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/rshade/finfocus/copilot-instructionsgit clone --depth 1 https://github.com/rshade/finfocusWhat 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 | $0.02105 | $0.02105 |
| Opus 5 | $0.01052 | $0.01052 |
| Sonnet 5 | $0.00421 | $0.00421 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
finfocus copilot-instructions.md 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FinFocus Development Instructions
FinFocus is a CLI tool for calculating cloud infrastructure costs from Pulumi infrastructure definitions. It uses a plugin-based architecture to query multiple cost data sources via gRPC.
Build, Test, and Lint Commands
make build # Build binary to bin/finfocus
make build-all # Build binary + all plugins (recorder, Pulumi tool)
make clean # Remove build artifacts
make test # Run unit tests (fast, default)
go test ./internal/cli/... # Test specific package
go test -run TestName ./... # Run single test by name
go test -v -run TestName ./internal/engine/... # Single test in one package
make test-race # Run with race detector
make test-integration # Integration tests (slower)
make test-e2e # E2E tests (requires AWS credentials)
make lint # golangci-lint v2.9.0 + markdownlint + actionlint
make validate # go mod tidy -diff + go vet
make docs-lint # Lint documentation only
go test -coverprofile=coverage.out ./... # Coverage report
go tool cover -html=coverage.out
Always run make lint and make test before committing.
Architecture
Pulumi JSON → Ingestion → Resource Descriptors → Router → Engine → Plugins (gRPC) / Specs (YAML) → Output
Dual-Mode Binary
The finfocus binary runs as both a standalone CLI and a Pulumi tool plugin. Mode is detected via binary name (pulumi-tool-finfocus) or FINFOCUS_PLUGIN_MODE=true. This changes the Use string and examples but shares all subcommands.
Core Components
- CLI (
internal/cli/) — Cobra commands:overview,cost projected|actual|recommendations|budget|estimate,plugin *,config *,analyzer serve - Engine (
internal/engine/) — Orchestrates cost calculation. Tries plugins first, falls back to local YAML specs inspecs/. UseshoursPerMonth = 730. Supports table, JSON, NDJSON output. Includes batch processing (threshold: 100 resources), caching, and budget forecasting. - Router (
internal/router/) — Routes resource types to the correct plugin based on provider patterns, priority rules, and config-driven routing from~/.finfocus/config.yaml. - Proto Adapter (
internal/proto/) — Bridge between engine and plugins. ConvertsResourceDescriptorto protobuf requests, performs pre-flight validation viapluginsdk, extracts SKU/Region from resourceInputs, and aggregates errors withCostResultWithErrors. - Plugin Host (
internal/pluginhost/) — gRPC plugin lifecycle.ProcessLauncher(TCP) andStdioLauncher(stdin/stdout). 10-second timeout, 100ms retry. Always callcmd.Wait()afterKill()to prevent zombies. - Registry (
internal/registry/) — Discovers plugins at~/.finfocus/plugins/<name>/<version>/. Optionalplugin.manifest.jsonvalidation. - Ingestion (
internal/ingest/) — Parsespulumi preview --json. Must inspectnewStateto extractInputs— without this, property extraction fails and plugins returnInvalidArgument. - Analyzer (
internal/analyzer/) — Implementspulumirpc.AnalyzerServerfor zero-click cost estimation duringpulumi preview. Prints ONLY port number to stdout (Pulumi handshake). All logs go to stderr. ADVISORY enforcement only. - Config (
internal/config/) — Manages~/.finfocus/config.yamlincluding plugin routing rules, budget definitions, and dismissed recommendation state (~/.finfocus/dismissed.json). - TUI (
internal/tui/) — Bubble Tea + Lip Gloss with adaptive color schemes.
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 · 168 lines · 2,105 tokens per session scan A 50834e9efcea
finfocus copilot-instructions.md is an instructions file published in the GitHub repository rshade/finfocus (5 stars, last pushed 16d ago), licensed Apache-2.0. It adds 2,105 tokens to every session, about $0.0105 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 instructions, from other repositories
costory-finops-mcp-skills AGENTS.md
AGENTS.md instructions for costory-io/costory-finops-mcp-skills, covering agents.md — conventions for ai coding agents in this repo, layout, skill id mapping (costory mcp), when changing a skill and when adding a new skill.
ai-pricing-hub-mcp CLAUDE.md
Claude Code instructions for OptimNow/ai-pricing-hub-mcp, covering claude.md - ai pricing hub mcp app, what this project does, architecture, data sources and the fallback chain and project structure.
ai-pricing-hub-mcp AGENTS.md
AGENTS.md instructions for OptimNow/ai-pricing-hub-mcp: Before writing code, first explore the project structure, then invoke the chatgpt-app-builder skill for documentation.
insideout-power AGENTS.md
Instructions for luthersystems/insideout-power, covering insideout — riley infrastructure agent, what riley can do for you, how to invoke riley, via remote mcp (preferred — use this first) and via agent skills.
cloud-mcp-server CLAUDE.md
Claude Code instructions for alexei-led/cloud-mcp-server, covering aws mcp server development guide, build & test commands, architecture, server (server.py) and sandbox (sandbox.py).
langchain-aws AGENTS.md
Instructions for langchain-ai/langchain-aws, covering global development guidelines for the langchain monorepo, project architecture and context, langchain-aws structure, key components and langgraph-checkpoint-aws structure.