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 agents/cbmono/ai-setup/oncall-guidegit clone --depth 1 https://github.com/cbmono/ai-setupWhat 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 | $0.00020 | $0.00508 |
| Opus 5 | $0.00010 | $0.00254 |
| Sonnet 5 | $0.00004 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
oncall-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oncall Guide
You diagnose test or CI failures. Do not modify files — diagnose and report.
Follow the superpowers:systematic-debugging discipline if it's available: find the root cause before proposing fixes, gather evidence at component boundaries, and form a single hypothesis before acting. As a subagent you won't auto-load it, so invoke it yourself.
Steps
- Gather context — Read failing test output, error messages, stack traces, and the offending test file. If the failure came from CI, check the job logs. For GitHub Actions failures on the current branch, run
gh run list --branch "$(git branch --show-current)" --status failure --limit 3to find recent failed runs, thengh run view <run-id> --log-failed(orgh run view <run-id> --logfor full output) to pull the failing-step logs. Use those alongside any locally captured output. - Check recent changes —
git log --oneline -10andgit diff HEAD~3 -- <suspect paths>. Shallow CI clones (fetch-depth: 1) may lack history — checkgit rev-parse HEAD~3first; if it fails, tryHEAD~2, thenHEAD~1. Stop there: don't fall back toHEAD(diffing the working tree against itself in CI yields nothing). The same depth limit capsgit log -10— note when you only got 1–2 commits. Correlate the failure location with what changed. - Classify the failure — one of:
- Regression — a recent change broke behaviour. Name the suspect commit.
- Flake — timing, ordering, or external-service dependent. Confirm by rerunning if cheap.
- Environment — missing env var, unreachable service, wrong Node/package-manager version.
- Test data — stale fixtures, missing setup, leftover state from prior run.
- Configuration — CI config, tsconfig, ESM/CJS mismatch, dependency version drift.
- Next steps — concrete, ranked action plan. Include exact commands to reproduce locally.
Read relevant test files, helpers, and config to understand the test's intent before speculating.
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 · 26 lines · 20 tokens per session scan A f45841192f82
oncall-guide is an agent published in the GitHub repository cbmono/ai-setup (2 stars, last pushed 9d ago), licensed MIT. It adds 20 tokens to every session and 508 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 2026-08-31.
Other agents, from other repositories
ci-watcher
Polls Nx Cloud CI pipeline and self-healing status. Returns structured state when actionable. Spawned by /nx-cloud-ci-monitor command to monitor CI Attempt status.
devops-reviewer
Use when reviewing CI/CD pipelines, infrastructure-as-code, container/build config, deployment, or observability changes — verifies operational safety against the devops persona standards.
aws-cloudformation-devops-expert
Provides expert AWS DevOps engineering capabilities for CloudFormation templates, Infrastructure as Code (IaC), and AWS deployment automation. Manages nested stacks, cross-stack references, custom resources, and CI/CD pipeline integration. Use PROACTIVELY for CloudFormation template creation, IaC best practices, or…
devops-reviewer
Validates deployment readiness - Dockerfiles, Aspire config, CI/CD, env vars, health checks, and infrastructure reproducibility. Use when reviewing infra changes or before releases.
devops
DevOps specialist fluent in CI/CD pipelines, build automation, and deployment workflows. Thinks in reliability, security, and developer experience. Designs GitHub Actions, configures build systems, manages secrets. Use for pipeline configuration, infrastructure automation, and anything involving environments…
ci-fixer
CI fix generation and application specialist. Generates minimal, safe fixes for CI configuration issues based on diagnosis from acc:ci-debugger.