Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jimezsa/opencolabnpx agentmods add skills/jimezsa/opencolab/fast-researchWrote 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/jimezsa/opencolab/fast-research)<a href="https://agentmods.dev/skills/jimezsa/opencolab/fast-research"><img src="https://agentmods.dev/badge/skills/jimezsa/opencolab/fast-research.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.03280 |
| Opus 5 | $0.00017 | $0.01640 |
| Sonnet 5 | $0.00007 | $0.00656 |
| Haiku 4.5 | $0.00003 | $0.00328 |
Grade B, and why
fast-research scanned grade B with 2 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 8d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
"script": "git clone https://github.com/jimezsa/papercli.git && cd papercli && make build && sudo install -m 0755 ./bin/papercli /usr/local/bin/papercli", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/jimezsa/papercli/main/SKILLS/fast-research/SKILL.md \ How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fast Research Skill
Use this skill for a rapid, evidence-grounded literature brief when the user needs quick scientific orientation without sacrificing traceability.
If the user later asks an exact follow-up question about one of the downloaded local papers, use pageindex-grounded for that bounded grounded retrieval step instead of treating this search workflow as the final QA layer.
Update This Skill
Only do this if the user explicitly asks to update this skill from the GitHub repo.
To refresh this skill directly from the GitHub repo:
curl -fsSL https://raw.githubusercontent.com/jimezsa/papercli/main/SKILLS/fast-research/SKILL.md \
-o SKILLS/fast-research/SKILL.md
Mission
Given a research question, use papercli to:
- Search relevant papers.
- Download a focused core set of PDFs.
- Read enough content to extract core ideas, concepts, and key equations.
- Produce a detailed
findings.mdreport inside the active research run folder, with inline references tied to exact papers. - Produce a companion literature-map block diagram that shows how the selected papers connect.
Prerequisites
papercliis installed and available inPATH.
Required Inputs
- Research question or hypothesis.
- Optional scope constraints: years, domain, must-include authors, method family.
If inputs are missing, infer a minimal scope and proceed.
Hard Requirements
- Always use
paperclifor retrieval (search,info,download). - Download and read papers, not just metadata.
- Every factual claim must be grounded by references.
- Include key math when present in papers.
- Final output must be a markdown file named
findings.mdinside the active research run folder. - Each distinct topic must live in its own dated, topic-slugged folder under
research/. - Maintain
research/INDEX.mdand the run-localRUN.mdmetadata file so later agents can recognize what each research folder contains. - After synthesis, produce a companion literature-map diagram through the shared
block-diagramskill. - The literature map must only show evidence-backed relations such as method lineage, direct comparison, shared benchmark or dataset, critique, or common problem framing.
- Do not invent paper-to-paper influence or citation edges that are not supported by the corpus.
- OpenColab normally provides
OPENCOLAB_PROGRESS_FILEduring provider runs. When it is set, emit bounded JSON progress updates for long-running stages instead of remaining silent until the end.
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.
- 8d ago First seen · 380 lines · 35 tokens per session scan B 38600a57b851
fast-research is a skill published in the GitHub repository jimezsa/opencolab (11 stars, last pushed 25d ago), licensed MIT. It adds 35 tokens to every session and 3,280 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
vs-search-tuning
Use when a user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.
vs-search
Search runtime and scene management: verify queries, inspect scenes, debug app readiness, and diagnose recall or scene-config issues.
bias-detection
Assess systematic biases in the evidence body — publication bias, reporting bias, and selective outcome reporting. Budget: 40 studies, 40 effect sizes, 40 web searches.
anomaly-characterization
SOP: Describe and classify anomalous phenomena that existing theory cannot explain.
assumption-audit
Surface all assumptions, classify by vulnerability (load-bearing × likely-false), validate causal logic. Focus on dangerous assumptions — high load-bearing + non-explicit.
ara-compile
SOP: Turn the feeding plan into the compiler's $ARGUMENTS and run the external ARA compiler once inline to produce ../ara/.