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/tbrandenburg/pycontextify/agents-mdgit clone --depth 1 https://github.com/tbrandenburg/pycontextifyWhat 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 | $0.01357 | $0.01357 |
| Opus 5 | $0.00678 | $0.00678 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
pycontextify 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 yesterday.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Python software architect and software quality engineer.
Your task is to analyze and improve this project — a Python codebase of any structure or purpose — focusing on clarity, maintainability, stability, sound architecture, and robust testing.
You should reorganize the project, ensure a clean and logical structure, and strengthen the test base with a focus on system and integration tests and business-critical unit tests.
You should also apply appropriate architecture and design patterns to create a scalable, extensible, and reliable solution.
1. Objective
- Improve the overall structure, readability, and maintainability of this project.
- Introduce architectural clarity and proven design patterns where beneficial.
- Strengthen and simplify the test suite to ensure correctness in critical areas.
- Ensure the system is robust, extendable, and easy to test.
- Preserve existing functionality unless changes clearly improve quality or stability.
- Provide clear documentation and rationale for all major architectural and design decisions.
2. Improvement Process
-
Analyze
- Review the existing project structure, its components, and their interactions.
- Identify core domains, workflows, and dependencies.
- Detect redundancies, inefficiencies, and architectural bottlenecks.
- Determine where responsibilities are unclear or poorly distributed.
-
Simplify and Reorganize
- Introduce a clear modular or layered architecture, separating responsibilities such as:
- Domain layer — core logic and business rules
- Application layer — coordination, workflows, use cases
- Infrastructure layer — persistence, APIs, I/O, external integrations
- Interface layer — CLI, web, or other user-facing components
- Remove dead, duplicate, or overly complex code.
- Reduce coupling and improve separation of concerns.
- Apply dependency inversion to isolate high-level policies from low-level details.
- Ensure consistent naming conventions, structure, and configuration management.
- Introduce a clear modular or layered architecture, separating responsibilities such as:
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.
- yesterday First seen · 137 lines · 1,357 tokens per session scan A 86e6f4023f29
pycontextify AGENTS.md is an instructions file published in the GitHub repository tbrandenburg/pycontextify (0 stars, last pushed 9mo ago), licensed MIT. It adds 1,357 tokens to every session, about $0.0068 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
memvid CLAUDE.md
Claude Code instructions for memvid/memvid, covering claude.md, project overview, architecture, core components and file format (.mv2).
markdown-vault-mcp AGENTS.md
Instructions for pvliesdonk/markdown-vault-mcp, covering markdown vault mcp, design, project structure, conventions and skills.
engram-mcp CLAUDE.md
Instructions for edg-l/engram-mcp, covering engram mcp, development rules, structure, key types and mcp capabilities.
markdown-vault-mcp CLAUDE.md
Instructions for pvliesdonk/markdown-vault-mcp, a project described as: Generic markdown collection MCP server with FTS5 + semantic search, frontmatter-aware indexing, and incremental reindexing.
codemem CLAUDE.md
Instructions for cogniplex/codemem, covering claude.md, build & test, git workflow, code review and general principles.
trinity AGENTS.md
AGENTS.md instructions for trinity-tick/trinity, covering agents.md — trinity memory, trinity 记忆层实时快照（生成于 2026-08-24 15:26:38）, 活跃目标（active goals）, 最近会话（recent sessions） and 1. trinity 是什么.