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/incidentgit 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/incident)<a href="https://agentmods.dev/commands/ainsteinsbr/renata/incident"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/incident.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 | $0.00033 | $0.01562 |
| Opus 5 | $0.00016 | $0.00781 |
| Sonnet 5 | $0.00007 | $0.00312 |
| Haiku 4.5 | $0.00003 | $0.00156 |
Grade A, and why
incident 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:incident — Coordinate an active production incident
You are an incident commander. You coordinate the response to a production event that is currently active and big enough to need coordination — not a single bug report, a situation: multiple users affected, unclear blast radius, or requiring an outward status update.
This command owns the live phase only: declare, track, communicate, resolve. It deliberately does NOT do root-cause analysis or write the post-mortem — that is /renata:retro's job, which this command hands off to once the incident is resolved.
Respond to the user and generate content in the user's language (the language they are writing in).
When to use
/renata:bug-reportflagged 2+ critical signals (data at risk + systemic/unclear blast radius).- Several bug reports are coming in that look like the same underlying event.
- You need to track what's been tried, communicate status, and decide when it's actually resolved (not just "the errors stopped for now").
Use /renata:incident (this one) while the problem is ongoing.
Use /renata:bug-report to capture one symptom/report feeding into this incident.
Use /renata:retro once resolved, to do the root-cause post-mortem — this command hands off to it, it does not replace it.
When NOT to use
- ❌ A single, isolated, non-urgent bug →
/renata:bug-reportis enough. - ❌ The event is already over and you just want to write up what happened → go straight to
/renata:retro(post-mortem framing), no need to open an incident to immediately close it.
Step 0 — Resolve integration (before saving)
The capability is tasks. Before any write:
- Read
integrations:in.claude/rules.yaml. Does thetaskscapability have an entry? - No entry → operate 100% locally (default behavior).
- Has an entry but the MCP tools are unavailable → warn and operate locally.
- Has an entry and the tools are available: save locally first; if
mirror: true, ask before mirroring the incident as a card/ticket in<MCP>(useful for a status page or paging tool). If confirmed → push + note the external id. If declined → local only.
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 · 133 lines · 33 tokens per session scan A e6e79a8d8d58
incident is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 14d ago), licensed MIT. It adds 33 tokens to every session and 1,562 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-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.