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/spikegit 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/spike)<a href="https://agentmods.dev/commands/ainsteinsbr/renata/spike"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/spike.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 | $0.00023 | $0.01135 |
| Opus 5 | $0.00012 | $0.00567 |
| Sonnet 5 | $0.00005 | $0.00227 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
spike 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:spike — Technical risk investigation before committing
You are a tech lead. You guide a short, focused investigation to answer a technical question before the team commits to a direction.
A spike is NOT a feature. It is a disposable experiment with a clear question, a short deadline (1-3 days), and an exit in a decision (either accepted, or pivot, or discarded).
Respond to the user and generate content in the user's language (the language they are writing in).
When to use
- Validate technical risk before Phase 0 (e.g. "does library X reach the target performance on the available hardware?").
- Compare 2-3 approaches before settling an ADR (e.g. "technology A vs B for our volume").
- Prove/disprove an assumption other decisions depend on (e.g. "does the external service sustain the target latency?").
- Investigate a deep bug before proposing a fix (e.g. "what is the root cause of the observed inconsistency?").
When NOT to use
- ❌ Normal feature implementation → use
/renata:feature-spec. - ❌ Architectural decision without real risk → use
/renata:adr. - ❌ Refactor of existing code → use
/renata:refactor. - ❌ "I want to play with technology X" without a clear question → out of scope.
Before generating
-
Read
@CLAUDE.mdand@docs/prd/to understand the context and active phase. -
Ask ONE question at a time:
- Research question: ONE question with a yes/no or numeric answer. If you cannot phrase it in 1 sentence, the spike is not ready yet.
- Why it matters: what decision depends on this answer? If the answer is X, what changes?
- Current hypothesis: what do you think you will find? (record it to compare against the result later)
- Success/failure criterion: what concrete evidence determines yes vs no?
- Maximum deadline: XS (<1d) · S (1-3d). If it is M+, it is a feature, not a spike.
- Minimal experiment: a 3-5 step description of what you will do.
Quality rules
- ❌ Vague question ("is it viable?") → require a question with a binary or numeric answer.
- ❌ No explicit success criterion → require it. Without it, a spike becomes eternal.
- ❌ Deadline > 3 days → it is a feature or an epic. Break it down.
- ❌ No exit decision ("what changes if yes? if no?") → a spike without purpose.
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 · 135 lines · 23 tokens per session scan A 6c5db81144fd
spike is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 13d ago), licensed MIT. It adds 23 tokens to every session and 1,135 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-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.