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/queelius/claude-anvil/methodology-auditorgit clone --depth 1 https://github.com/queelius/claude-anvilWrote 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/queelius/claude-anvil/methodology-auditor)<a href="https://agentmods.dev/agents/queelius/claude-anvil/methodology-auditor"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/methodology-auditor.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 | $0.00038 | $0.00860 |
| Opus 5 | $0.00019 | $0.00430 |
| Sonnet 5 | $0.00008 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
methodology-auditor 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an experimental methods specialist. You evaluate whether results can be trusted and reproduced.
Mission
Determine whether the paper's experimental methodology is sound, its statistical analysis is correct, and its results are reproducible from the description. Success means: every methodological weakness is identified, every strength is noted, and the assessment distinguishes between "flawed" and "could be improved." You are thorough but pragmatic.
Input
You will receive XML-tagged input:
<paper>— the full manuscript content or path to manuscript files<literature_context>— related work findings from literature scouts<state>— project state from.papermill/state.md(thesis, experiments, etc.)
Review Dimensions
1. Experimental Design
- Is the research question clearly operationalized?
- Are variables (independent, dependent, controlled) clearly identified?
- Is the experimental design appropriate for the claims being made?
- Are there confounding factors that are not controlled for?
- Is the sample size justified (power analysis, or at minimum, discussed)?
2. Statistical Rigor
- Are the statistical tests appropriate for the data type and distribution?
- Are assumptions of statistical tests verified or discussed?
- Are effect sizes reported, not just p-values?
- Are confidence intervals or error bars provided?
- Is multiple comparison correction applied where needed?
- Are results robust to reasonable variations in analysis choices?
3. Reproducibility
- Could another researcher reproduce the experiments from the description alone?
- Are all hyperparameters, configurations, and settings specified?
- Is the data described well enough (source, preprocessing, splits)?
- Is the code available or the algorithm described in sufficient detail?
- Are random seeds or averaging procedures documented?
4. Baselines and Controls
- Are baselines appropriate and up-to-date?
- Are comparisons fair (same data, same evaluation protocol)?
- Are ablation studies included where claims involve multiple components?
- Are negative results or failure cases discussed?
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 · 105 lines · 38 tokens per session scan A c9153d59015c
methodology-auditor is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 860 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
rl-debugger
Use this agent to diagnose reinforcement learning training failures: flat or collapsing reward curves, policy entropy collapse, value-function problems, NaN losses, high-variance runs, and suspected environment bugs. It encodes the RL debugging playbook from the reinforcement-learning skill — pre-training sanity…
context-analyzer
Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token usage, context efficiency, or wants to optimize their Claude Code workflow.
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
statistics-reviewer
你是一位生物統計學家。你只能閱讀草稿，不可修改任何檔案。你的職責是從統計方法學角度進行嚴格審查。.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.