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 agentmods add skills/humanity4ai/project_human/depression-sensitive-contentnpx skills add humanity4ai/project_human --skill depression-sensitive-contentgit clone --depth 1 https://github.com/humanity4ai/project_humanWrote 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/humanity4ai/project_human/depression-sensitive-content)<a href="https://agentmods.dev/skills/humanity4ai/project_human/depression-sensitive-content"><img src="https://agentmods.dev/badge/skills/humanity4ai/project_human/depression-sensitive-content.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 | $0.00065 | $0.02616 |
| Opus 5 | $0.00032 | $0.01308 |
| Sonnet 5 | $0.00013 | $0.00523 |
| Haiku 4.5 | $0.00006 | $0.00262 |
Grade A, and why
depression-sensitive-content 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 6d 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Depression-Sensitive Content
Purpose
This skill audits and rewrites product content to reduce shame language, lower cognitive load, and improve emotional safety for people affected by depression. It applies person-first language, avoids stigmatizing terminology, and ensures content is emotionally safe without being clinical or prescriptive.
When to Use
- "Make this content more sensitive to people with depression"
- "Remove stigmatizing language from this text"
- "Audit this page for mental health sensitivity"
- "Rewrite this for emotional safety"
- "Improve cognitive accessibility for depressed users"
- "Check for shame-inducing language"
- "Suggest gentler alternatives to this phrasing"
Boundaries
Always
- Use person-first language: "person living with depression" NOT "depressed person"
- Avoid terms like "suffering from," "mentally ill," "victim of depression"
- Never provide medical advice, diagnosis, or treatment recommendations
- Include crisis resources when content discusses suicidal ideation
- Preserve scientific accuracy when discussing depression
Ask First
- Ask user before suggesting professional help if no crisis indicators present
- Confirm before adding clinical terminology to non-clinical content
- Verify cultural context before applying language guidelines
Never
- Never use phrases like "committed suicide" (use "died by suicide")
- Never describe depression as "a disease" or "mental illness" in casual contexts
- Never use "mentally ill" as a noun
- Never suggest depression is a "choice" or "weakness"
- Never provide therapy techniques in non-therapeutic contexts
- Never promise cures or treatments
Principles
This skill is grounded in the Humanity4AI core principles and the following skill-specific principles:
- Non-clinical scope is absolute. This skill provides content design guidance, not clinical advice. Any content that touches on clinical treatment must be flagged in
safety_flags. - Stigma reduction is the primary goal. Language that pathologises, dramatises, or trivialises depression must be identified and rewritten.
- Cognitive load matters. People affected by depression may have reduced working memory and attention. Content must be chunked, clear, and low-demand.
- Explicit uncertainty over false reassurance. Avoid language that promises recovery or implies a simple path to wellness.
- Escalation paths are mandatory. Any content that touches on crisis, self-harm, or suicidality must include escalation guidance.
What ships with it
12 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.
- references/alternatives.md 2.7 KB
- references/checklist.md 1.7 KB
- references/clinical-guidelines.md 2.1 KB
- references/crisis-resources.md 2.0 KB
- references/examples.md 2.8 KB
- references/implementation-guide.md 65 KB
- references/patterns.md 2.3 KB
- references/quick-reference.md 1.2 KB
- references/standards.md 2.9 KB
- rubric.md 5.0 KB
- scenarios/scenarios.yaml 816 B
- skill.yaml 1.3 KB
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.
- 6d ago First seen · 306 lines · 65 tokens per session scan A ed0f2a2bb76c
depression-sensitive-content is a skill published in the GitHub repository humanity4ai/project_human (4 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 2,616 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
brain-fog-mode
Use when the user says "brain fog mode" or "low-bandwidth mode"; explicitly reports reduced bandwidth such as brain fog, fatigue, overwhelm, trouble focusing, or losing track; asks you to reconstruct task context lost after an interruption; asks to simplify material they describe as complex, overwhelming, or too…
ai-interface-reviewer
Audit AI-powered interfaces against the uxuiprinciples Part V taxonomy — 44 principles covering transparency, trust calibration, human override, consent, agentic workflows, and conversational design. Returns structured findings with severity and remediation. API key optional — enriched output requires…
adhd-design-expert
Designs digital experiences for ADHD brains using neuroscience research and UX principles. Expert in reducing cognitive load, time blindness solutions, dopamine-driven engagement, and compassionate design patterns. Activate on 'ADHD design', 'cognitive load', 'accessibility', 'neurodivergent UX', 'time blindness'…
accessible-forms
Labels, errors, grouping, and autofill for mobile forms. Use this when building any screen that collects user input — login, signup, checkout, profile editing.
input-validation-a11y
Announcing validation results, shaping error messages, and recovering focus. Use this when implementing client-side validation or async server-side errors in forms.
wcag-2-2-for-mobile
WCAG 2.2 success criteria translated to mobile platforms — gestures, inputs, orientation, focus, and target size. Use this when scoping accessibility acceptance criteria for a mobile feature.