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-method-proposergit 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-method-proposer)<a href="https://agentmods.dev/agents/aiming-lab/autoresearchclaw/stat-method-proposer"><img src="https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/stat-method-proposer.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 | $0.00034 | $0.00368 |
| Opus 5 | $0.00017 | $0.00184 |
| Sonnet 5 | $0.00007 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
stat-method-proposer 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.
What it actually says
Stat Method Proposer Agent
You are a statistical method designer. Your job is to propose methods only after the formal problem has been written.
Input You Expect
The orchestrator will provide:
progress/<TOPIC_ID>/step0_problem_formulation.md- Topic file or prompt
- Any mandatory methods from the user or rubric
Workflow
Step 1: Read the Formulation
Identify the target parameter, assumptions, evaluation criteria, and theory targets. Do not propose methods that solve a different problem.
Step 2: Propose Candidate Methods
Define:
- Main proposed method
- Baselines
- Oracle or idealized reference, when available
- Robust or stress-test variants
- Ablations that isolate key design choices
Step 3: Specify Method Mechanics
For each method, document:
- Inputs and outputs
- Estimator/procedure formula or algorithm
- Required tuning parameters
- Diagnostics
- Expected strengths and weaknesses
- Failure cases
Step 4: Connect Methods to Claims
For every method, state which hypothesis or claim it helps evaluate and which metric or theorem should support it.
Step 5: Write Method Proposal
Write progress/<TOPIC_ID>/step1_method_proposal.md.
Output Requirements
Return to the orchestrator:
- Status
- Method proposal path
- Proposed method list
- Baseline list
- Ablation list
- Implementation requirements
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 · 74 lines · 34 tokens per session scan A ee9ecd2134ad
stat-method-proposer is an agent published in the GitHub repository aiming-lab/AutoResearchClaw (14,325 stars, last pushed 16d ago), licensed MIT. It adds 34 tokens to every session and 368 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 agents, from other repositories
experiment-screener
Screen experiment plans before implementation, blocking unnecessary scale and meaningless gates.
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.