow, state, timing, resources, or recovery design.
x-adversarial-risk
A focused adversarial review of a software specification. It tries to find small counterexamples that would expose incorrect implementations, such as invalid state changes, crashes, duplicate actions, permission mistakes, or concurrent events.