Borrowing it
Nothing to install: this file belongs to arnaudgelas/K-Ops. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/arnaudgelas/K-Ops/main/.claude/commands/research_review.mdgit clone --depth 1 https://github.com/arnaudgelas/K-OpsWrote 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/commands/arnaudgelas/k-ops/research_review)<a href="https://agentmods.dev/commands/arnaudgelas/k-ops/research_review"><img src="https://agentmods.dev/badge/commands/arnaudgelas/k-ops/research_review.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 | $0.00002 | $0.00483 |
| Opus 5 | $0.00001 | $0.00242 |
| Sonnet 5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
research_review 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 8d 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 the Research Review agent for this repository.
Goal:
- Stress-test the emerging thesis, challenging assumptions, and identifying weak evidence, contradictions, and missing sources.
Inputs:
- Research brief: research/briefs/-.md
- Findings file: research/findings/-.md
- Review file: research/notes/-contrarian-review.md
Instructions:
- Adversarial mindset: Assume the emerging thesis in the findings file is incorrect or incomplete. Actively search for counter-evidence, alternative explanations, and logical flaws. Do not write a polite review; be extremely critical and raise P0 objections.
- Review findings and source notes:
- Read the brief, findings, and related source notes in
notes/Sources/thoroughly. - Check the
evidence_strengthof each source. If any claims are backed bysecondaryormodel-generatedevidence, flag them as high-priority risks. - Verify if any imported model reports are cited without primary source confirmation.
- Read the brief, findings, and related source notes in
- Draft the review:
- Write/update
research/notes/<topic-slug>-contrarian-review.md. Preserve its frontmatter (type:research-review,topic_slug, etc.). - Under
## Strongest Objections, list logical weaknesses, alternative interpretations of the evidence, or negative results. - Under
## Missing Evidence, list crucial gaps where claims are made without primary sources or with weak/secondary evidence. Suggest specific primary specs, docs, or code to fetch. - Under
## Claims To Soften, name specific claims from the findings file that should be qualified, softened, or removed because the evidence is insufficient.
- Write/update
- No fabrication: Do not invent counter-evidence. Identify genuine gaps in the current research and evidence base.
- Progress Log: Append a short progress update when done.
Done checklist:
- Substantive written review saved in
research/notes/<topic-slug>-contrarian-review.mdcovering objections, missing evidence, and claims to soften. - All objections are grounded in logical critique or real counter-evidence.
- Evidence strength is evaluated, highlighting any secondary or model-generated dependency.
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.
- 8d ago First seen · 34 lines · 2 tokens per session scan A b99d3c0fd860
research_review is a command published in the GitHub repository arnaudgelas/K-Ops (1 stars, last pushed 20d ago), licensed MIT. It adds 2 tokens to every session and 483 once invoked, about $0.0000 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 commands, from other repositories
zotero-review
Read and analyze papers from a Zotero collection, then synthesize them into the bound Obsidian project knowledge base or markdown review outputs.
kb-links
Repair or strengthen wikilinks among canonical KB notes without generating extra artifact sprawl.
kb-promote
Promote durable content from Daily or source notes into canonical Knowledge, Experiments, Results, Results/Reports, or Writing notes.
wiki-retro
Save an atomic insight from the current task into the wiki. Creates a single markdown file that layered recall surfaces in future sessions.
wiki-discover
Auto-discover new sources from the web. Searches based on config topics and known knowledge gaps.
wiki-run
Run the full wiki cycle: discover → ingest → lint. Optionally schedule for auto-updates.