review

A command for simulating a peer-review report by checking an academic draft against its primary sources.

In plain words
What is it for?
Use it to write a structured review, verify every claim against source texts, record objections, and prepare the next revision step.
Why use it?
It prevents the draft from validating itself and exposes inaccurate quotations, weak evidence, unsupported connections, and overly broad claims.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/josefslerka/study-kit/review
Clone the repo
git clone --depth 1 https://github.com/josefslerka/study-kit

Made for: Claude Code.

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 401 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00401
Opus 5 $0.00013 $0.00200
Sonnet 5 $0.00005 $0.00080
Haiku 4.5 $0.00003 $0.00040

Measured 2d ago against content hash e611f92b78c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

cs/.claude/commands/review.md · 21 lines

What it actually says

Proveď fázi 4.3 dle CLAUDE.md.

KLÍČOVÉ: konfrontuj draft ze study/ PROTI primárním textům v raw_primary/. Draft NEBER jako zdroj pravdy — tvůj výtvor nesmí validovat sám sebe. U každého tvrzení draftu ověř, zda sedí s raw_primary/.

Tři tvrdé kontroly proveď VŽDY:

  • věrnost citátů (doslovnost + kontiguita; pravidlo 1),
  • frekvence „důkazů" (grep; pravidlo 9),
  • spoje, ne cihly — syntetický spoj jádra stojí na pojmu, ne na shodě slov (pravidlo 8). A zvlášť prověř ohraničení teze (pravidlo 8b): je některý text, na který se teze nerozšíří, „zachráněn" vývojovým příběhem nebo „výjimkou, co potvrzuje pravidlo"? Pokud ano, je to námitka — správné ohraničení je ověření na protikladu (chybí předpoklad → chybí účinek).

Napiš posudek: shrnutí, původní příspěvek, silné stránky, hlavní námitky (popis + požadavek

  • závažnost), drobné připomínky, verdikt, a 1 nejdůležitější větu. U námitek ukaž, kde se draft míjí s raw_primary/. Zapiš process/posudek.md, zaloguj, navrhni /revize.
Changes

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.

  1. 2d ago First seen · 21 lines · 25 tokens per session scan A e611f92b78c8

Subscribe to this mod's changes

review is a command published in the GitHub repository josefslerka/study-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 401 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.