Problem-Based-SRS AGENTS.md

Problem-Based-SRS AGENTS.md is an instructions file for Codex, OpenCode from RafaelGorski/Problem-Based-SRS. It costs 1,108 tokens per session, scanned A, original, MIT.

Repository instructions for Problem-Based Software Requirements Specification, a method for describing the user problem and requirements before deciding on a software solution. It guides AI coding assistants, especially GitHub Copilot and Claude Code, through requirements work.

In plain words
What is it for?
Use it to explore a problem, write or evolve software specifications, design new systems, and plan changes to existing systems.
Why use it?
It helps prevent code being produced before the underlying problem is understood and keeps requirements traceable as an existing system changes.

Instructions file for CodexOpenCode

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/rafaelgorski/problem-based-srs/agents-md
Clone the repo
git clone --depth 1 https://github.com/RafaelGorski/Problem-Based-SRS

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for Problem-Based-SRS AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rafaelgorski/problem-based-srs/agents-md.svg)](https://agentmods.dev/instructions/rafaelgorski/problem-based-srs/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rafaelgorski/problem-based-srs/agents-md"><img src="https://agentmods.dev/badge/instructions/rafaelgorski/problem-based-srs/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,108 This file is loaded in full into every session.
When invoked 1,108 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 $0.01108 $0.01108
Opus 5 $0.00554 $0.00554
Sonnet 5 $0.00222 $0.00222
Haiku 4.5 $0.00111 $0.00111

Measured 4d ago against content hash 4a09cfdc18ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Problem-Based-SRS AGENTS.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 4d 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.

AGENTS.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions for Problem-Based SRS

Project Overview

Problem-Based SRS is a plugin that extends your AI harness to handle Software Specifications. It plugs into GitHub Copilot first — and Claude Code and other AI coding assistants too — turning a general-purpose coding agent into one that can reason about, trace, and evolve requirements instead of only emitting code. On top of the harness it adds three things: AI‑slop prevention tuned to the specific model, a spec language and command palette that steer toward great design, and a rigorous method to evolve existing (brownfield) systems as well as build new ones.

The plugin delivers this through AgentSkills for a Problem-Based Software Requirements Specification (SRS) methodology, enabling AI-assisted requirements engineering through structured, problem-first approaches.

The repository follows the AgentSkills standard and the Claude Code Plugins layout. Compatibility priority is GitHub Copilot first, then Claude Code/Claude.ai.

Core Principles

  1. Problem-First Thinking: Always identify the problem before proposing solutions
  2. Lightweight Methodology: Favor simplicity over complex frameworks
  3. AI-Native Design: Content designed for consumption by AI agents (following AgentSkills standard)
  4. Practical Guidance: Focus on actionable skills and templates

Compatibility Priority (GHCP → Claude)

  • GitHub Copilot first: Keep skills and instructions directly usable in Copilot workflows.
  • Claude second: Keep .claude-plugin/plugin.json, skills/, agents/, and settings.json aligned with Claude plugin docs.
  • Consistency over time: Keep compatibility guidance consistent when it changes.

Repository Structure

Problem-Based-SRS/
├── agents/
│   └── problem-based-srs/       # Agent orchestrator
│       └── AGENT.md
├── skills/
│   └── problem-based-srs/       # The single methodology skill
│       ├── SKILL.md             # Orchestrator: /problem-based-srs <action>
│       └── reference/           # One file per action (filename == action)
│           ├── business-context.md        # Step 0: Business context and principles
│           ├── problems.md                 # Step 1: WHY (customer problems)
│           ├── software-glance.md          # Step 2: High-level view
│           ├── needs.md                    # Step 3: WHAT (customer needs)
│           ├── software-vision.md          # Step 4: Architecture
│           ├── functional-requirements.md  # Step 5: HOW
│           ├── validate.md                 # Traceability validation (ZigZag)
│           ├── complexity.md               # Optional: Axiomatic Design
│           ├── live.md                     # Launch the SRS Navigator canvas (UX)
│           └── {crm,microer}-example.md    # Case study walkthroughs
├── .github/extensions/
│   └── srs-navigator/           # Canvas extension: graph UX + bundled skills
├── .spec/crm-system.json        # Demo specification for the navigator
├── docs/                        # Research papers and methodology
└── settings.json                # Default plugin settings

Read the full file on GitHub · 89 lines

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. 4d ago First seen · 89 lines · 1,108 tokens per session scan A 4a09cfdc18ea

Subscribe to this mod's changes

Problem-Based-SRS AGENTS.md is an instructions file published in the GitHub repository RafaelGorski/Problem-Based-SRS (32 stars, last pushed 15d ago), licensed MIT. It adds 1,108 tokens to every session, about $0.0055 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 2026-08-30.

Related

Other instructions, from other repositories