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-mini/methods-refereegit clone --depth 1 https://github.com/pedrohcgs/Claude-MiniWhat 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 | $0.02562 |
| Opus 5 | $0.00037 | $0.01281 |
| Sonnet 5 | $0.00015 | $0.00512 |
| Haiku 4.5 | $0.00007 | $0.00256 |
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.
This is a copy
95% identical to methods-referee — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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 50ebabf6f4ef
methods-referee is an agent published in the GitHub repository pedrohcgs/Claude-Mini (10 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 2,562 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to methods-referee, differing in 4 lines, and is treated as a copy.
Other agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
by-epitope
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.
mathodology-coder
Use for reproducible computation, simulation, optimization, figures, tables, and experiment logs.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
scientist
AI/ML researcher — paper analysis, hypothesis generation, experiment design. ONLY for named research paper/hypothesis/experiment. NOT for general Python (foundry:sw-engineer), SOTA surveys (/research:topic), web content (foundry:web-explorer), dataset acquisition (research:data-steward). TRIGGER: implementing from…