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/wenyuchiou/research-hub/paper-memory-buildernpx skills add WenyuChiou/research-hub --skill paper-memory-buildergit clone --depth 1 https://github.com/WenyuChiou/research-hubWhat 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 | $0.00122 | $0.01990 |
| Opus 5 | $0.00061 | $0.00995 |
| Sonnet 5 | $0.00024 | $0.00398 |
| Haiku 4.5 | $0.00012 | $0.00199 |
Grade A, and why
paper-memory-builder 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper-memory-builder
Bridge between research-hub and academic-writing-skills. Reads a
manuscript draft (Word, LaTeX, Markdown, Obsidian paper folder) plus the
figures it references, and writes structured .paper/claims.yml +
.paper/figures.yml so the writing skill can reason about the paper
without parsing the manuscript on every call.
This skill does not edit the manuscript itself. That's the writing skill's job. We just produce the memory layer it consumes.
When to use
Trigger phrases:
- "Build paper memory for this manuscript."
- "Extract claims, figures, and evidence from this paper folder."
- "Prepare reusable memory for writing and revision."
- "I'm starting a rebuttal — give me the claims layer first."
Not for:
- Writing the rebuttal itself —
academic-writing-skills. - Building the orientation memo —
research-project-orienter. - Comparing papers —
literature-triage-matrix. - Verifying a NotebookLM brief —
notebooklm-brief-verifier.
Inputs
In priority order:
.paper/existing files — ifclaims.ymlalready exists, parse it; this run should refresh, not replace human edits.- The manuscript file — usually one of:
paper/manuscript.docx/manuscript.tex/manuscript.md- Obsidian paper note under
raw/<paper-cluster>/manuscript.md - Word/LaTeX in a sibling repo specified by the user
- Figure files under
figures/oroutputs/figures/— read filenames + captions; don't OCR images. .research/project_manifest.yml— for project context (research question, datasets, current_stage). Use to anchor claims in the project's overall question..research/literature_matrix.md— for citation key lookup if the manuscript references "Smith 2024" but you need to disambiguate.
Scanning the paper repo for evidence artifacts (v0.3.16+)
Beyond the manuscript + figures, real research repos typically contain
sibling artifacts that populate claims[].evidence_artifacts for
non-figure evidence. When scanning, look for:
What ships with it
4 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.
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 · 177 lines · 122 tokens per session scan A 62fb06a3c19c
paper-memory-builder is a skill published in the GitHub repository WenyuChiou/research-hub (53 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 1,990 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 2026-08-30.
Other skills, from other repositories
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
architecture-design
Use only when creating new registrable ML components that require Factory or Registry patterns.
aaai-experiments
Use when designing or auditing AAAI experiments for the broad-AI program committee, including baselines, ablations, statistical significance, robustness, human evaluation, AI-for-Social-Impact and alignment/safety evidence, compute and cost reporting, and reproducibility-checklist alignment for Phase-1 survival.
acmmm-experiments
Use when designing or auditing the experiments of an ACM MM (ACM Multimedia) paper — matched baselines per modality, ablations that isolate the cross-modal fusion, user studies or QoE measurement where the claim is subjective, dataset and media licensing, and honest compute reporting, so evidence supports a multimedia…
ccs-writing-style
Use when revising an ACM CCS paper for a precise threat model, calibrated attack/defense claims, 12-page ACM sigconf compression, double-blind wording, adaptive-evaluation honesty, and the security house style that survives an adversarial SIGSAC program committee.