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 arjunprabhulal/devops-skills --skill toil-reductiongit clone --depth 1 https://github.com/arjunprabhulal/devops-skillsWrote 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/arjunprabhulal/devops-skills/toil-reduction)<a href="https://agentmods.dev/skills/arjunprabhulal/devops-skills/toil-reduction"><img src="https://agentmods.dev/badge/skills/arjunprabhulal/devops-skills/toil-reduction.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.01290 |
| Opus 5 | $0.00056 | $0.00645 |
| Sonnet 5 | $0.00022 | $0.00258 |
| Haiku 4.5 | $0.00011 | $0.00129 |
Grade A, and why
toil-reduction 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 7d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toil Reduction
Toil is work that's manual, repetitive, automatable, tactical, and scales linearly with growth — and it's dangerous precisely because each instance feels small. Nobody schedules a project called "toil"; it accumulates one "just do it by hand this once" at a time until an engineer's week is gone before they've built anything.
The fix isn't a blanket instinct to automate everything — some repeated work is judgment, not toil, and automating it badly just moves the risk somewhere less visible. Toil reduction starts with measuring honestly what's actually eating time, not with automating whatever's most annoying today.
1. Measure toil before you fight it
Teams that "know" what's eating their time are usually wrong about the proportion, if not the source — the loud, annoying task isn't always the biggest time sink; the quiet one done fifty times a week often is. Without a number, every automation decision is a guess dressed up as priority.
- Track time spent per recurring task category, even roughly, for a few weeks before deciding what to fix first.
- Count frequency, not just duration — a five-minute task done twenty times a day outweighs an hour-long task done monthly.
- Re-measure after automating — confirm the toil actually dropped instead of assuming the fix worked because it shipped.
Done when: you can name the top three toil sources by measured time, not by whoever complained most recently.
2. Automate the repetitive, not the judgment
Not every recurring task is toil. A task that requires a human to weigh context, make a call, or handle a genuinely novel situation each time is engineering work that happens to repeat, and forcing it into automation either fails on the first edge case or quietly removes judgment that was load-bearing.
- Toil: the steps are the same every time, and a checklist or script fully covers it.
- Not toil: the steps depend on context that changes the right answer each time.
- When unsure, automate the mechanical parts and leave the decision to a human — a script that gathers the evidence for a judgment call still eliminates real toil without removing the call.
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.
- 7d ago First seen · 108 lines · 111 tokens per session scan A 136a1b771706
toil-reduction is a skill published in the GitHub repository arjunprabhulal/devops-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 111 tokens to every session and 1,290 once invoked, about $0.0006 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
gke-alert-configuration
Configures alerting policies in Terraform for Google Kubernetes Engine (GKE) clusters, workloads, and services using PromQL and Google Cloud Managed Service for Prometheus. Use when writing, analyzing, validating, or deploying Terraform alerting policies to monitor GKE service latency, traffic, error rates using…
cloud-run-basics
Manages Cloud Run services, jobs, and worker pools. Use when you need to deploy applications responding to HTTP requests (services), run event-triggered or scheduled tasks (jobs), or handle always-on pull-based background processing (worker pools).
iam-helper-for-privileged-access-management
Manages the end-to-end lifecycle of on-demand, temporary access using Privileged Access Manager (PAM). Use when a user asks to create, read, update, or delete PAM entitlements, request temporary access, or approve/deny pending PAM grants. Do NOT use for permanent IAM policy bindings, troubleshooting IAM permission…
google-analytics-data-api-basics
Manages Google Analytics reporting data, enables the Analytics Data API via the Cloud CLI, and creates reports using the Google Analytics Data API (v1beta). Use when you need to interact with Google Analytics properties, run customized analytics reports, query metrics (like activeUsers, screenPageViews) and dimensions…
developer-device-platform-basics
Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.
google-cloud-slo-alert-configuration
Configures PromQL-based Service Level Objective (SLO) alerting policies for Google Cloud resources registered in App Hub or individually specified. Generates Terraform output. Use when the user asks to configure an SLO or Service Level Objective. Don't use for standard alerting policies.