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 instructions/maweiruc/stat-toolkits-eif/agents-mdgit clone --depth 1 https://github.com/maweiruc/stat-toolkits-eifWrote 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/instructions/maweiruc/stat-toolkits-eif/agents-md)<a href="https://agentmods.dev/instructions/maweiruc/stat-toolkits-eif/agents-md"><img src="https://agentmods.dev/badge/instructions/maweiruc/stat-toolkits-eif/agents-md.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 | $0.01072 | $0.01072 |
| Opus 5 | $0.00536 | $0.00536 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
stat-toolkits-eif AGENTS.md 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 4d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions for the EIF toolkit
This repository is a documentation-first toolkit for deriving, validating, and implementing efficient influence functions (EIFs). It is not primarily a Python package yet. Treat the files in agent/, theory/, examples/, and simulations/ as the working system.
First files to read
For any EIF task, read these files first:
agent/eif_agent_task_spec.mdagent/eif_latex_problem_protocol.mdagent/eif_target_triage.mdagent/eif_research_problem_protocol.mdagent/eif_hard_problem_protocol.mdagent/eif_answer_rubric.mdtheory/semiparametric_influence_function_guide.mdtheory/eif_projection_guide.mdagent/eif_danger_zone.mdexamples/eif_examples.mdagent/eif_validation_tests.mdagent/eif_implementation_guide.md
Use examples/eif_formula_registry.yaml only after checking that the observed data, target, model, assumptions, nuisance definitions, and positivity conditions match.
For self-testing or evaluation, use both examples/eif_benchmark_tasks.md and examples/eif_hard_benchmark_tasks.md.
Default workflow
When the user gives a problem, especially in LaTeX:
- Normalize the problem statement.
- Assign a target triage label.
- State the observed-data unit (O).
- Separate the scientific target from the observed-data functional.
- State identification assumptions.
- State the statistical model.
- Check pathwise differentiability.
- Check whether the model is fully nonparametric or restricted.
- Identify nuisance functions and positivity conditions.
- Factorize the likelihood and decompose the score.
- Derive the IF/EIF component by component.
- Verify mean zero and the pathwise derivative identity.
- Check special-case reductions.
- Provide estimator, standard error, and validation code only when requested or useful.
LaTeX inbox behavior
For LaTeX inbox/problem-folder artifacts, follow agent/eif_problem_artifacts.md.
When the user asks to process a LaTeX problem under problems/latex_inbox/problem_*/problem.tex, check whether notes.md exists in the same folder.
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.
- 4d ago First seen · 104 lines · 1,072 tokens per session scan A b7e8be577240
stat-toolkits-eif AGENTS.md is an instructions file published in the GitHub repository maweiruc/stat-toolkits-eif (12 stars, last pushed 3mo ago), licensed MIT. It adds 1,072 tokens to every session, about $0.0054 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 instructions, from other repositories
co-mathematician CLAUDE.md
Instructions for VeryMath/co-mathematician, covering claude.md, repository contract, required flow, claude code operating notes and harness commands.
SutroYaro GEMINI.md
Instructions for cybertronai/SutroYaro, covering gemini.md - sutro group research workspace, project context, read these first, core concepts and current best methods.
mcp-pubmed-server-pancrpal CLAUDE.md
Instructions for PancrePal-xiaoyibao/mcp-pubmed-server-pancrpal, covering claude.md, project overview, commands, architecture and mcp tools (8 total).
braina GEMINI.md
Instructions for brainets/braina, covering project: braina (brain interaction analysis), 1. project context & purpose, 2. commands, verify environment (all core dependencies) and run the verification test suite for frites + hoi.
cdxml-toolkit-community AGENTS.md
AGENTS.md instructions for ZiChenWang114514/cdxml-toolkit-community, a project described as: Community CDXML toolkit and MCP server.
research-automation CLAUDE.md
Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.