Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add andrewcigan/vibe-dev-plugin/plugin install vibe-devWrote 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/skills/andrewcigan/vibe-dev-plugin/doctor)<a href="https://agentmods.dev/skills/andrewcigan/vibe-dev-plugin/doctor"><img src="https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/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 | $0.00070 | $0.01562 |
| Opus 5 | $0.00035 | $0.00781 |
| Sonnet 5 | $0.00014 | $0.00312 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade A, and why
doctor 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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/doctor — жив ли enforcement
Профиль строгости в файле — это заявление. Этот скилл проверяет ФАКТЫ: работают ли хуки физически. Запускай диагностику сам (правило 8: не отправляй пользователя в терминал).
Шаг 1: Снять показания (одним bash-блоком)
echo "=== Vibe Dev /doctor ==="
echo "— Папка: $(pwd)"
echo "— Vibe-проект: $([ -d .harness ] || [ -f feature_list.json ] && echo да || echo НЕТ)"
echo "— Профиль: $(cat .harness/profile 2>/dev/null || echo '(нет файла)')"
echo "— Движок проекта (пин): $(cat .harness/engine-version 2>/dev/null || echo '(нет — legacy)')"
PV=$(jq -r '.version // "?"' "${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json" 2>/dev/null)
echo "— Установлен плагин: ${PV:-?} ($(git -C "${CLAUDE_PLUGIN_ROOT}" log -1 --format='%h %cd' --date=short 2>/dev/null || echo 'не git-копия'))"
PIN=$(tr -d '[:space:]' < .harness/engine-version 2>/dev/null); PINMAJ="${PIN%%.*}"
SOFT=0; [ -z "$PIN" ] && SOFT=1
case "$PINMAJ" in ''|*[!0-9]*) : ;; *) [ "$PINMAJ" -lt 6 ] 2>/dev/null && SOFT=1 ;; esac
[ "$SOFT" = 1 ] && echo "— ⚠️ Проект в МЯГКОМ режиме (движок не закреплён/устарел, major<6) → /upgrade-project для полной строгости. Пин 6.x/7.x уже строгий — апгрейд не нужен (новые механизмы v7 работают и так)."
if [ -f .harness/hooks-heartbeat ]; then
HB_TS=$(awk '{print $1; exit}' .harness/hooks-heartbeat); NOW=$(date +%s)
echo "— Heartbeat: $((NOW - HB_TS))с назад ($(cat .harness/hooks-heartbeat))"
else
echo "— Heartbeat: НЕТ (ни один хук ни разу не сработал в этом проекте)"
fi
echo "— Краши сторожей: $(ls .harness/hook-crashes/ 2>/dev/null | tr '\n' ' ' || echo нет)"
[ -f .harness/last-checkpoint.md ] && echo "— Слепок сжатия (M2): есть ($(awk -F'trigger=' '/trigger=/{print $2; exit}' .harness/last-checkpoint.md 2>/dev/null))"
# Аудит журнала (read-only, G5 + дешёвый дедуп): только отчёт, без правок.
bash "${CLAUDE_PLUGIN_ROOT}/scripts/journal-audit.sh" "$(pwd)" 2>/dev/null
[ -f .harness/hooks-disabled ] && echo "— ⚠️ hooks-disabled: backstop ОСОЗНАННО выключен"
[ -f .git/hooks/pre-commit ] && grep -q "Vibe Dev" .git/hooks/pre-commit 2>/dev/null \
&& echo "— pre-commit backstop: установлен" || echo "— pre-commit backstop: НЕ установлен"
echo "— Claude Code: $(claude --version 2>/dev/null || echo '(CLI не найден)')"
claude plugin list 2>/dev/null | grep -i vibe || echo "— Плагин: не виден в claude plugin list (или команда недоступна)"
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.
- 5d ago First seen · 66 lines · 70 tokens per session scan A 6c1cef1bfedd
doctor is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,562 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
dhpk-agent-architecture-audit
Full-stack diagnostic for agent and LLM applications — audits the 12-layer agent stack for wrapper regression, memory pollution, tool-discipline failures, hidden repair loops, and rendering corruption. Use when: shipping an agent/LLM feature, an agent degrades after adding wrapper/memory/tool layers, the same model…
dhpk-issue-analyze
GitHub Issue and PR review thread deep analysis with an optional blind verdict. Purpose: analyze issue root causes, classify problems, plan investigations, or triage PR review comments for actionability. Not for: fixing bugs (use flow-guide in bug mode), code exploration (use code-trace). Output: classified analysis +…
dhpk-gitnexus-debugging
Trace bugs and errors through the GitNexus knowledge graph. Use when: debugging a failure, tracing an error to its origin, finding callers of a suspect symbol, investigating unexpected behavior. Not for: general architecture understanding (use dhpk-gitnexus-exploring), change blast-radius (use…
dhpk-gitnexus-guide
Reference for GitNexus MCP tools, resources, and graph schema. Use when: asking what GitNexus tools exist, how to query the graph, or for MCP resource / schema reference. Not for: CLI commands (use dhpk-gitnexus-cli), task flows (use dhpk-gitnexus-exploring / dhpk-gitnexus-debugging / dhpk-gitnexus-impact-analysis /…
dhpk-feature-verify
Feature verification (READ-ONLY, P0-P5). Purpose: verify feature behavior after deployment, validate API responses, diagnose production issues, or run a post-deploy smoke test. Not for: modifying data (use flow-guide in feature mode), code review (use change-verdict), writing tests (use dhpk-tdd-workflow), security…
dhpk-python-static-checks
Static-check strategy for Python — ruff rule selection (lint vs format), pyright-strict vs mypy trade-offs, progressive typing adoption, per-file/per-line suppression discipline, and how the dhpk python module's post-edit + pre-commit hooks invoke them. Use when configuring ruff/pyright/mypy or triaging their output.…