badani

A workflow for adding secondary literature to a research map. It summarizes what each source argues, records where the claim appears, and compares it with positions already documented.

In plain words
What is it for?
Use it to process files in a raw_secondary folder, verify claims in context, map agreements and disagreements, identify research gaps, and update the study's research notes.
Why use it?
It helps distinguish an author's argument from evidence about the subject being studied. It also reveals contradictions, missing research, and which parts of a thesis are not original.

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/badani
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 546 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 $0.00546
Opus 5 $0.00013 $0.00273
Sonnet 5 $0.00005 $0.00109
Haiku 4.5 $0.00003 $0.00055

Measured 2d ago against content hash 451c61534563, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

badani 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/badani.md · 25 lines

What it actually says

Proveď ingest sekundární literatury dle CLAUDE.md, sekce „Sekundární literatura".

Pro nový soubor v raw_secondary/:

  1. Přečti ho a zkompiluj jeho POZICI (co tvrdí o předmětu studie) — PARAFRÁZÍ, s provenance (raw_secondary/<soubor>) a kotevní frází u každého klíčového tvrzení. NECITUJ ho jako doklad o světě, jen jako cizí pozici s atribucí.
  2. Dvouvrstvé ověření (pravidlo 1): u každé připsané pozice ověř nejen, že kotevní fráze v souboru JE, ale že pozice sedí i v KONTEXTU — že použití nepřekrucuje, co autor reálně tvrdí. Shoda slov nestačí; překroucení cizí pozice je fabulace. Nejistý kontext → oslab nebo vynech.
  3. Zařaď do process/badani.md. Zmapuj shody a rozpory s pozicemi, co tam už jsou.
  4. Vyznač mezeru, kterou teze studie zaplňuje (co tahle literatura přehlíží).
  5. Přepočítej originalitu: co z teze tenhle zdroj už říká sám → co zbývá jako vlastní příspěvek? Zapiš ten zbytek. (Zdroj, který tezi potvrzuje, umí novost tiše sebrat.)
  6. Typ a rovnováha: je to teoretická optika, nebo doklad konsensu oboru? Když přibývá 3.+ teoretická čočka bez jediného oborového zdroje, NAHLAS disbalanci (riziko „přehlídky aparátu") — chybí bádání o předmětu, ne další čočka.
  7. Připiš JEN to, co v souboru najdeš — nikdy „autor by nejspíš řekl". Zdroj mimo raw_secondary/ vůbec nejmenuj.

Zaloguj. Po několika zdrojích nabídni, že z badani.md napíšeš situování do úvodu.

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 · 25 lines · 25 tokens per session scan A 451c61534563

Subscribe to this mod's changes

badani 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 546 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.