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 skills/jeremydev87/codingbuddy/incident-responsenpx skills add JeremyDev87/codingbuddy --skill incident-responsegit clone --depth 1 https://github.com/JeremyDev87/codingbuddyWhat 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 | $0.00029 | $0.02961 |
| Opus 5 | $0.00015 | $0.01481 |
| Sonnet 5 | $0.00006 | $0.00592 |
| Haiku 4.5 | $0.00003 | $0.00296 |
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 2d 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Response
Overview
Incidents demand disciplined response, not heroic fixes. Rushed patches mask problems and create new ones.
Core principle: ALWAYS triage, communicate, and contain before attempting fixes. Technical investigation follows organizational response.
Violating the letter of this process is violating the spirit of incident response.
First 5 Minutes Checklist
Use this when alerts fire. Don't think, follow the list.
| Minute | Action | Output |
|---|---|---|
| 0-1 | Acknowledge alert | incident_acknowledged |
| 1-2 | Screenshot dashboards NOW | Evidence preserved |
| 2-3 | Assess: >50% users? Critical function? | Severity (P1-P4) |
| 3-4 | Post in incident channel: severity + impact + trace_id | stakeholders_notified |
| 4-5 | If P1/P2: Open war room, page on-call | Responders engaged |
After 5 minutes: Proceed to Phase 4 (Mitigate) - you've completed Detect, Triage, Communicate.
The Iron Law
NO FIXES WITHOUT TRIAGE AND COMMUNICATION FIRST
If you haven't classified severity and notified stakeholders, you cannot propose fixes.
When to Use
Use for ANY production incident:
- Alerts firing (P1-P4)
- Customer reports of issues
- Monitoring anomalies
- Service degradation
- Security incidents
- Data integrity concerns
Use this ESPECIALLY when:
- Under time pressure (emergencies make shortcuts tempting)
- Multiple systems failing (panic causes scattered responses)
- "Just fix it" pressure from stakeholders
- You don't fully understand the scope yet
- Previous fix attempt didn't work
Don't skip when:
- Issue seems simple (simple incidents have complex causes too)
- You're in a hurry (systematic response is faster than thrashing)
- Management wants it fixed NOW (protocol prevents extended outages)
When NOT to Use
This skill is for organizational incident response. Don't use it for:
- Local development issues - Your build failing isn't an incident
- Non-production environments - Staging bugs use normal debugging
- Planned maintenance - Scheduled changes have different protocols
- Feature bugs with no urgency - Normal backlog items, not incidents
- Performance optimization - Use systematic-debugging for investigation
- One-off user reports - Investigate first; escalate to incident if widespread
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 375 lines · 29 tokens per session scan A 5abbff38ec1a
incident-response is a skill published in the GitHub repository JeremyDev87/codingbuddy (31 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 2,961 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 2026-08-30.
Other skills, from other repositories
bzdesignprompt
为前端或网页设计任务选择并下载合适的 DESIGN.md 模板。当用户需要网页设计模板、UI 风格参考、设计系统、落地页或前端界面设计时，浏览长亭百智云 UI 设计模板库，根据产品场景和视觉偏好匹配模板，并将完整 DESIGN.md 保存到项目中。.
add-agent-property
Add a new property to the AI agents database. Use when the user wants to add, create, or introduce a new column, property, field, or feature to track across all agents in the comparison matrix. Handles all four required steps - database updates, groups.json, table display, and GitHub issue templates.
ai-agent-rules
This skill covers development patterns for the ai-agent-rules repository, a comprehensive collection of structured rules and guidelines for AI agent behavior. The repository focuses on maintaining consistent documentation standards, systematic rule organization, and automated synchronization workflows. It uses…
se-dev-server-code
Allows reading the decompiled C# code of the Space Engineers Dedicated Server.
se-dev-game-code
Allows reading the decompiled C# code of Space Engineers version 1.
se-dev-plugin
Plugin development for Space Engineers version 1. Search plugin code from PluginHub (client) and MagnetarHub (server) for examples and patterns.