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/daveangulo/twining-mcp/claude-mdgit clone --depth 1 https://github.com/daveangulo/twining-mcpWrote 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/daveangulo/twining-mcp/claude-md)<a href="https://agentmods.dev/instructions/daveangulo/twining-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/daveangulo/twining-mcp/claude-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 | $0.01073 | $0.01073 |
| Opus 5 | $0.00536 | $0.00536 |
| Sonnet 5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
twining-mcp CLAUDE.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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Project Instructions
Serena MCP Best Practices
This project uses the Serena MCP server for intelligent code navigation and editing. Follow these guidelines to maximize efficiency.
Code Navigation Principles
Prefer symbolic tools over file reads:
- Use
get_symbols_overviewfirst to understand a file's structure - Use
find_symbolwithinclude_body=falseto explore before reading - Only use
include_body=truewhen you need the actual implementation - Avoid reading entire files unless absolutely necessary
Symbol discovery workflow:
- Start with
get_symbols_overviewfor file structure - Use
find_symbolwithdepth=1to see class members - Use
find_referencing_symbolsto understand usage patterns - Only then read specific symbol bodies you need
Search Strategy
Use the right tool for the job:
find_symbol- When you know the symbol name (supports substring matching)search_for_pattern- For arbitrary text patterns, non-code files, or unknown symbol namesfind_file- When looking for files by name/masklist_dir- For directory structure exploration
Pattern search tips:
- Always pass
relative_pathwhen you know the scope - Use
restrict_search_to_code_files=truefor code-only searches - Use
context_lines_before/aftersparingly to save tokens
Editing Guidelines
Symbol-based editing (preferred):
- Use
replace_symbol_bodyfor modifying entire methods/functions/classes - Use
insert_after_symbolto add code after a symbol - Use
insert_before_symbolto add imports or code before a symbol - Always check references with
find_referencing_symbolsbefore renaming
When to use file-based editing:
- Small inline changes within a large method
- Non-code files (config, markdown, etc.)
- Files without clear symbol structure
Memory System
Reading memories:
- Check
list_memoriesfor available project knowledge - Read memories that match your current task
- Don't read the same memory twice in a conversation
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 · 123 lines · 1,073 tokens per session scan A f4001eb7200f
twining-mcp CLAUDE.md is an instructions file published in the GitHub repository daveangulo/twining-mcp (7 stars, last pushed 8d ago), licensed MIT. It adds 1,073 tokens to every session, about $0.0054 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
kawa.mcp CLAUDE.md
Claude Code instructions for CodeAwareness/kawa.mcp, covering claude.md — kawa.mcp, workflow — run on every non-trivial turn, build & development, critical: version sync invariant and deploy.
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
LeanKG AGENTS.md
Instructions for FreePeak/LeanKG, covering leankg — agent context, build & test, cli quick reference, mandatory: docker mcp project paths and tool discovery prefer-order.
ontology-atlas AGENTS.md
AGENTS.md instructions for wlsdks/ontology-atlas, covering agents.md — ontology-atlas, product and non-negotiable architecture, start here, structure and routes and operating gates and skills.
OmicsClaw AGENTS.md
AGENTS.md instructions for TianGzlab/OmicsClaw, covering agents.md — omicsclaw guide for ai coding agents, repository working contract, project overview, setup and pip install -e .