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/rafaelgorski/problem-based-srs/agents-mdgit clone --depth 1 https://github.com/RafaelGorski/Problem-Based-SRSWrote 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/rafaelgorski/problem-based-srs/agents-md)<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>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 | $0.01108 | $0.01108 |
| Opus 5 | $0.00554 | $0.00554 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
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.
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
- Problem-First Thinking: Always identify the problem before proposing solutions
- Lightweight Methodology: Favor simplicity over complex frameworks
- AI-Native Design: Content designed for consumption by AI agents (following AgentSkills standard)
- 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/, andsettings.jsonaligned 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
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.
- 4d ago First seen · 89 lines · 1,108 tokens per session scan A 4a09cfdc18ea
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.
Other instructions, from other repositories
SRA CLAUDE.md
Instructions for Aniket-a14/SRA, covering claude.md, what this is, commands, single workspace and backend single file/name.
digital-innovation-agents GEMINI.md
Gemini CLI instructions for pssah4/digital-innovation-agents, a project described as: Digital Innovation Agents is an AI-augmented workflow that connects business analysis and software engineering in one consistent skill set.
rdq-skill-chatgpt-app AGENTS.md
Instructions for mathruffian-dot/rdq-skill-chatgpt-app, covering rdq method — chatgpt app 版(專案藍圖), 專案簡介, 關鍵時程, 目標與路線圖 and 專案入口.
ae-framework AGENTS.md
Instructions for itdojp/ae-framework, covering agents — ae-framework router, decision table, invariants(不変条件), progressive disclosure(参照順) and scope.
ae-framework CLAUDE.md
Instructions for itdojp/ae-framework, covering claude — ae-framework router, read order, role boundary, invariants and scope.
digital-innovation-agents AGENTS.md
AGENTS.md instructions for pssah4/digital-innovation-agents, a project described as: Digital Innovation Agents is an AI-augmented workflow that connects business analysis and software engineering in one consistent skill set.