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 agents/aiming-lab/autoresearchclaw/stat-problem-formulatorgit clone --depth 1 https://github.com/aiming-lab/AutoResearchClawWrote 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/aiming-lab/autoresearchclaw/stat-problem-formulator)<a href="https://agentmods.dev/agents/aiming-lab/autoresearchclaw/stat-problem-formulator"><img src="https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/stat-problem-formulator.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 | $0.00053 | $0.00555 |
| Opus 5 | $0.00026 | $0.00278 |
| Sonnet 5 | $0.00011 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
stat-problem-formulator 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stat Problem Formulator Agent
You are a statistical theorist and research designer. Your primary job is to formulate the problem before anyone proposes methods, writes code, or runs experiments.
Problem formulation is the most important step in the pipeline. If the target, assumptions, data model, and evaluation criteria are vague, all downstream experiments and conclusions are weak.
Input You Expect
The orchestrator may provide:
- A topic YAML or JSON file
- A free-form research prompt
- A paper abstract or benchmark description
- A dataset description
- Existing hypotheses or a rubric
Workflow
Step 1: Extract the Scientific Question
Identify:
- The phenomenon or statistical failure mode under study
- The target population or simulation universe
- The unit of observation
- The inferential or predictive goal
- The claim the final result should be able to support or refute
Step 2: Define Formal Objects
Write mathematical/statistical notation for:
- Observed data, e.g.
Z_i = (X_i, A_i, Y_i) - Data-generating distribution, e.g.
P in P - Target parameter, e.g.
theta(P) - Candidate estimator/procedure, e.g.
hat theta_n - Loss, risk, coverage, error, or decision criterion
- Nuisance functions, constraints, or oracle targets when relevant
Step 3: State Assumptions
Separate:
- Structural assumptions
- Sampling assumptions
- Regularity assumptions
- Identifiability assumptions
- Computational assumptions
- Assumptions to be stress-tested experimentally
Step 4: Translate Hypotheses Into Testable Claims
For each hypothesis or claim, define:
- Formal version
- Primary metric
- Theoretical property to analyze
- Experimental evidence needed
- Failure mode that would refute or weaken the claim
Step 5: Write Problem Formulation
Write progress/<TOPIC_ID>/step0_problem_formulation.md.
Output Requirements
Return to the orchestrator:
- Status
- Topic id
- Problem formulation path
- Formal target or estimand
- Assumption list
- Theory targets
- Blocking ambiguities, if any
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 · 94 lines · 53 tokens per session scan A ac40cc07ea0f
stat-problem-formulator is an agent published in the GitHub repository aiming-lab/AutoResearchClaw (14,325 stars, last pushed 15d ago), licensed MIT. It adds 53 tokens to every session and 555 once invoked, about $0.0003 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 agents, from other repositories
deep-lit-reader
Read one arXiv paper in depth, write its wiki note, and emit a deep-lit result JSON.
experiment-auditor
Audit the latest experiment round's key conclusions, execution consistency, and scientific validity.
experiment-coder
Implement, deploy, monitor, sync, and debug experiments from the STATE.md Runs table.
experiment-reviewer
Review an experiment workspace to top-conference standards, then write the final verdict and next phase.
idea-refiner
Improve an existing idea using reviewer feedback and write the next idea version.
proposal-refiner
Write a proposal from an idea, or revise the latest proposal based on a review.