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 ashtonian/llm-init --skill incident-responsegit clone --depth 1 https://github.com/ashtonian/llm-initWrote 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/ashtonian/llm-init/incident-response)<a href="https://agentmods.dev/skills/ashtonian/llm-init/incident-response"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/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/ashtonian/llm-init/incident-response"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/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 | $0.00008 | $0.01768 |
| Opus 5 | $0.00004 | $0.00884 |
| Sonnet 5 | $0.00002 | $0.00354 |
| Haiku 4.5 | $0.00001 | $0.00177 |
Grade A, and why
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 8d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Response Skill
Structured workflow for investigating production incidents, identifying root causes, implementing fixes, and writing post-mortems. Speed matters -- follow the steps in order but don't over-analyze before acting.
Workflow
Step 1: Assess Impact
Immediately determine the scope and severity of the incident:
| Question | How to Answer |
|---|---|
| Which tenants are affected? | Check error logs filtered by tenant_id, check monitoring dashboards |
| What functionality is broken? | Check health endpoints, test critical paths, review error types |
| When did it start? | Check deploy timestamps, metric anomaly detection, first error log |
| Is it getting worse? | Check error rate trend over last 15 minutes |
| Is there a workaround? | Assess if affected users can use alternative paths |
Severity Classification:
| Severity | Criteria | Response |
|---|---|---|
| SEV-1 | Service down, data loss, security breach, all tenants affected | All hands, continuous updates every 15 min |
| SEV-2 | Major feature broken, significant tenant subset affected | Dedicated team, updates every 30 min |
| SEV-3 | Minor feature degraded, few tenants affected | Next business day, update on resolution |
| SEV-4 | Cosmetic issue, no functionality impact | Backlog, fix in next sprint |
Output: Impact assessment with severity, affected tenants/features, and timeline.
Step 2: Collect Evidence
Gather all available diagnostic data BEFORE making changes:
Logs:
# Recent error logs (adjust for your logging system)
# Filter by time window, error level, and affected service
Look for:
- Error messages and stack traces
- Request IDs for failing requests
- Tenant IDs of affected users
- Timestamps of first and most recent errors
Metrics:
- Error rate (overall and per-endpoint)
- Latency percentiles (p50, p95, p99)
- Resource utilization (CPU, memory, connections)
- Deployment markers (did a deploy happen before 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.
- 8d ago First seen · 222 lines · 8 tokens per session scan A 3628082ea2b4
incident-response is a skill published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 1,768 once invoked, about $0.0000 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 skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.