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 skills add jeffreytse/grimoire-core --skill design-incident-responsegit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/skills/jeffreytse/grimoire-core/design-incident-response)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/design-incident-response"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-incident-response/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/design-incident-response"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-incident-response.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00021 | $0.00971 |
| Opus 5 | $0.00010 | $0.00485 |
| Sonnet 5 | $0.00004 | $0.00194 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
design-incident-response 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 7d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Incident Response
Build a structured incident response process that minimizes customer impact, coordinates responders, and prevents recurrence.
Why This Is Best Practice
Adopted by: Google SRE, PagerDuty, Atlassian, AWS, and organizations following NIST SP 800-61 as the federal standard for incident handling Impact: Organizations with a documented incident response process resolve incidents 28% faster and have 50% lower repeat-incident rates than those without (PagerDuty State of Digital Operations, 2022)
Why best: Without a defined process, incidents devolve into heroics — one person firefighting while everyone else watches. A defined incident command structure, clear roles, and a blameless postmortem loop convert incidents into organizational learning.
Steps
- Define severity levels — Create 3–4 tiers (SEV1–SEV3 or P0–P3) with explicit, measurable criteria: "SEV1 = customer-facing service unavailable for >1% of users or data loss." Avoid vague language like "significant impact."
- Assign incident command roles — Incident Commander (IC): owns the incident and decisions. Communications Lead: updates stakeholders. Subject Matter Experts (SMEs): do the technical work. No one plays two roles during a SEV1.
- Create the alert-to-acknowledge SLA — Define time limits per severity: SEV1 = 5 min page, 15 min acknowledge; SEV2 = 30 min. Document escalation path if the primary on-call does not respond.
- Build the incident channel template — On-call tooling should auto-create a dedicated channel with: severity, incident summary, IC assigned, customer impact, and links to runbooks. Standardize the format so responders orient instantly.
- Define the update cadence — SEV1: status update every 15 minutes to stakeholders. SEV2: every 30 minutes. Updates follow the format: Current state / Actions taken / Next action / ETA. No open-ended updates.
- Conduct blameless postmortem within 48 hours — Document timeline, contributing factors (no "root cause" — systems have multiple causes), and action items with owners and due dates. Publish internally.
- Track postmortem action items — Assign each item to a team with a sprint commitment. Review completion in the next postmortem. Untracked items repeat the incident.
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.
- 7d ago First seen · 53 lines · 21 tokens per session scan A 9427e097e477
design-incident-response is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 22d ago), licensed MIT. It adds 21 tokens to every session and 971 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 2026-09-03.
Other skills, from other repositories
sre-runbooks
Safe-by-default DevOps/SRE runbook automation for incident response, postmortems, on-call handovers, and operational troubleshooting. Implements Google SRE principles with agent-safe execution patterns including dry-run modes, human approval gates, and blast-radius limits.
k8s-incident-triage
Read-only Kubernetes incident triage using kubectl. Accepts natural language or structured input. Produces root-cause hypotheses, evidence, and next-step commands.
performance-profiling
CPU, memory, network bottleneck analysis — systematic performance investigation.
power-bi-performance-troubleshooting
Systematic Power BI performance troubleshooting prompt for identifying, diagnosing, and resolving performance issues in Power BI models, reports, and queries.
refactor
Systematic code refactoring to improve maintainability without changing behavior. Use when asked to "refactor this", "clean up this code", "improve code quality", "simplify this", "reduce complexity", or "eliminate code smells". Always preserves existing behavior.
extension-audit-methodology
Systematic 5-dimension audit framework for VS Code extensions — debug hygiene, dead code, performance, menu validation, dependency cleanup.