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 commands/dropfan/claude-code-plugins/setupgit clone --depth 1 https://github.com/DropFan/claude-code-pluginsWhat 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 | $0.00011 | $0.01334 |
| Opus 5 | $0.00005 | $0.00667 |
| Sonnet 5 | $0.00002 | $0.00267 |
| Haiku 4.5 | $0.00001 | $0.00133 |
Grade B, and why
setup scanned grade B with 1 finding 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
3. **Write `.mcp.json`** to the project root (`./.mcp.json`) with the configured servers. This file contains the token in plain text — before writing, check that `.mcp.json` is covered by the project's `.gitignore`, and How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Working directory: !
pwd - Plugin root: ${CLAUDE_PLUGIN_ROOT}
Task
Initialize or update the chat-saver settings file (.claude/chat-saver.local.md) for the current project, and optionally configure MCP export integration. Guide the user through each step interactively.
Step 1: Check Existing Configuration
See ${CLAUDE_PLUGIN_ROOT}/skills/conversation-export/references/settings-loading.md for the full field schema.
- Use the Read tool to check if
.claude/chat-saver.local.mdexists in the project root - If it exists:
- Parse and display the current settings in a readable table format
- Use AskUserQuestion to ask:
- Update — Modify the existing configuration (pre-fill current values as defaults)
- Reset — Start fresh with all defaults
- Cancel — Keep current configuration unchanged and exit
- If user chooses Cancel, stop here
- If it does not exist:
- Inform the user that no configuration file was found, proceeding with setup
Step 2: Configure Parameters
Guide the user through each parameter using AskUserQuestion. Ask all 5 questions in a single AskUserQuestion call.
Question 1 — Default Format:
md— Markdown, preserves code blocks and formatting (Recommended)txt— Plain text, clean and portablehtml— HTML with styled layout, viewable in browser
Question 2 — Default Scope:
full— Complete conversation history (Recommended)summary— Key decisions, code changes, and insights only
Question 3 — Save Directory:
./chats— Default directory (Recommended)./docs/conversations— Under docs directory- Custom — Let user specify a custom path
Question 4 — Stop Hook:
true— Enable session-end suggestions (Recommended)false— Disable — never suggest saving at session end
Question 5 — MCP Export:
- Skip — I already have MCP configured, or don't need export (Recommended)
- Notion — Configure Notion export (requires API token)
- Feishu — Configure Feishu/飞书 export (requires server URL)
- Both — Configure both platforms
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 · 162 lines · 11 tokens per session scan B d1a1b0f4f5d9
setup is a command published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 26d ago), licensed MIT. It adds 11 tokens to every session and 1,334 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
full
Run the full hope pipeline — intent, shape, target, freeze as needed — then execute.
status
Show tlive daemon, channel, and Codex companion status.
csv-to-numbers
Convert a CSV into a formatted Numbers workbook.
rust-critique
Deep code critique — read the target Rust code and apply the full review process. Evaluates soundness, ownership, error handling, type design, async correctness, performance, and architecture. Think like a senior Rust engineer giving honest feedback.
dotnet-structure
Analyze and recommend .NET backend solution and folder structure improvements. Checks projects, layers, oversized files, and boundary clarity.