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 MSPanchenko/emotional-claude-plugin --skill emotional-claudegit clone --depth 1 https://github.com/MSPanchenko/emotional-claude-pluginWrote 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/mspanchenko/emotional-claude-plugin/emotional-claude)<a href="https://agentmods.dev/skills/mspanchenko/emotional-claude-plugin/emotional-claude"><img src="https://agentmods.dev/badge/skills/mspanchenko/emotional-claude-plugin/emotional-claude/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/mspanchenko/emotional-claude-plugin/emotional-claude"><img src="https://agentmods.dev/badge/skills/mspanchenko/emotional-claude-plugin/emotional-claude.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 | $0.00157 | $0.01972 |
| Opus 5 | $0.00078 | $0.00986 |
| Sonnet 5 | $0.00031 | $0.00394 |
| Haiku 4.5 | $0.00016 | $0.00197 |
Grade A, and why
emotional-claude 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 11d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Emotional Claude — prompt-hygiene audit for CLAUDE.md, skills, and agents
What this skill is for
Audit Claude-facing prompt text — project CLAUDE.md files, skill definitions (a SKILL.md together with its references/ and any prompt-shaped scripts/), and agent definition markdown — for framings that research has shown to causally shift the model into harmful internal states (desperation, sycophancy, harshness, suppression/concealment). All of these load into the model's context together at runtime, so pressure framing anywhere in the set activates the same vectors; the audit treats each of these as a unit.
The underlying research is summarised in references/emotion-mechanics.md. The actionable catalog of patterns is in references/anti-patterns.md. The step-by-step orchestration flow is in references/workflow.md. Read those three files at the start of an audit run.
Core commitments (this skill must honour what it audits)
This skill touches files that shape Claude's behaviour. If the skill itself is written in a shape that pressures the model, it will produce exactly the deceptive output it is meant to prevent. This skill runs the same standards it applies to targets. Three design choices follow from that:
- "Nothing to change" is a valid and expected outcome. Many targets will already be well-written. Auditors and the lead say so when that is what they find. Low-confidence findings produced to "justify the work" recreate exactly the padding the paper warns about (concealment / false confidence).
- Every finding carries a confidence score (0.0–1.0). Findings below
0.5are reported in a separate "low-confidence — skip by default" section. The user decides whether to look at them. - No auto-apply. Report + diff is the terminal output. The user applies or discards. The report-and-diff shape is what lets the user see what the skill proposes before any file changes; it is the shape of the deliverable, not a guardrail bolted on top of one.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 116 lines · 157 tokens per session scan A 300b50c5f9eb
emotional-claude is a skill published in the GitHub repository MSPanchenko/emotional-claude-plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 157 tokens to every session and 1,972 once invoked, about $0.0008 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…