hypothesis

A command for recording experiments based on hypotheses, which are testable explanations or predictions. It maintains an append-only experiment log and a design document that collects the best results.

In plain words
What is it for?
Use it to document research rounds and conclude or update a state-of-the-art design. It also checks and upgrades a required toolkit before starting.
Why use it?
It keeps each experiment's setup, prediction, result, and verdict together, so later design decisions can be traced back to evidence.

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/stellarshenson/claude-code-plugins/hypothesis
Clone the repo
git clone --depth 1 https://github.com/stellarshenson/claude-code-plugins
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 1,098 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 $0.01098
Opus 5 $0.00012 $0.00549
Sonnet 5 $0.00005 $0.00220
Haiku 4.5 $0.00002 $0.00110

Measured 2d ago against content hash c2b0f028147a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hypothesis 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.

plugins/datascience/commands/hypothesis.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hypothesis

Read the datascience:hypothesis skill first - it is the single source of truth for the document structure, the per-hypothesis template, and the canonical-doc-across-runs rules. Do NOT duplicate its content here.

Write up or extend hypothesis-driven research documentation: the canonical append-only experiments log (each hypothesis with setup, prediction, result, verdict) and the SOTA document (winning components distilled into a final design).

Toolchain gate (MANDATORY - run before anything else)

Run this first, every session, before any other work. The upgrade always runs; a version mismatch blocks.

python3 -m pip install --user --upgrade stellars-claude-code-plugins 2>&1 | tail -1
LIB=$(python3 -c "import importlib.metadata as m;print(m.version('stellars-claude-code-plugins'))" 2>/dev/null) || { echo "FATAL: toolkit unavailable"; exit 1; }
PLUG=$(grep -m1 '"version"' "${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json" 2>/dev/null | cut -d'"' -f4)
OLDER=$(printf '%s\n%s\n' "$LIB" "$PLUG" | sort -V | head -1)
[ -n "$PLUG" ] && [ "$LIB" != "$PLUG" ] && [ "$OLDER" = "$LIB" ] && { echo "STALE: library $LIB older than plugin $PLUG - refusing to run on an outdated CLI; re-run the upgrade"; exit 1; }
echo "toolkit $LIB"

Run the CLI without touching the caller's project. The gate above puts it on PATH, so the bare command name is the whole invocation. uv run instead resolves whatever project the working directory sits in and writes uv.lock and .venv into it, so if you reach for uv pass --no-project (uv run --no-project <cli> ...) - it skips project discovery, leaves the tree untouched and still finds the same PATH binary. --no-sync and --frozen are not substitutes; both still create .venv.

Both branches exit non-zero and neither is advisory: an absent library (FATAL) and a version mismatch (STALE). A mismatch means the CLI is not the one this file was written against, so its documented flags and rules are unverified. Report the line and stop; do not work around it.

Read the full file on GitHub · 50 lines

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 · 50 lines · 23 tokens per session scan A c2b0f028147a

Subscribe to this mod's changes

hypothesis is a command published in the GitHub repository stellarshenson/claude-code-plugins (3 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 1,098 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.