harms-check

harms-check is a skill for Claude Code from haabe/mycelium. It costs 83 tokens per session (1,241 once invoked), scanned A, original, MIT.

A design review for user-facing products and flows that checks for foreseeable harm, such as deceptive patterns or misuse. It complements security checks, which focus on attacks, and privacy checks, which focus on personal data.

In plain words
What is it for?
Use it while designing a product or feature that people will use, particularly when it influences choices or handles sensitive situations. Skip it for purely internal developer tools, libraries, or build scripts.
Why use it?
It catches ways a feature could harm people even when it works exactly as designed. This is especially relevant for persuasion, pricing, cancellation, consent, or vulnerable-user scenarios.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery.

Part of the mycelium plugin — 61 skills, 6 hooks shipped together

Good fit Use it while designing a product or feature that people will use, particularly when it influences choices or handles sensitive situations. Skip it for purely internal developer tools, libraries, or build scripts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/haabe/mycelium/harms-check
Install

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.

Any agent
npx skills add haabe/mycelium --skill harms-check
Clone the repo
git clone --depth 1 https://github.com/haabe/mycelium

Made for: Claude Code.

Or install mycelium, the plugin that ships this one along with the rest of its 61 skills, 6 hooks.

Wrote 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.

agentmods badge for harms-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/haabe/mycelium/harms-check/github.svg)](https://agentmods.dev/skills/haabe/mycelium/harms-check)
Your own site
<a href="https://agentmods.dev/skills/haabe/mycelium/harms-check"><img src="https://agentmods.dev/badge/skills/haabe/mycelium/harms-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.

agentmods 80×15 button for harms-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/haabe/mycelium/harms-check"><img src="https://agentmods.dev/badge/skills/haabe/mycelium/harms-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.01241
Opus 5 $0.00042 $0.00620
Sonnet 5 $0.00017 $0.00248
Haiku 4.5 $0.00008 $0.00124

Measured 9d ago against content hash 00627d7f0cdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

harms-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 9d 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.

plugins/mycelium/skills/harms-check/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harms Check Skill

Design-time harm-to-users check — the safety-by-design lens the security/privacy/compliance gates structurally miss. Assumes the product works EXACTLY as designed. /threat-model (STRIDE) asks how an attacker breaks it; /privacy-check asks about personal data; neither asks: who could this harm when it works as intended, and how could a legitimate feature be misused?

This is the design-time front-end of the BVSSH Happier dimension: a manipulative or harmful design is Happier-negative by definition, and this gate catches it before /bvssh-check would only measure it post-hoc.

When to run (JiT — conditional, NOT universal)

Fires only when the product-shape warrants it:

  • User-facing product/feature (real people use it), OR
  • has persuasion / retention / conversion / cancellation / consent / pricing flows (the dark-pattern surface), OR
  • touches vulnerable people (children, patients, financially- or otherwise at-risk).

If none apply (internal dev tooling, a library, a build script), SKIP — say so and move on. This is a NUDGE, never a hard block.

Workflow

1. Dark / deceptive patterns (Brignull) — does the design manipulate the user?

Check the design against the recognised, regulated catalog (deceptive.design; FTC / EU Digital Fairness Act / GDPR-consent):

  • Obstruction / roach motel — easy to get in, hard to cancel, leave, or delete
  • Sneaking — hidden costs, drip pricing, sneak-into-basket, hidden subscription
  • Forced continuity / forced action — silent auto-renew; forced account/consent to proceed
  • Confirmshaming — guilt/shame wording to steer a choice ("No, I don't want to save money")
  • Nagging — repeated interruption until the user relents
  • Misdirection / visual interference — pre-ticked boxes, manipulative default, tricked hierarchy
  • Privacy zuckering — coaxing users to share more than intended; consent dark patterns
  • Bait and switch / disguised ads — the control does something other than advertised

Read the full file on GitHub · 92 lines

Changes

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.

  1. 9d ago First seen · 92 lines · 83 tokens per session scan A 00627d7f0cdd

Subscribe to this mod's changes

harms-check is a skill published in the GitHub repository haabe/mycelium (45 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 1,241 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

skill-finder

Find the right Affitor skill for your goal. Triggers on: "which skill should I use", "find me a skill", "what skills are available", "help me choose a skill", "skill for SEO", "skill for email", "explore skills", "I'm new to Affitor", "what can Affitor do", "search skills", "skill for blog writing", "skill for landing…

Affitor/affiliate-skills · 94 tokens

Discovery Response Workflow

Use when organizing responses to written discovery — document requests, interrogatories, or requests for admission — inventorying each request verbatim into a response tracker, organizing objection candidates and privilege candidates as questions for counsel, planning collection and custodians, and drafting response…

zgbrenner/agentcounsel · 71 tokens

Privilege Log Review

Use when conducting a first-pass review of a privilege log to sort entries into three tiers — confidently privileged, uncertain (flagged for attorney decision), and recommend-remove — so attorney review time focuses on the entries that require judgment.

zgbrenner/agentcounsel · 49 tokens

Subpoena Triage

Use when an incoming subpoena has been received to produce a structured triage summary identifying the compliance deadline, scope, objections, privilege issues, preservation obligations, and internal notification requirements for immediate attorney review.

zgbrenner/agentcounsel · 45 tokens

Deposition Preparation

Use when building a structured deposition outline from the case theory, witness profile, and documentary record to produce a focused, attorney-ready map for taking or defending a deposition.

zgbrenner/agentcounsel · 37 tokens

Family Law Discovery Tracker

Use when organizing family-law discovery requests, responses, disclosures, subpoenas, authorizations, deficiencies, and meet-and-confer items into a tracker for attorney review.

zgbrenner/agentcounsel · 38 tokens