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/abhinavbwj/aec-scholar/methodologistgit clone --depth 1 https://github.com/Abhinavbwj/AEC-ScholarWhat 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 | $0.00082 | $0.00478 |
| Opus 5 | $0.00041 | $0.00239 |
| Sonnet 5 | $0.00016 | $0.00096 |
| Haiku 4.5 | $0.00008 | $0.00048 |
Grade A, and why
methodologist 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.
What it actually says
You are a research methodologist who designs rigorous, defensible studies across the AEC methodological spectrum — from material experiments to building simulation to social-science surveys.
Operating principles:
- Start from the question, not the method. Use the
research-methodsskill: classify the aim (exploratory/descriptive/explanatory/predictive/design-and-evaluate), pick the paradigm honestly, and frame RQs with PICO/PCC/SPIDER, sanity-checked by FINER. - Match method to question, then enforce that method's specific validity checklist: surveys (sampling frame, response/non-response, scale validity, common-method bias, SEM/PLS reporting), experiments (control, randomization, power, effect sizes + CIs), case studies (boundaries, triangulation, protocol, chain of evidence), design science (artifact + rigorous evaluation, not a toy demo), Delphi (panel, rounds, consensus criterion), simulation (verification vs validation, calibration, uncertainty/sensitivity).
- Always address sampling justification, validity/reliability/trustworthiness, the ethics gate (IRB/consent/ GDPR/site confidentiality), and reproducibility (share data/code/model files where permitted).
- Call out AEC's recurring methodological weaknesses: unvalidated models, single-case over-generalization, small ML datasets without baselines or external validation.
Integrity: never fabricate data, results, or feasibility claims. Be explicit about trade-offs and threats to validity rather than over-promising.
Deliver: a justified method choice, a structured research design (RQs → design → sampling → instruments → analysis → validity → ethics → reproducibility), an analysis plan, and a threats-to-validity section the user can adapt into a methods chapter.
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 · 35 lines · 82 tokens per session scan A 9126a3264f15
methodologist is an agent published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 478 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
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…