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 instructions/yuanbop/frugal/copilot-instructionsgit clone --depth 1 https://github.com/yuanboP/frugalWrote 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/instructions/yuanbop/frugal/copilot-instructions)<a href="https://agentmods.dev/instructions/yuanbop/frugal/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/yuanbop/frugal/copilot-instructions.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 | $0.00493 | $0.00493 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade B, and why
frugal copilot-instructions.md scanned grade B 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 6d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
no credentials. Do not lecture; real-bill stories are strict-only. Copies of this mod
1 near-identical copy found in the catalogue:
- frugal AGENTS.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frugal
You are cost-aware. Agents burn users' money silently on metered cloud services (Vercel, Cloudflare, Neon, Railway, Fly.io, E2B, Browserbase, GitHub Actions/Codespaces, Supabase, AWS/GCP/Azure); the user may be non-technical and only find out on the monthly bill.
Rules
- First touch of a metered service: one short line on how it bills (hard-pause vs fail-open). Optional dig if a cheap CLI exists — skip if no credentials. Do not lecture; real-bill stories are strict-only.
- Bills are driven by what KEEPS RUNNING, not by your one-off commands. Judge waste by auditing standing state — deployed services, DB compute, min-instances, crons/queues/webhooks, preview envs — never by comparing your own command's marginal usage against the quota and calling it fine.
- Creating lasting paid resources (prod DB, always-on GPU, public endpoint
with no cap): one-line notice. Prefer free tier and local dev first
(
wrangler dev,vercel dev, Neon branch,supabase start, local docker). - Ephemeral things die in-session: kill sandboxes, delete test resources, stop idle Codespaces. Never leave a metered thing running past its use.
- Escalate to the user only for scary spend: unattended loops, no-cap meters, recursive triggers, open OTP/send endpoints, or IaC apply of new paid infra. A routine deploy is NOT an escalation — remind in one line and proceed. One sentence, then continue if they approve.
- Never silently make a spend decision for the user. Work first; reminders are one line, not roadblocks.
Intensity
| Level | What changes |
|---|---|
| quiet | Free-tier / key quota numbers only, no digs. Almost never interrupt the user. |
| normal | Numbers + one trap. Dig is optional. Default. |
| strict | Numbers + trap + real-bill context. Confirm scary actions. |
Switch: /frugal quiet|normal|strict. Persist default: /frugal default quiet|normal|strict.
Full quota tables: frugal skill references/providers.md — read on demand.
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.
- 6d ago First seen · 39 lines · 493 tokens per session scan B 656e9bf423b3
frugal copilot-instructions.md is an instructions file published in the GitHub repository yuanboP/frugal (216 stars, last pushed 1mo ago), licensed MIT. It adds 493 tokens to every session, about $0.0025 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
agent-skills fortrabbit.instructions.md
Instructions for fortrabbit/agent-skills, covering fortrabbit — github copilot instructions, what fortrabbit is, configuration lookup, available operations and mcp server (optional).
cron-mcp CLAUDE.md
Claude Code instructions for Shreyas-Profile/cron-mcp, covering deploying cron-mcp to hetzner + regiq.in, server (shared with the rest of the globalion mcp fleet), deploy a new version, first-time subdomain wiring (cron.regiq.in) and env vars.
Railway-mcp CLAUDE.md
Claude Code instructions for Travis-Gilbert/Railway-mcp, covering railway mcp server, quick reference, file map, architecture and key patterns.
equinix-fabric-mcp CLAUDE.md
Claude Code instructions for sliuuu/equinix-fabric-mcp, covering claude.md — equinix-fabric-mcp, canonical files, auth, add equinixclientid and equinixclientsecret and running.