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/pageindex-groundedWrote 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/pageindex-grounded)<a href="https://agentmods.dev/skills/jimezsa/opencolab/pageindex-grounded"><img src="https://agentmods.dev/badge/skills/jimezsa/opencolab/pageindex-grounded/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/jimezsa/opencolab/pageindex-grounded"><img src="https://agentmods.dev/badge/skills/jimezsa/opencolab/pageindex-grounded.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 | $0.00045 | $0.02162 |
| Opus 5 | $0.00023 | $0.01081 |
| Sonnet 5 | $0.00009 | $0.00432 |
| Haiku 4.5 | $0.00005 | $0.00216 |
Grade A, and why
pageindex-grounded 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.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PageIndex Grounded Skill
Use this skill when the user needs precise, grounded follow-up answers from papers that already exist locally under the current project.
Typical use cases:
- exact claim verification from one downloaded paper
- "where does this paper say X?" questions
- page-level follow-up after
fast-research,pro-research, ordeep-research - bounded cross-paper comparison across a small local paper set
- checking whether a prior synthesis overclaimed or missed a qualification
Do not use this skill for paper discovery. Use fast-research, pro-research, or deep-research first when the papers are not already local.
Do not use this skill as a replacement for paper-summary. paper-summary remains the canonical per-paper summary workflow.
When the user wants the figure image itself instead of only a grounded answer, hand off to the shared pdf-figure-extract skill after you identify the likely paper and page range.
Mission
Given a precise question over already-downloaded local papers:
- Select a bounded local paper set that is likely to contain the answer.
- Generate or reuse cached PageIndex tree artifacts for those papers.
- Use the tree structure to retrieve the most relevant sections.
- Verify the answer against the tree output, the local PDF, and existing paper summaries when needed.
- Return a concise grounded answer with exact paper or page references and explicit limitations.
- Persist reusable artifacts under the active research run folder, normally
<RUN_ROOT>/pageindex/.
Prerequisites
- Local PDFs already exist under an active research run folder, normally
research/<YYYY-MM-DD>-<topic-slug>/pdf/, or under the legacy flatresearch/pdf/layout. - Optional metadata exists under
<RUN_ROOT>/meta/or legacyresearch/meta/. - Optional paper summaries exist under
<RUN_ROOT>/pdf/*.mdor legacyresearch/pdf/*.md. python3is installed and available inPATH.- A local checkout of the open-source PageIndex repo exists. Recommended path:
tools/PageIndex. GEMINI_API_KEYis available for the local PageIndex runner.
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 · 241 lines · 45 tokens per session scan A 87d641b02595
pageindex-grounded is a skill published in the GitHub repository jimezsa/opencolab (11 stars, last pushed 29d ago), licensed MIT. It adds 45 tokens to every session and 2,162 once invoked, about $0.0002 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
gpt-researcher
Autonomous deep research from Codex via MCP.
vs-search-tuning-specify-policy-direction
Viking Search tuning for specified policy directions. Use this when the user provides specific queries, a type of query, or a business policy direction, and asks to boost, suppress, or fix a class of search results through request-parameter passthrough. You must only perform read-only baseline evaluation and…
vs-search-tuning-partial-case
Use when the user provides 1-50 concrete bad-case search queries for one Viking Search app and wants local deterministic fixes. This skill only verifies request-level fine-operation interventions against a read-only baseline scene and delivers a console-ready configuration sheet, validated payloads, and a replay…
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.
research-suite
A multi-source research tool that searches several web services, extracts article text, ranks sources, and produces an answer with citations and differences between sources.