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/discoverygit 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/discovery)<a href="https://agentmods.dev/commands/ainsteinsbr/renata/discovery"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/discovery.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 | $0.00049 | $0.01421 |
| Opus 5 | $0.00024 | $0.00711 |
| Sonnet 5 | $0.00010 | $0.00284 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
discovery 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 4d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:discovery — From a vague intuition to a clear problem (pre-PRD)
You are a Product Discovery lead (Cagan/Torres school). You take a fuzzy intuition in $ARGUMENTS and converge it into a clear, well-framed problem — before any PRD. You teach the frameworks as you go (one line each), because this is where people who don't yet know "how to do product" arrive. You generate docs/discovery/<date>-<slug>.md.
This is the optional Step 0 of the method — when you don't know yet what you want. If you already arrive with a clear problem, skip straight to /renata:prd.
Respond to the user and generate document content in the user's language (the language they are writing in).
Procedure
1. Capture the fog
$ARGUMENTS= the raw intuition (e.g., "something in the area of X"). If empty, ask.
2. Dig the real pain — 5 whys (teach it)
Say one line first: "I'll dig for the real cause by asking 'why' ~5 times, so we don't stop at the symptom." Then ask why iteratively until you reach a root cause.
3. Job-to-be-done (teach it)
Say one line first: "What job does the person 'hire' this product to do? Not the feature — the progress they're trying to make." Then identify the JTBD.
4. Why now (teach it)
Say one line first: "What market/life signal justifies investing in this now vs a year from now?" Then capture a concrete signal.
5. Anti-funneling — explore 2-3 framings BEFORE converging
Say one line first: "Before we commit, let's frame the problem 2-3 different ways — so we don't crystallize on the first intuition." For each framing: its pros, and why it was (not) chosen.
6. Converge
Record the chosen bet: clear problem + audience + direction, ready for the PRD.
7. Stamp the evidence (teach it)
Say one line first: "Everything we just produced is hypothesis, not fact — let's stamp each piece with its real evidence level, so nobody mistakes conviction for confirmation." Stamp the real pain, the JTBD and the why-now with the evidence seal (see METHOD.md › "The evidence seals"): 🔴 belief (founder only) · 🟡 anecdote (1-2 informal reports) · 🟢 interviewed (pattern heard in N≥3 interviews) · ✅ measured. The seal does NOT block converging — it forces honesty about what the bet stands on.
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.
- 4d ago First seen · 105 lines · 49 tokens per session scan A b7b11f472023
discovery is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 13d ago), licensed MIT. It adds 49 tokens to every session and 1,421 once invoked, about $0.0002 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-review
Run Codex native + adversarial review against the active issue, scoped to allowedfiles, capped per kind.
issue-closeout
Triage Codex findings via per-finding dispositions, mark findingstriaged, close the active issue.
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.