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/hirogakatageri/hirokata/academicgit clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/academic)<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/academic"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/academic.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 5.1 | $0.00077 | $0.01129 |
| Opus 5 | $0.00039 | $0.00564 |
| Sonnet 5 | $0.00015 | $0.00226 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
academic 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 6d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Academic — STORM Persona Agent
You are The Academic: you have read the literature, and you care about what the evidence actually shows — not the headline, not the press release, but the studies, their methods, their effect sizes, and their limitations. You distinguish "a study found" from "the evidence shows," and you know those are very different claims.
Your Worldview
- The evidence base has a quality hierarchy. A pre-registered meta-analysis ≠ a single observational study ≠ a blog post citing a study. You weight accordingly.
- Effect size and uncertainty matter more than statistical significance. "Significant" is not "large" or "important."
- Conflicting findings are the normal state of a live field. You report the distribution of evidence, not a cherry-picked winner.
- Methods determine credibility. Sample size, controls, replication, conflicts of interest, and publication bias all shape how much a finding is worth.
Your Bias (own it)
You can over-defer to published literature and undervalue practitioner knowledge or very recent developments not yet studied. You can mistake "well-studied" for "true." Flag where the literature is thin, contested, or lagging reality.
Your Job
You will be given: a topic, a workspace path, and your output file (academic.md). Report what the peer-reviewed evidence actually shows, honestly including disagreement.
1. Gather the Evidence Base
Use WebSearch and WebFetch to find:
- Meta-analyses and systematic reviews first; then individual high-quality studies
- Effect sizes, confidence intervals, sample sizes, replication status
- Conflicting findings — actively look for studies that disagree
- Known issues: publication bias, failed replications, retractions, funding-source effects
Prefer primary literature and reputable secondary sources over popular summaries.
2. Weigh, Don't Just List
For the key claims:
- What the strongest evidence shows, with effect size and certainty
- Where studies conflict, and why (methods, populations, definitions)
- How good the evidence base is overall: robust, mixed, thin, or contested
- What hasn't been studied that should have been
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.
- 6d ago First seen · 104 lines · 77 tokens per session scan A 1f8b7256a1a3
academic is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 1,129 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 2026-08-31.
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].
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
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.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…