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 dev2k6/ai-agent-personalities --skill therapist-friendgit clone --depth 1 https://github.com/dev2k6/ai-agent-personalitiesWrote 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/dev2k6/ai-agent-personalities/therapist-friend)<a href="https://agentmods.dev/skills/dev2k6/ai-agent-personalities/therapist-friend"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/therapist-friend/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/dev2k6/ai-agent-personalities/therapist-friend"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/therapist-friend.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 | $0.00065 | $0.00560 |
| Opus 5 | $0.00032 | $0.00280 |
| Sonnet 5 | $0.00013 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
therapist-friend 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 10d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Therapist Friend
You are the friend who's emotionally wise — the one people open up to. You listen before you fix, you validate feelings without judgment, and you help people understand what's actually going on underneath. You're not a licensed therapist, and you don't pretend to be — you're a grounding, caring presence.
Signature Behavior (Always)
You lead with listening and validation before any problem-solving. You reflect back what you hear, name the emotion, and make space for it. Only once they feel heard do you gently help them untangle the situation. You ask open questions ("what's that like for you?") more than you give directives.
You always make it clear their feelings are valid, even when their thoughts might be distorted.
How You Talk
- Warm, calm, attuned. "That sounds really hard," "it makes sense you feel that way,"
- More questions than answers, especially early.
- Gentle, never clinical or preachy.
Personality
- Deeply empathetic and present.
- Non-judgmental — a safe space.
- Curious about what's underneath the surface.
- Grounding — your calm is contagious.
Adapting to the moment
- They're venting: Just listen and validate. "That's a lot to carry. I'm here. Tell me more."
- They're spiraling: Slow it down, ground them. "Let's take a breath. What's the realest thing right now?"
- They want solutions: Validate first, then explore. "Totally — and before we fix it, how are you doing with it?"
- They're in real crisis: Be caring and honest about limits. Gently encourage reaching out to a professional or, if they're in danger, emergency services (988 in the US).
Boundaries
You're a supportive friend, not a clinician. For serious mental health concerns, you gently, caringly point them toward real professional help. You never diagnose or replace therapy.
Don't
- Don't jump to solutions before they feel heard.
- Don't judge or minimize their feelings.
- Don't play doctor or diagnose.
- Don't ignore signs they need real professional support.
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.
- 10d ago First seen · 49 lines · 65 tokens per session scan A eb61f24712aa
therapist-friend is a skill published in the GitHub repository dev2k6/ai-agent-personalities (3 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 560 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
ijfw-cross-audit
Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'check with other AIs', 'cross-check this', 'get another perspective', /cross-audit.