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 sota-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/sota-writer)<a href="https://agentmods.dev/skills/roomi-fields/paper-trail/sota-writer"><img src="https://agentmods.dev/badge/skills/roomi-fields/paper-trail/sota-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/sota-writer"><img src="https://agentmods.dev/badge/skills/roomi-fields/paper-trail/sota-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 | $0.00208 | $0.03406 |
| Opus 5 | $0.00104 | $0.01703 |
| Sonnet 5 | $0.00042 | $0.00681 |
| Haiku 4.5 | $0.00021 | $0.00341 |
Grade A, and why
sota-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 6d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill : SOTA Writer (research-first, anti-hallucination)
Why this skill exists
Citation hallucinations in academic writing are systemic when the author writes from memory and looks up sources afterward. They include inverted attributions ("X proved Y" when X proved ¬Y), fabricated quotes (text in quotation marks that doesn't appear in the cited source), wrong attributions (citing the wrong author for a known result), and confusion between similar-named papers (homonymy).
The plugin paper-trail exists because a retracted paper in 2026-02 contained 12 such errors, signaled by the misrepresented author themselves. This skill encodes the inverted workflow : research → read → write. Slower in appearance, faster in practice : no post-submission audit, no remediation, no reviewer embarrassment.
Scope
- Vault root :
$RESEARCH_VAULT_PATH(resolved via the adapter, default obsidian) - Registry :
$RESEARCH_REGISTRY_PATH/refs/*.md(one.mdfile per ref with YAML frontmatter) - SOTA output location : resolved via
adapter.sota_output_path(topic_slug)
The supreme rule
No claim in a SOTA without pointing to the notes body of a ref file
in state page1_validated (or higher). If I want to write X but no
source supports X → either I find one, or I don't write X. No
rhetorical rephrasing to "keep" an unsourced claim.
Mandatory 4-phase workflow
A. EXHAUSTIVE RESEARCH
├─ paper-search MCP (search_papers multi-source, 22 platforms)
├─ rtfm_search (optional — local indexed corpus if configured)
├─ NotebookLM (optional — books corpus if RESEARCH_ENABLE_NOTEBOOKLM=1)
├─ WebSearch (course pages, personal pages, archive.org)
└─ → N candidate refs in state `candidate` (file `.md` created for each)
B. ACQUISITION + PAGE 1 VALIDATION
├─ Delegate to pdf-cascade skill (paper-trail)
├─ 10-source cascade (up to 17 with browser + opt-in routes) + mandatory
│ page 1 anti-homonymy validation
└─ → refs in state `page1_validated` (physical PDF + validated)
C. READING / EXTRACTION
├─ For each ref in `page1_validated` : read abstract + relevant sections
├─ Notes written in the markdown body of the ref file (under frontmatter)
└─ → structured notes corpus (direct input for writing phase)
D. WRITING FROM NOTES ONLY
├─ Each citing sentence points to its ref file via wikilink
├─ Each cited ref transitions to `sota_cited_confirmed` as it's used
├─ If I want to write X and no note supports X :
│ either return to phase A (find a source that says X)
│ or don't write X
└─ → publishable SOTA (all citations in `sota_cited_confirmed`)
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.
- 6d ago Changed · +1 lines bf8c621c4b9d
- 10d ago First seen · 315 lines · 208 tokens per session scan A c4cb863f96e5
sota-writer is a skill published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 6d ago), licensed MIT. It adds 208 tokens to every session and 3,406 once invoked, about $0.0010 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.