prd-v08-runbook-creation

prd-v08-runbook-creation is a skill for Claude Code from mattgierhart/PRD-driven-context-engineering. It costs 87 tokens per session (4,331 once invoked), scanned A, original, MIT.

A set of operational playbooks for handling incidents, deployments, and routine maintenance. A runbook is a step-by-step guide that tells the team what to do during a specific operational situation.

In plain words
What is it for?
Use it to write incident-response guides, deployment and recovery procedures, maintenance instructions, escalation paths, and practice drills.
Why use it?
It gives on-call staff a documented response instead of requiring them to work out procedures during an incident. It also links important risks, alerts, deployments, and escalation paths to concrete actions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/notify-deploy.sh --env production --version v${VERSION} --channel #deployments.

Good fit Use it to write incident-response guides, deployment and recovery procedures, maintenance instructions, escalation paths, and practice drills.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering
agentmods
npx agentmods add skills/mattgierhart/prd-driven-context-engineering/prd-v08-runbook-creation

Made for: Claude Code.

Wrote 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.

agentmods badge for prd-v08-runbook-creation

README.md
[![agentmods](https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v08-runbook-creation/github.svg)](https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v08-runbook-creation)
Your own site
<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v08-runbook-creation"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v08-runbook-creation/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.

agentmods 80×15 button for prd-v08-runbook-creation

Your own site · 80×15
<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v08-runbook-creation"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v08-runbook-creation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,331 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 196
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 209
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Excessive Agency · line 523
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 523
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 489
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.04331
Opus 5 $0.00044 $0.02166
Sonnet 5 $0.00017 $0.00866
Haiku 4.5 $0.00009 $0.00433

Measured 10d ago against content hash df0a4cc14bd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prd-v08-runbook-creation scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- [ ] New version visible: curl https://api.prod.example.com/health | jq .version
.claude/skills/prd-v08-runbook-creation/SKILL.md · 552 lines

How it starts

The opening of the file, as written. The whole thing — 552 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Runbook Creation

Position in workflow: v0.8 Release Planning → v0.8 Runbook Creation → v0.8 Monitoring Setup

Execution Mode

Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.

Mode What this skill produces
quick 2–3 runbooks covering the top RISK-/MON- pairs
standard Incident + deployment + maintenance runbooks linked to MON- and DEP-, with escalation paths
deep Full matrix + drill schedule + recovery scenarios + tabletop exercise outputs

Consumes

This skill requires prior work from v0.8 Release Planning and earlier stages:

  • DEP-* deployment entries (from v0.8 Release Planning) — Deployment procedures from DEP- rollback/validation sections inform RUN- deployment and recovery runbooks
  • RISK-* risk entries (from v0.5 Risk Discovery) — High/medium RISK- entries must have response runbooks; mitigations become procedures
  • MON-* monitoring specifications (planned from v0.8 Monitoring Setup, or anticipated) — Key alerts from MON- (before formalization) inform incident response runbooks; runbooks will be referenced FROM monitoring
  • ARC-* architecture decisions (from v0.6 Architecture Design) — System structure (single service vs microservices, databases, integrations) determines incident scope and escalation paths
  • TECH-* technology stack (from v0.5 Technical Stack Selection) — Technology choices (database, cloud provider, APM tools) determine specific commands and tools in runbook procedures
  • API-* endpoint contracts (from v0.6 Technical Specification) — For reference if incident involves specific endpoints or payloads

This skill assumes DEP- entries are complete with rollback procedures and post-deploy validation steps defined.

Produces

This skill creates/updates:

  • RUN-* entries (operational runbooks, category-based) — Step-by-step procedures for incident response, deployment execution, maintenance tasks, recovery from failures, and escalation paths
  • Incident response matrix — Mapping of scenarios (connection pool exhaustion, latency spike, deployment failure, etc.) to RUN- procedures
  • Runbook cross-reference — Links from RUN- procedures to DEP- rollback conditions, anticipated MON- alerts, and RISK- entries they address

Read the full file on GitHub · 552 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 552 lines · 87 tokens per session scan A df0a4cc14bd4

Subscribe to this mod's changes

prd-v08-runbook-creation is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 9d ago), licensed MIT. It adds 87 tokens to every session and 4,331 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.