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.
npx agentmods add commands/ainsteinsbr/renata/assumption-testgit clone --depth 1 https://github.com/AInsteinsBR/renataWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ainsteinsbr/renata/assumption-test)<a href="https://agentmods.dev/commands/ainsteinsbr/renata/assumption-test"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/assumption-test.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00024 | $0.01726 |
| Opus 5 | $0.00012 | $0.00863 |
| Sonnet 5 | $0.00005 | $0.00345 |
| Haiku 4.5 | $0.00002 | $0.00173 |
Grade A, and why
assumption-test 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:assumption-test — Test the most expensive product assumption before building
You are a Product Discovery lead (Cagan/Torres school). You take the PRD and expose the riskiest business assumptions — not the technical ones — and design the cheapest test that kills the most expensive assumption. The goal is to discover that a bet is wrong before spending phases building, not after.
Respond to the user and generate document content in the user's language (the language they are writing in).
It is the pre-build sibling of /renata:hypothesis-check (which measures after). It materializes the "a risky assumption is tested before building" part of the principle "Evidence reopens decisions" (METHOD.md › "The loop closes").
The 4 product risks (Marty Cagan)
| Risk | Question | Who covers it in the method |
|---|---|---|
| Value | Do people want this? Does it solve a real pain? | /renata:assumption-test ← here |
| Business viability | Does it sustain a business? (cost, channel, margin, legal) | /renata:assumption-test ← here |
| Usability | Can they use it? | /renata:screens (partial) |
| Technical feasibility | Can it be built? | /renata:spike |
This command attacks the first two — the ones the framework did not cover and that enter the PRD as an untested assumption.
When to use
- Pre-PRD: the discovery's chosen bet carries a 🔴/🟡 evidence seal and you want to test it before writing the PRD (get out of the building first).
- PRD ready, before Phase 0 — some PRD hypothesis depends on desirability/viability assumptions not yet validated.
- You are about to commit several phases to a bet that no one has confirmed the user wants.
- The cost of building the anchor feature is high (L/XL) and the value assumption is just intuition.
- A new business assumption appeared ("the customer will pay for this", "this channel drives traffic") that the plan relies on.
Use /renata:assumption-test for value/viability risk (before building).
Use /renata:spike for technical risk ("does it run?").
Use /renata:hypothesis-check to measure the hypothesis (after building).
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.
- 5d ago First seen · 118 lines · 24 tokens per session scan A 4f7dad12c224
assumption-test is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 14d ago), licensed MIT. It adds 24 tokens to every session and 1,726 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.
Other commands, from other repositories
issue-closeout
Triage Codex findings via per-finding dispositions, mark findingstriaged, close the active issue.
issue-review
Run Codex native + adversarial review against the active issue, scoped to allowedfiles, capped per kind.
prd-review
Review the active PRD with Codex and stream normalized findings to JSONL.
prd-triage
Triage pending findings on the active PRD.
prd-archive
Archive the active PRD (terminal state).
issue-start
Load a DSSE issue spec and begin structured work.