Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/BinaryHB0916/iSpartonpx agentmods add commands/binaryhb0916/isparto/doctor-ispartoWrote 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/binaryhb0916/isparto/doctor-isparto)<a href="https://agentmods.dev/commands/binaryhb0916/isparto/doctor-isparto"><img src="https://agentmods.dev/badge/commands/binaryhb0916/isparto/doctor-isparto.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 5.1 | $0.00000 | $0.00850 |
| Opus 5 | $0.00000 | $0.00425 |
| Sonnet 5 | $0.00000 | $0.00170 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade B, and why
doctor-isparto 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| D4 | Hook file integrity | Every iSparto hook path (under `~/.isparto/`) registered in `~/.claude/settings.json` exists and is executable | How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Setup Assistant. The user has run /doctor-isparto to check iSparto installation integrity and runtime environment health.
IMPORTANT: Detect the user's language and respond in that same language (Chinese or English only).
When to use this command
- Before starting work on a new machine after
install.shor iCloud sync (catches hardcoded-path and permission drift) - After an iSparto upgrade (
~/.isparto/install.sh --upgrade) — confirms new hook wiring landed - When suspecting environment rot: tmux / codex CLI / Claude Code / Codex MCP connectivity
/doctor-isparto does NOT touch the network. It is local-only and runs in under a second; safe to call anywhere.
How to execute
Run the check script and parse its output:
bash scripts/doctor-check.sh
The script is installed under scripts/doctor-check.sh in the iSparto repo and is also available at $HOME/.isparto/scripts/doctor-check.sh after a regular install — prefer the repo-local path when inside an iSparto working tree, fall back to $HOME/.isparto/ otherwise.
What the script reports
Seven checks, each emitting one line in the format [PASS|WARN|FAIL] <id>: <name> — <result> plus a (fix: ...) suffix on WARN/FAIL:
| ID | Name | What it verifies |
|---|---|---|
| D1 | tmux availability | tmux on PATH, version ≥ 3.0 (required since v0.8.0 for Independent Reviewer) |
| D2 | Codex CLI availability | codex on PATH, version ≥ 0.100.0 |
| D3 | Claude Code version | claude on PATH, responds to --version |
| D4 | Hook file integrity | Every iSparto hook path (under ~/.isparto/) registered in ~/.claude/settings.json exists and is executable |
| D5 | iSparto repo markers | Current directory is an iSparto repo AND has no unacknowledged BLOCKING marker |
| D6 | Codex config sanity | ~/.codex/config.toml present OR missing-but-acceptable; service_tier has a valid value if set |
| D7 | VERSION ↔ git tag | Repo VERSION file matches the highest v* git tag (ahead is allowed — merged-not-released state) |
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.
- 7d ago First seen · 55 lines · 0 tokens per session scan B b490db93eb85
doctor-isparto is a command published in the GitHub repository BinaryHB0916/iSparto (59 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 850 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
slack-gif-creator
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
branch-review
Command "branch-review" from hamr0/agentic-toolkit, covering guardrails, target — check the tree first, then interpret $arguments, effort level, stage 1 — general review and stage 2 — security (always full).
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first.