thesis

A process for forming and testing the central claim of a study. It checks whether the idea is supported by the source material, offers five versions with different levels of risk, and tests the chosen version before outlining the study.

In plain words
What is it for?
Use it to test the claim’s scope, structure, significance, uniqueness, and connection to the study’s own vocabulary, then record the result and propose an outline.
Why use it?
It helps turn a broad insight into a claim that can be argued, supported, and evaluated. Human approval remains part of choosing the final wording.

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/thesis
Clone the repo
git clone --depth 1 https://github.com/josefslerka/study-kit

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 212 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 $0.00023 $0.00212
Opus 5 $0.00012 $0.00106
Sonnet 5 $0.00005 $0.00042
Haiku 4.5 $0.00002 $0.00021

Measured 2d ago against content hash 7fee7df6846a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

thesis 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.

en/.claude/commands/thesis.md · 15 lines

What it actually says

Run BLOCK A per CLAUDE.md, section "Phases → BLOCK A".

First read idea.md and search raw_primary/ to see whether the insight has support in the corpus.

1.1: apply the thesis-ness test (5 conditions) and present 5 reformulations by risk (A–E). Recommend a version for the target journal, but LEAVE THE CHOICE TO THE HUMAN — ask and wait. 1.2: on the chosen thesis run the 4 stress tests (scope, structurability, "so what", uniqueness), plus the groundability check (is the load-bearing vocabulary the text's own or an imported label?).

GATE: the thesis meets the 5 thesis-ness conditions and all the tests. If not, go back. Once it passes, write process/thesis.md, add a line to log.md, and propose /outline.

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 · 15 lines · 23 tokens per session scan A 7fee7df6846a

Subscribe to this mod's changes

thesis is a command published in the GitHub repository josefslerka/study-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 212 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.