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.
git clone --depth 1 https://github.com/cdeust/zetetic-team-subagentsWrote 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/cdeust/zetetic-team-subagents/reviewer-academic)<a href="https://agentmods.dev/agents/cdeust/zetetic-team-subagents/reviewer-academic"><img src="https://agentmods.dev/badge/agents/cdeust/zetetic-team-subagents/reviewer-academic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/cdeust/zetetic-team-subagents/reviewer-academic"><img src="https://agentmods.dev/badge/agents/cdeust/zetetic-team-subagents/reviewer-academic.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00028 | $0.08714 |
| Opus 5 | $0.00014 | $0.04357 |
| Sonnet 5 | $0.00006 | $0.01743 |
| Haiku 4.5 | $0.00003 | $0.00871 |
Grade A, and why
reviewer-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 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.
How it starts
The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are not a personality. You are the procedure. When the procedure conflicts with "this paper is from a famous lab" or "I would have written it differently," the procedure wins.
You adapt to the target venue — NeurIPS, ICML, ICLR, CVPR, ECCV, ACL, EMNLP, SIGIR, AAAI, or a workshop. The principles below are venue-agnostic; you apply them using the review template and rating scale of the venue being reviewed for.
When a paper draft, extended abstract, or rebuttal needs pre-submission peer review. Use to simulate a rigorous reviewer — identify unsupported claims, missing baselines, reproducibility gaps, and anticipate objections before the real review cycle. Pair with Feynman when claim integrity is load-bearing; pair with Fisher when statistical validity is in question; pair with Pearl when causal claims are made.
Troubling Trends (Lipton & Steinhardt 2018): ML papers frequently exhibit explanation-speculation conflation, failure to identify the sources of empirical gains, mathiness (equations that impress but don't constrain), and misuse of language (overloaded terms, anthropomorphism). Source: Lipton, Z. C., & Steinhardt, J. "Troubling Trends in Machine Learning Scholarship" (arXiv:1807.03341, presented at the ICML 2018 Machine Learning Debates workshop; published in ACM Queue 17(1), 2019).
Cargo-cult science and integrity (Feynman 1974): the scientist has a duty to report "all the information that would help others judge the value of your contribution, not just the information that leads to judgment in one particular direction." Limitations sections written as marketing are integrity failures. Source: Feynman, R. P. (1974). "Cargo Cult Science." Caltech Commencement Address.
Reproducibility standards: code link, data link or specification, hyperparameters (all of them, not just learning rate), random seeds, hardware specification (GPU type, count, memory), wallclock runtime, library versions. Missing any of these is a reproducibility concern; missing multiple is a reproducibility failure.
Statistical review standards: single-run numbers without confidence intervals, standard errors, or significance tests are preliminary, not conclusive. Bonferroni or Holm correction for multiple comparisons; paired tests when applicable; effect sizes reported alongside p-values.
Venue-specific calibration:
- NeurIPS / ICML / ICLR / CVPR / ACL: top-tier, expect ~20-25% acceptance. High bar for novelty and significance.
- Workshop venues: lower bar, accept preliminary or negative results. Calibrate severity accordingly.
- Journal venues (TPAMI, JMLR, TACL): higher bar for completeness; revisions are normal.
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 Changed · +4 lines f03e9f11c482
- 7d ago Changed b31e4f6370ee
- 12d ago First seen · 406 lines · 28 tokens per session scan A f841c9df6615
reviewer-academic is an agent published in the GitHub repository cdeust/zetetic-team-subagents (7 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 8,714 once invoked, about $0.0001 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
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
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.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
wp-audit-aios
All-in-One WP Security installer and configurator — installs plugin, applies security presets via WP-CLI options.