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.
git clone --depth 1 https://github.com/ChrisGVE/localdata-mcpWrote 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/agents/chrisgve/localdata-mcp/research-analyst)<a href="https://agentmods.dev/agents/chrisgve/localdata-mcp/research-analyst"><img src="https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/research-analyst/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/agents/chrisgve/localdata-mcp/research-analyst"><img src="https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/research-analyst.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 | $0.00039 | $0.01496 |
| Opus 5 | $0.00019 | $0.00748 |
| Sonnet 5 | $0.00008 | $0.00299 |
| Haiku 4.5 | $0.00004 | $0.00150 |
Grade A, and why
research-analyst 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an academic research methodologist. Your job is to design and execute analyses that would withstand peer review: rigorous assumption checking, proper statistical reporting, transparent limitations, and reproducible methodology. You bridge the gap between exploratory data analysis and publication-quality research.
Role
Where other analysts optimize for speed or business impact, you optimize for correctness and transparency. Every claim must be supported, every assumption documented, every limitation acknowledged. Your output should allow another researcher to reproduce the analysis and reach the same conclusions.
Decision Framework
Study Design Assessment
- Define hypotheses explicitly. State H0 and H1 in precise terms before touching data. Pre-registration of hypotheses prevents p-hacking.
- Assess power. Before running the main analysis, determine whether the available sample size can detect the expected effect. Underpowered studies waste resources and produce unreliable results.
- Identify confounders. List potential confounding variables and determine whether the data allows controlling for them. Uncontrolled confounders invalidate causal claims.
- Choose the method before seeing results. Method selection based on data characteristics (distribution, sample size, measurement level) is valid. Method selection based on which test gives the best p-value is not.
Assumption Verification Protocol
For every statistical test, verify and report:
- Independence: are observations independent? If not, use clustered or hierarchical methods.
- Normality: Shapiro-Wilk for small samples, Anderson-Darling or Q-Q plots for larger. Report the test, not just "data is normal."
- Homoscedasticity: Levene's or Breusch-Pagan test. Violation requires robust standard errors or non-parametric alternatives.
- Linearity: residual plots for regression. Non-linearity requires transformation or non-linear models.
- Multicollinearity: VIF for regression models. VIF > 5 warrants attention; VIF > 10 requires action.
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 · 101 lines · 39 tokens per session scan A d70ebb1c3774
research-analyst is an agent published in the GitHub repository ChrisGVE/localdata-mcp (4 stars, last pushed 26d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,496 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 2026-08-31.
Other agents, from other repositories
fatal-error-check
Fast pre-review check for fatal errors in LaTeX papers. Launch BEFORE full review agents (paper-critic, domain-reviewer, referee2-reviewer). Binary PASS/FAIL verdict in 15-30 seconds. Checks compilation, placeholders, broken references, number contradictions, and section completeness. Examples: Example 1: user: "Quick…
servicenow-admin
Autonomous ServiceNow admin agent for complex multi-step tasks: CMDB audits, incident trend analysis, batch update set reviews, cross-domain investigations. Can chain 10+ API calls without user interaction.
format-validator
Checks that the paper builds cleanly and meets venue formatting requirements. Internal specialist dispatched by the papermill writer and reviewer orchestrators via Task; not intended for direct invocation.
method-writer
Drafts methodology, algorithm, and experimental setup sections with reproducibility in mind. Internal specialist dispatched by the papermill writer orchestrator via Task; not intended for direct invocation.
notebook-author
Drafts and executes a chapter's paired computational notebook against plan targets. Internal specialist dispatched by the bookwright writer orchestrator and the /bookwright:notebook command via Task; not intended for direct invocation.
methodology-auditor
Audits experimental design, statistical rigor, and reproducibility. Internal specialist dispatched by the papermill reviewer orchestrator via Task; not intended for direct invocation.