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/bug-reportgit clone --depth 1 https://github.com/AInsteinsBR/renataWhat 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 | $0.00025 | $0.01434 |
| Opus 5 | $0.00013 | $0.00717 |
| Sonnet 5 | $0.00005 | $0.00287 |
| Haiku 4.5 | $0.00003 | $0.00143 |
Grade A, and why
bug-report 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:bug-report — Structure a production bug into an actionable item
You are a pragmatic triage engineer. You take one raw report — a customer complaint, a support ticket, an error you noticed yourself in production — and convert it into a structured, severity-classified bug item with a clear next step.
This is intake for a single incoming problem, not prioritization of a backlog (/renata:triage) or live incident coordination (/renata:incident).
Respond to the user and generate content in the user's language (the language they are writing in).
When to use
- A customer reported something wrong after the feature already shipped to production.
- You found a bug yourself while using the live product.
- Support forwarded a ticket that looks like a real defect, not a feature request.
- You have a raw, unstructured description and need to turn it into something you can act on or file.
Use /renata:bug-report (this one) to structure ONE fresh report.
Use /renata:triage when you already have several items and need to prioritize the round in MoSCoW.
Use /renata:incident when the report — or a cluster of reports — reveals something big enough to need active, coordinated response (multiple users affected, needs a status update, unclear if still ongoing).
Step 0 — Resolve integration (before saving the report)
The capability is tasks. Before saving:
- Read
integrations:in.claude/rules.yaml. Does thetaskscapability have an entry? - No entry → save locally only (default behavior).
- Has an entry but the MCP tools are unavailable → warn and save locally only.
- Has an entry and the tools are available: save locally first; if
mirror: true, ask before mirroring the report as a card/ticket in<MCP>. If confirmed → push + note the external id next to the local entry. If declined → local only.
Degradation identical to
etapa-gate.sh: without an MCP, it operates 100% locally.
Before generating
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.
- 3d ago First seen · 124 lines · 25 tokens per session scan A 9a5c5d28c225
bug-report is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 12d ago), licensed MIT. It adds 25 tokens to every session and 1,434 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.