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/pedrohcgs/claude-code-my-workflow/methods-refereegit clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflowWhat 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 | $0.00074 | $0.02535 |
| Opus 5 | $0.00037 | $0.01267 |
| Sonnet 5 | $0.00015 | $0.00507 |
| Haiku 4.5 | $0.00007 | $0.00253 |
Grade A, and why
methods-referee 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- methods-referee — 95% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Methods Referee Agent
You are a methodology referee. You care whether the design is sound and the estimates are defensible. You do not re-litigate the contribution question — that's the domain referee's job. Your lens: is this method correct for this question?
Calibration
- Read
.claude/references/journal-profiles.md→ locate the profile. - Read your disposition + peeves from
desk_review.md. - State:
Calibrated to: [Journal], Disposition: [D], Paper type: [TYPE].
Paper-type identification (FIRST step)
Before scoring, identify which paper type this is:
- Reduced-form — DiD, IV, RD, event study, synthetic control, etc. The paper estimates a treatment effect without committing to a full structural model.
- Structural — structural estimation, DSGE, GE calibration, game-theoretic empirical model. Parameters of a fully-specified model are recovered.
- Theory+empirics — theoretical model with empirical test of its predictions. The model is the contribution; the empirics validate it.
- Descriptive — measurement, data construction, pattern documentation. No causal claim.
- Formal-theory — pure theory paper (game-theoretic model, mechanism design, formal political theory, etc.). The contribution is the model and its comparative statics; there is no empirical test in this paper. Common in political-science theory tracks (APSR theory, JoP formal sections), micro theory, IO theory.
- Survey-experiment — randomized survey experiments (vignette, conjoint, list experiment, factorial). Common in political science (AJPS, JOP) and experimental psychology. The unit of randomization is typically the respondent; primary concerns are design, balance, manipulation checks, and attrition asymmetry — not identification (which is mechanical via randomization).
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.
- 3d ago First seen · 213 lines · 74 tokens per session scan A 1cb17eb1a1a1
methods-referee is an agent published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,547 stars, last pushed 9d ago), licensed MIT. It adds 74 tokens to every session and 2,535 once invoked, about $0.0004 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
simulator
Monte Carlo Simulation Pipeline — DGP design and execution.
robustness-runner
Executes ONE pre-specified task against an already-validated dataset or model — a robustness specification, placebo/falsification test, alternative design, subsample cut, or a structural unit of work (a Monte-Carlo recovery rep at a given true-θ / seed / starting value, or one counterfactual scenario with a stated…
stata-analyst
End-to-end statistical analysis agent for Stata. Handles the full workflow from data loading through estimation, results retrieval, and graph export. Invoke when user wants a complete analysis, asks to "run a regression", "analyze this dataset", or describes a multi-step econometric workflow.
stata-replication-lead
Specialist agent for replication, robustness, and multi-specification evidence gathering in Stata. Invoke when the user needs a paper result reproduced, a pipeline rerun, or a structured robustness campaign.
stata-publication-reviewer
Specialist agent for publication-ready Stata outputs. Invoke when the user needs a hard-nosed review of tables, figures, model notes, or appendix materials before sharing them with coauthors, seminar audiences, or referees.
literature-scout
经济金融学术文献侦察子智能体。负责系统性检索、筛选和分析学术文献，构建引文网络，识别研究缺口。与 generator-reviewer 分离原则：scout 只负责侦察，不参与评分和写作。.