finfocus specs.instructions.md

Rules for working with specification files, which describe planned features, requirements, or project decisions outside the main codebase.

In plain words
What is it for?
Use it when consulting feature plans, coordinating work across repositories, or checking project history without treating specs as live code documentation.
Why use it?
They prevent accidental changes to planning documents and remind you that specifications may be outdated or non-authoritative.

Instructions file for GitHub Copilot

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 instructions/rshade/finfocus/specs
Clone the repo
git clone --depth 1 https://github.com/rshade/finfocus

Made for: GitHub Copilot.

Per session 187 This file is loaded in full into every session.
When invoked 187 The same file — it is already loaded in full.
Security scan A 0 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 $0.00187 $0.00187
Opus 5 $0.00093 $0.00093
Sonnet 5 $0.00037 $0.00037
Haiku 4.5 $0.00019 $0.00019

Measured 2d ago against content hash 83f030ee0d6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finfocus specs.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.

.github/instructions/specs.instructions.md · 30 lines

What it actually says

Specs Directory Instructions

This directory contains specification files and feature plans that are not part of the main codebase. These files are primarily for project management and planning purposes.

Guidelines for this directory:

  • Do not modify existing spec files unless explicitly instructed
  • Do not add new spec files without approval
  • Do not reference spec files in code or documentation
  • Do not commit changes to spec files unless they are part of a planned feature implementation

Purpose:

  • Feature planning and requirements gathering
  • Cross-repository coordination
  • Project milestone tracking
  • Historical record of feature decisions

When working with specs:

  • Read-only access for understanding project context
  • Use information from specs to inform code decisions
  • Do not treat specs as authoritative documentation
  • Specs may contain outdated or superseded information
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. 2d ago First seen · 30 lines · 187 tokens per session scan A 83f030ee0d6e

Subscribe to this mod's changes

finfocus specs.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 187 tokens to every session, about $0.0009 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.

Related

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.

costory-io/costory-finops-mcp-skills · 1,611 tokens

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.

OptimNow/ai-pricing-hub-mcp · 7,347 tokens

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.

OptimNow/ai-pricing-hub-mcp · 22 tokens

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.

luthersystems/insideout-power · 1,155 tokens

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).

alexei-led/cloud-mcp-server · 1,114 tokens

devopness AGENTS.md

Instructions for devopness/devopness, covering agents, core flow, shared constraints, monorepo structure and git workflow.

devopness/devopness · 570 tokens