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.
git clone --depth 1 https://github.com/MadAppGang/magusWrote 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/commands/madappgang/magus/repl)<a href="https://agentmods.dev/commands/madappgang/magus/repl"><img src="https://agentmods.dev/badge/commands/madappgang/magus/repl/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/madappgang/magus/repl"><img src="https://agentmods.dev/badge/commands/madappgang/magus/repl.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00048 | $0.00957 |
| Opus 5.5 | $0.00019 | $0.00383 |
| Sonnet 5.5 | $0.00010 | $0.00191 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
repl 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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/terminal:repl
Opens an interactive REPL or database shell, executes queries or expressions, and closes it when done.
Usage
/terminal:repl {application} [query]
Examples
Database shells:
/terminal:repl psql $DATABASE_URL
/terminal:repl "psql -d myapp" "SELECT count(*) FROM users"
/terminal:repl mongosh $MONGO_URI
/terminal:repl redis-cli
Language REPLs:
/terminal:repl python3
/terminal:repl node
/terminal:repl "bun repl"
What It Does
- Opens the REPL in an isolated slot and blocks until its prompt appears:
mcp__plugin_terminal_mux__start-and-watch({ slot: 2, isolated: true, command: "python3", pattern: ">>>" }) → { "slot": 2, "created": true, "event": "pattern:>>>", "detail": "Ready — matched: >>>", "elapsed": 0.51, "output": "…", "paneState": { "foregroundCmd": "Python", "isAlive": true, "waitingForInput": true } } - Executes each query with
run-in-repl, which returns the output between the input and the next prompt:mcp__plugin_terminal_mux__run-in-repl({ slot: 2, input: "1+1", promptPattern: ">>>", timeout: 10 }) → { "slot": 2, "created": false, "output": "1+1\n2", "exited": false } - Closes the slot.
close-paneinterrupts the REPL, so no exit command is needed:mcp__plugin_terminal_mux__close-pane({ slot: 2 }) → [{ "slot": 2, "action": "killed" }]
Use slot 2 unless mcp__plugin_terminal_mux__list-slots shows it is taken; then pick the next free number. isolated: true needs an explicit slot on start-and-watch.
Prompt Patterns
| Application | pattern / promptPattern |
|---|---|
| psql | "=#" |
| mongosh | ">" |
| redis-cli | "127\\.0\\.0\\.1:\\d+>" |
| python3 | ">>>" |
| node / bun | "> " |
| irb | "irb>" |
| turso shell | ">" |
Multi-Query Sessions
Each query is one run-in-repl call; output holds the full response, however long:
mcp__plugin_terminal_mux__run-in-repl({ slot: 2, input: "SELECT count(*) FROM users;", promptPattern: "=#" })
mcp__plugin_terminal_mux__run-in-repl({ slot: 2, input: "SELECT * FROM settings LIMIT 5;", promptPattern: "=#" })
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.
- 1mo ago Changed · -8 lines · +4 tokens per session 151d58640a47
- 1mo ago First seen · 94 lines · 44 tokens per session scan A 0f73ed388890
repl is a command published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 957 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other commands, from other repositories
gen
Automatically generates type definitions based on your Postgres database schema.
drizzle-orm-rules
Rules for using Drizzle ORM within the src/lib/db directory. Ensures consistent data modeling and database interactions.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.