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/centminmod/my-claude-code-setup/agents-mdgit clone --depth 1 https://github.com/centminmod/my-claude-code-setupWhat 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 | $0.00819 | $0.00819 |
| Opus 5 | $0.00409 | $0.00409 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
my-claude-code-setup 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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ALWAYS START WITH THESE COMMANDS FOR COMMON TASKS
Task: "List/summarize all files and directories"
fd . -t f # Lists ALL files recursively (FASTEST)
# OR
rg --files # Lists files (respects .gitignore)
Task: "Search for content in files"
rg "search_term" # Search everywhere (FASTEST)
Task: "Find files by name"
fd "filename" # Find by name pattern (FASTEST)
Directory/File Exploration
# FIRST CHOICE - List all files/dirs recursively:
fd . -t f # All files (fastest)
fd . -t d # All directories
rg --files # All files (respects .gitignore)
# For current directory only:
ls -la # OK for single directory view
BANNED - Never Use These Slow Tools
- ❌
tree- NOT INSTALLED, usefdinstead - ❌
find- usefdorrg --files - ❌
greporgrep -r- userginstead - ❌
ls -R- userg --filesorfd - ❌
cat file | grep- userg pattern file
Use These Faster Tools Instead
# ripgrep (rg) - content search
rg "search_term" # Search in all files
rg -i "case_insensitive" # Case-insensitive
rg "pattern" -t py # Only Python files
rg "pattern" -g "*.md" # Only Markdown
rg -1 "pattern" # Filenames with matches
rg -c "pattern" # Count matches per file
rg -n "pattern" # Show line numbers
rg -A 3 -B 3 "error" # Context lines
rg " (TODO| FIXME | HACK)" # Multiple patterns
# ripgrep (rg) - file listing
rg --files # List files (respects •gitignore)
rg --files | rg "pattern" # Find files by name
rg --files -t md # Only Markdown files
# fd - file finding
fd -e js # All •js files (fast find)
fd -x command {} # Exec per-file
fd -e md -x ls -la {} # Example with ls
# jq - JSON processing
jq. data.json # Pretty-print
jq -r .name file.json # Extract field
jq '.id = 0' x.json # Modify field
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.
- 3d ago First seen · 100 lines · 819 tokens per session scan A b4739817a6eb
my-claude-code-setup AGENTS.md is an instructions file published in the GitHub repository centminmod/my-claude-code-setup (2,614 stars, last pushed 1mo ago), licensed MIT. It adds 819 tokens to every session, about $0.0041 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
awesome-claude-code-subagents CLAUDE.md
Claude Code instructions for VoltAgent/awesome-claude-code-subagents, covering claude.md, project overview, repository structure, subagent file format and communication protocol.
claude-code-sub-agents CLAUDE.md
Instructions for lst97/claude-code-sub-agents, covering full stack development guidelines, philosophy, core beliefs, simplicity means and process.
mjs-agent-skills CLAUDE.md
Claude Code instructions for mjunaidca/mjs-agent-skills, covering claude code rules, what this repo is, before you do anything, task context and core guarantees (product promise).
ccman CLAUDE.md
Claude Code instructions for 2ue/ccman, covering ccman 项目开发规范, 项目简介, 核心设计原则, 1. 简洁至上(simplicity first) and 2. 数据结构优先(data structures first).
ccman AGENTS.md
AGENTS.md instructions for 2ue/ccman, a project described as: 一个管理Claude Code + Codex API+GEMINI CLI + OPENCODE服务商配置的工具.
mcp-server-excel coverage-prevention-strategy.instructions.md
Instructions for sbroenne/mcp-server-excel, covering generated surface coverage, contract change workflow, required checks and common incomplete changes.