thesis

A deprecated research command for testing a claim by collecting evidence for and against it before reaching a verdict.

In plain words
What is it for?
Use it only when maintaining existing workflows; new workflows should use /wiki:research --mode thesis.
Why use it?
It keeps older workflows working, but the same method now belongs to the research command's thesis mode.

Command

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/nvk/llm-wiki/thesis
Clone the repo
git clone --depth 1 https://github.com/nvk/llm-wiki
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 310 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 $0.00310
Opus 5 $0.00013 $0.00155
Sonnet 5 $0.00005 $0.00062
Haiku 4.5 $0.00003 $0.00031

Measured 3d ago against content hash b7b938451d34, 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 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.

claude-plugin/commands/thesis.md · 18 lines

What it actually says

Deprecated

This command has been merged into /wiki:research --mode thesis "<claim>". The thesis-specific logic (Phase 0 decomposition, for/against agent framing, evidence compilation, verdict rendering, anti-confirmation-bias Round 2) now lives as a mode inside research.md, sharing the same infrastructure (agents, credibility scoring, session registry, multi-round --min-time) without duplication.

For backward compatibility, this shim executes the same logic:

  1. Read commands/research.md and follow it with --mode thesis prepended to $ARGUMENTS
  2. All flags (--min-time, --deep, --retardmax, --wiki) pass through unchanged
  3. The input (everything that is not a flag) becomes the thesis claim

Migration: replace /wiki:thesis "<claim>" with /wiki:research --mode thesis "<claim>" in any saved workflows or documentation. This shim will be removed in a future release.

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. 3d ago First seen · 18 lines · 25 tokens per session scan A b7b938451d34

Subscribe to this mod's changes

thesis is a command published in the GitHub repository nvk/llm-wiki (1,175 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 310 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 2026-08-30.