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/kobiton/automateWrote 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/kobiton/automate/doctor)<a href="https://agentmods.dev/commands/kobiton/automate/doctor"><img src="https://agentmods.dev/badge/commands/kobiton/automate/doctor.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 | $0.00020 | $0.02801 |
| Opus 5 | $0.00010 | $0.01401 |
| Sonnet 5 | $0.00004 | $0.00560 |
| Haiku 4.5 | $0.00002 | $0.00280 |
Grade A, and why
doctor scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
LATEST="$(curl -sI --connect-timeout 5 --max-time 15 "https://public.kobiton.download/kobiton-cli/latest/" 2>/dev/null | awk 'tolower($1)=="location:"{print $2}' | tr -d '\r' | sed -e 's|/$||' -e 's|.*/||')" How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kobiton Automate Doctor
Run each check below in sequence. Print one line per check using ✓ (pass) or ✗ (failure). Never short-circuit — run all checks even if some fail. After the last check, print a summary line: Summary: <passed>/5 checks passed.
For each ✗, also print an indented remediation hint on the following line (prefixed with → ).
This command must NOT modify any files. The ~/.kobiton/bin/kobiton symlink is created by the plugin's SessionStart hook on Claude Code and Codex CLI (Codex prompts the user to trust the hook once via /hooks on first install), or by /automate:setup on demand. GitHub Copilot CLI and Gemini CLI both load /automate:setup (Copilot via Claude-format .md, Gemini via the bundled TOML at commands/automate/setup.toml) but have no SessionStart hook, so users on those CLIs run /automate:setup once after install. Cursor CLI also loads the shared .md commands but registers them without the plugin namespace — there they appear as /setup and /doctor (distinguishable from Cursor's built-ins by their Kobiton descriptions); read every /automate:setup / /automate:doctor mention in this file accordingly. This /automate:doctor command itself never modifies anything.
Check 1: CLI installed
Verifies the wrapper entry point is present: a symlink to the plugin's run.sh on macOS/Linux, or a bash exec-shim (regular file) on Windows, where symlinks aren't reliable under Git Bash.
LINK="$HOME/.kobiton/bin/kobiton"
if [ -L "$LINK" ]; then
TARGET="$(readlink "$LINK")"
if [ -f "$TARGET" ] && [ -x "$TARGET" ]; then
echo "PASS:$TARGET"
else
echo "FAIL:bad-target:$TARGET"
fi
elif [ -f "$LINK" ] && [ -x "$LINK" ] && grep -q 'run\.sh' "$LINK" 2>/dev/null; then
echo "PASS:shim:$(grep -o '"[^"]*run\.sh"' "$LINK" | tr -d '"')"
elif [ -e "$LINK" ]; then
echo "FAIL:not-a-symlink"
else
echo "FAIL:missing"
fi
PASS:<target>→ print✓ CLI installed (~/.kobiton/bin/kobiton → <target>)PASS:shim:<target>→ print✓ CLI installed (~/.kobiton/bin/kobiton is a Windows exec shim → <target>)FAIL:missing→ print✗ CLI installed (~/.kobiton/bin/kobiton not found)and→ Run /automate:setup to install the wrapper. On Claude Code and Codex CLI, restarting the session re-creates it via the bundled SessionStart hook (Codex requires trusting the hook once via /hooks). If the hook was denied or you need to install without an active session, fall back to: bash "$(find ~/.codex -name install-cli.sh -path '*automate*' 2>/dev/null | head -1)".FAIL:not-a-symlink→ print✗ CLI installed (~/.kobiton/bin/kobiton is neither a symlink nor an exec shim)and the same hint.FAIL:bad-target:<t>→ print✗ CLI installed (symlink target missing or not executable: <t>)and the same hint.
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 · 164 lines · 20 tokens per session scan A 2b45bc6604c5
doctor is a command published in the GitHub repository kobiton/automate (12 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 2,801 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
lint
Command "lint" from ApexIQ/skillsmith, covering command: /lint, goal, resources and execution plan.
debug
Command "debug" from ApexIQ/skillsmith, covering command: /debug, goal, resources and execution plan.
debug-issue
Command "debug-issue" from ApexIQ/skillsmith, covering command: /debug-issue, goal, resources and execution plan.
clean
Fix all linting and formatting issues across the codebase.
debug
Systematic debugging: root cause before any fix, one hypothesis at a time, and a three-strikes rule that questions the architecture instead of stacking patches.
validate
Run SDLC compliance check against the current project. Validates build system, code quality, testing, CI/CD, security, documentation, VCS, and release configurations.