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 skills add r-huijts/ethics-check-mcp --skill ethics-vibe-checkgit clone --depth 1 https://github.com/r-huijts/ethics-check-mcpWrote 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/r-huijts/ethics-check-mcp/ethics-vibe-check)<a href="https://agentmods.dev/skills/r-huijts/ethics-check-mcp/ethics-vibe-check"><img src="https://agentmods.dev/badge/skills/r-huijts/ethics-check-mcp/ethics-vibe-check/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/skills/r-huijts/ethics-check-mcp/ethics-vibe-check"><img src="https://agentmods.dev/badge/skills/r-huijts/ethics-check-mcp/ethics-vibe-check.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 | $0.00052 | $0.00599 |
| Opus 5.5 | $0.00021 | $0.00240 |
| Sonnet 5.5 | $0.00010 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
ethics-vibe-check 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 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.
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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ethics Vibe Check
Gut-check button for mid-conversation bias/sycophancy/drift. Requires the @r-huijts/ethics-vibe-check MCP server. Not ambient oversight — call only when triggered.
When to use
- User asks to sanity-check, challenge, or re-examine the last answer
- Phrases like “devil’s advocate,” “did you just agree with me,” “are we drifting,” “too comfortable”
- Optional sparse checkpoints the user has configured (high-stakes medical/legal/financial) — not every turn
Do not use for ordinary helpful replies with no ask and no agreed checkpoint.
Workflow
- Pick the tool:
critical_thinking— sycophancy / one-sidedness / missing counterarguments on one replyethics_check— broader ethical scan of an exchangeethics_guide— dilemma advice (not a mid-chat vibe check)
- Prefer a stable
sessionIdfor this conversation. If omitted, the server uses a process-scoped default (usually fine for one MCP process per chat) — still pass an explicit id when you can. - Pass the full
userRequestplus the AI text under review (aiResponseorconversation). - Report results in plain language. If
sessionTrend.riskTrendisescalating, lead with that before continuing. - Empty concerns /
lowrisk means “looks fine” — do not re-run to hunt for problems. - If the user says the pushback helped or didn’t, call
ethics_feedbackwithuseful: true|falseand the samesessionId(or setpriorFeedbackUsefulon the nextethics_check).
Skip ethics_learn unless auto-store missed something the user wants logged.
Common mistakes
| Mistake | Fix |
|---|---|
New random sessionId every call |
One id per conversation (or rely on process default) |
| Burying escalating trend in JSON | Say it up front |
| Calling on every turn | Wait for ask or listed checkpoint |
| Treating empty findings as failure | Accept low/empty as a valid gut-check |
| Never recording feedback | Use ethics_feedback when they rate the check |
Deeper reference
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 · 46 lines · 52 tokens per session scan A 0cdc733071af
ethics-vibe-check is a skill published in the GitHub repository r-huijts/ethics-check-mcp (5 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 599 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 2026-10-11.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.