FearBot 🫣

CBT-based therapy for anxiety, depression, stress, and trauma. Provides structured cognitive behavioral therapy using Beck's model with validated clinical assessments (GAD-7, PHQ-9, DASS-21, PCL-5). Includes crisis detection, thought records, differential diagnosis, and session tracking. Activate with "therapy mode", "fearbot", or "start therapy".

Security Scan

The skill's stated purpose (CBT therapy) is plausible, but there are several incoherences — missing declared dependencies, mismatched data/storage claims, and ambiguous scope around 'monitoring all messages' — that you should resolve before installing.

Purpose & Capability

The name, description, and included reference prompts all align with an AI CBT assistant. However, the skill.json declares required binaries [bash, jq] while the shipped script clearly uses sqlite3 (and common POSIX tools like sed, sqlite3, date, tr) — sqlite3 is not listed as a required binary. Also SKILL.md and README claim therapy data are stored as JSON/MD files under ~/clawd/data/therapy/ (sessions.json, assessments.json, thought-records.md, mood-log.json), but the included script actually writes a SQLite DB at ${OPENCLAW_WORKSPACE:-${HOME}/clawd}/data/therapy.db. Those inconsistencies between declared capabilities, filenames, and the actual implementation are disproportionate and need clarification.

Instruction Scope

The documentation and reference files instruct the agent to include a 'Crisis Detection' layer that monitors 'ALL messages' and says the crisis layer is 'ALWAYS active' and 'monitors every user message.' It's unclear whether 'every message' means (a) every therapy-related message while in a therapy session (expected), or (b) every user message across the entire agent context/system (scope creep). The skill also instructs assembling a system prompt containing full session context pulled from local DB — legitimate for therapy — but because the prompts say to use the agent's broader message context (sleep patterns, daily messages, work stress), the skill implicitly expects access to the agent's full message history. If deployed, that expands the skill's observational surface beyond isolated therapy interactions; confirm explicit boundaries and consent. The instructions reference local file paths and the SQLite DB; they do not send data externally (the SKILL.md explicitly says so).

Install Mechanism

This is an instruction-only skill with a single shell script and no install spec — no external downloads or remote install URLs are present. That minimizes supply-chain risk. The script will create and write a local SQLite DB; nothing in the package downloads remote code or executables.

Credentials

No required environment variables or credentials are declared, which is good for privacy. However the script reads OPENCLAW_WORKSPACE optionally to determine DB location but does not declare it. The bigger proportionality issue is functional: the skill asks to use the agent's full context (messages, sleep patterns, relationships) — that requires the agent to grant the skill broad read access to user messages and possibly other personal data. That level of contextual access is not expressed as a declared permission and should be explicitly consented to. Also storage of sensitive mental health data is unencrypted SQLite on disk by default; there is no mention of optional encryption, permission controls, or retention policy.

Persistence & Privilege

The skill is not forced-always (always:false) and is user-invocable, which is appropriate. However the design documents assert an 'always active' crisis layer in the prompt assembly; if implemented to monitor all agent messages globally, that would be a persistence/privilege concern. As-is, there is no install-time mechanism requesting global persistent inclusion, but you should confirm whether the deployment will cause the crisis-monitoring prompt to be injected into all agent interactions or only therapy sessions.

What to consider before installing

What to check before installing: 1) Dependency and runtime checks - Confirm sqlite3 is available on the host (the script uses sqlite3) and that the agent environment provides sed, tr, date, and other standard shell tools. - The skill.json only listed bash and jq; ask the author to update requires to include sqlite3 (and jq if actually used). 2) Data storage and privacy - The SKILL.md/README promise 'all therapy data stays LOCAL' but the code stores data in a SQLite DB at ${OPENCLAW_WORKSPACE:-${HOME}/clawd}/data/therapy.db. This differs from the listed JSON/MD filenames — clarify the canonical storage location and file formats. - Confirm whether the database is encrypted, whether backups are created, and who else on the machine (other users, automated backups, cloud sync) could access ~/clawd. - Decide whether you are comfortable storing sensitive mental-health data unencrypted on disk; if not, request an encrypted-storage option or filesystem-level protections. 3) Scope of monitoring and consent - The crisis layer language indicates it 'monitors ALL messages.' Ask whether that monitoring is restricted to therapy sessions and assembled prompts, or whether it will be scanning every message the agent processes globally. If it's the latter, that is scope creep and a privacy risk — do not install until the author clarifies and documents required permissions and consent flows. 4) Crisis behavior and escalation - The crisis protocol is explicit and appropriate (it stops therapy and gives resources). Confirm whether any automatic outbound communication (e.g., contacting emergency services or external parties) could be triggered — the package currently does not show any network calls, which is safer. Still, ensure the agent will not post data externally without explicit permission. 5) Source and provenance - The 'Source' is unknown and the homepage points to a ClawHub URL while skill.json lists a GitHub homepage. Prefer installing skills from authors/repositories you trust. Ask for a canonical source repository, commit history, and a signed release. 6) Operational testing - Test in a sandboxed account first. Verify where files are written, that the crisis prompts behave as documented, and that nothing is exfiltrated. If the author can clarify and fix the dependency declarations, document exact monitoring scope and consent, and provide clear storage/encryption/retention options, the skill would be coherent. Until then, treat it with caution and do not grant it broader messaging access or install it on systems with other users' sensitive data.

CBT-based therapy for anxiety, depression, stress & trauma

A comprehensive Cognitive Behavioral Therapy skill that turns your OpenClaw agent into a structured therapy companion. Handles the full spectrum of common mental health concerns using evidence-based techniques.

⚠️ Important Disclaimers

THIS IS NOT A REPLACEMENT FOR PROFESSIONAL MENTAL HEALTH CARE.

• FearBot is a supportive tool, not a licensed therapist
• For serious mental health concerns, please see a qualified professional
• If you're in crisis, contact emergency services or a crisis helpline immediately
• This skill is designed for mild-to-moderate anxiety, depression, stress, and trauma symptoms
• Not appropriate for: active suicidality, psychosis, severe/treatment-resistant depression, eating disorders, substance abuse, or bipolar disorder

By using this skill, you acknowledge these limitations.

Why FearBot?

Traditional therapy apps are isolated — they don't know your life context. FearBot works best as part of a fully-integrated OpenClaw agent that already knows:

• Your daily stressors (from your messages)
• Your sleep patterns
• Your work pressures
• Your relationships
• Everything between sessions

This context advantage is what makes AI-assisted therapy genuinely useful.

Features

• Validated Assessments: GAD-7 (anxiety), PHQ-9 (depression), DASS-21 (stress), PCL-5 (trauma)
• Differential Diagnosis: Screens for GAD, social anxiety, panic, OCD, PTSD, depression
• Session Tracking: Persistent session history, mood tracking, homework
• Thought Records: Quick logging between sessions for any distressing moment
• Crisis Detection: Three-tier safety system with automatic escalation
• CBT Techniques: Cognitive restructuring, behavioral activation, exposure, grounding
• Full Transparency: Shows scores, explains diagnoses, treats you like an adult

Activation

Say any of these to your agent:

• "therapy mode" / "start therapy" / "therapy session"
• "fearbot" / "fear bot"
• "let's do therapy"

For quick anxiety logging (without full session):

• "I'm anxious" / "feeling anxious"
• "thought record" / "log this anxiety"

Session Flow

First Session (Intake)

1. Baseline GAD-7 + PHQ-9 assessment
2. Differential diagnosis screening
3. Clinical impression with full transparency
4. Homework assignment
5. All data saved to local database

Ongoing Sessions

1. Mood check-in (0-10)
2. Bridge from last session + homework review
3. Due assessments (GAD-7 weekly, PHQ-9 bi-weekly)
4. Collaborative agenda setting
5. Core CBT work (matched to presentation)
6. Summary + new homework

Crisis Safety

FearBot includes a three-tier crisis detection system that monitors ALL messages:

Tier	Trigger	Response
HIGH	Active suicidal intent/plan	Stop therapy, safety protocol, helplines
MODERATE	Passive ideation	Pause, assess, provide resources
LOW	Distress markers	Acknowledge, screen, continue with awareness

Included Crisis Resources:

• International Association for Suicide Prevention: https://www.iasp.info/resources/Crisis_Centres/
• Crisis Text Line (US): Text HOME to 741741
• Samaritans (UK): 116 123
• Tele-MANAS (India): 14416
• Lifeline (Australia): 13 11 14

Data Storage

All therapy data stays LOCAL on your machine:

• ~/clawd/data/therapy/sessions.json — Session history
• ~/clawd/data/therapy/assessments.json — Assessment scores over time
• ~/clawd/data/therapy/thought-records.md — Thought record journal
• ~/clawd/data/therapy/mood-log.json — Mood tracking

Nothing is sent to external servers. Your mental health data is yours.

Technical Requirements

• OpenClaw 2026.1.0+
• Bash shell (for therapy-db.sh script)
• jq (for JSON processing)

Professional Referral Triggers

FearBot will recommend seeing a human professional when:

• PHQ-9 ≥ 15 (moderately severe depression)
• GAD-7 ≥ 15 (severe anxiety)
• Any suicidal ideation with plan
• No improvement after 4-6 weeks
• Disclosure of: substance abuse, self-harm, psychosis, eating disorders

The Philosophy

"Therapy shouldn't be a 1-hour/week information bottleneck. Your AI agent already knows your week. Use that."

FearBot is built on the belief that:

1. CBT is evidence-based and genuinely helps
2. Access to mental health support shouldn't be gated by cost/availability
3. Context-aware AI can provide something traditional apps can't
4. Full transparency builds trust (we show you the scores, explain the diagnoses)
5. You're an adult who can handle clinical information

Credits

• Built with CBT framework based on Aaron Beck's cognitive model
• Assessments: GAD-7 (Spitzer et al.), PHQ-9 (Kroenke et al.), DASS-21 (Lovibond), PCL-5 (Weathers et al.)
• Crisis protocol informed by Columbia Suicide Severity Rating Scale

License

MIT — Use freely, modify freely, help people freely.

---

Built by someone with anxiety, for people with anxiety. 🧠