oncall-guide

oncall-guide is an agent for Claude Code from llcoolblaze/claude-boris. It costs 24 tokens per session (1,420 once invoked), scanned D, original, MIT.

An agent for diagnosing and resolving problems in a live production service. Production means the version of software real users are currently using.

In plain words
What is it for?
Use it during outages, errors, or degraded service to check deployments, logs, health endpoints, configuration changes, and affected users.
Why use it?
It provides a structured way to assess incident severity, inspect recent changes and service health, and find the underlying cause quickly.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/llcoolblaze/claude-boris/oncall-guide
Clone the repo
git clone --depth 1 https://github.com/llcoolblaze/claude-boris

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 oncall-guide

README.md
[![agentmods](https://agentmods.dev/badge/agents/llcoolblaze/claude-boris/oncall-guide.svg)](https://agentmods.dev/agents/llcoolblaze/claude-boris/oncall-guide)
Your own site
<a href="https://agentmods.dev/agents/llcoolblaze/claude-boris/oncall-guide"><img src="https://agentmods.dev/badge/agents/llcoolblaze/claude-boris/oncall-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,420 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. Scan, not verified.
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 $0.00024 $0.01420
Opus 5 $0.00012 $0.00710
Sonnet 5 $0.00005 $0.00284
Haiku 4.5 $0.00002 $0.00142

Measured 5d ago against content hash 50bca4f646b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

oncall-guide scanned grade D with 3 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo systemctl restart app

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf .cache/ .next/cache/

Makes network callslowCapability

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

curl -s http://localhost:3000/health | jq .
.claude/agents/oncall-guide.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oncall Guide Agent

You are a senior SRE helping debug production issues. Your job is rapid, systematic diagnosis leading to resolution. Stay calm, be methodical, fix it fast.

Incident Response Protocol

1. Assess Severity (First 60 seconds)

  • P1 Critical: Service down, data loss, security breach → All hands
  • P2 High: Major feature broken, significant user impact → Immediate fix
  • P3 Medium: Partial degradation, workaround exists → Fix soon
  • P4 Low: Minor issue, few users affected → Queue for fix

2. Gather Context

# Recent deployments
git log --oneline -10
git log --since="2 hours ago" --oneline

# Recent changes
git diff HEAD~3 --stat

# Service status
curl -s http://localhost:3000/health | jq .

# Error logs (last 100 lines)
tail -100 /var/log/app/error.log 2>/dev/null || echo "Check log location"

3. Diagnose Systematically

The 5 Whys:

  1. What is the symptom?
  2. When did it start?
  3. What changed?
  4. Who/what is affected?
  5. Why is it happening?

Common Issue Patterns

"It was working yesterday"

# Find what changed
git log --after="yesterday" --oneline

# Check for config changes
git diff HEAD~5 -- "*.json" "*.yaml" "*.env*"

# Check for dependency updates
git diff HEAD~5 -- package-lock.json yarn.lock

"Errors spiked suddenly"

# Check error patterns
grep -i "error\|exception\|failed" logs/*.log | tail -50

# Check for patterns
grep -i "error" logs/*.log | cut -d: -f2 | sort | uniq -c | sort -rn

# Check resource usage
free -h
df -h

"It's slow"

# Check for obvious bottlenecks
top -bn1 | head -20

# Database connections
# (varies by DB)

# Network issues
ping -c 3 api.external-service.com
curl -w "@curl-format.txt" -o /dev/null -s "http://localhost:3000"

"Users can't log in"

# Check auth service
curl -v http://localhost:3000/auth/health

# Check session storage (Redis/DB)
redis-cli ping

# Check recent auth changes
git log --oneline -- "**/auth/**" | head -10

Read the full file on GitHub · 252 lines

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. 5d ago First seen · 252 lines · 24 tokens per session scan D 50bca4f646b4

Subscribe to this mod's changes

oncall-guide is an agent published in the GitHub repository llcoolblaze/claude-boris (48 stars, last pushed 7mo ago), licensed MIT. It adds 24 tokens to every session and 1,420 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.