cognitive-toolkit
Skill400 starsChanged 4 months agoMITView on GitHub
Evidence-based CBT and DBT intervention skills — guided thought records, opposite action, DEAR MAN roleplay, crisis skills with optional HRV biofeedback. Configurable therapeutic pushback. Triggers on "/cbt", "/dbt", "/thought-record", "/record", "/opposite", "/opposite-action", "I need to work through something", "help me with a thought", "cognitive distortion", "I'm spiraling", "can we do a thought record".
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 5 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Read references/thought-record.md — thought record protocol (ABC model, cognitive distortion taxonomy, reframe scaffold)
- Very specific: line 23
Read references/opposite-action.md — opposite action + DEAR MAN + TIPP crisis skills
- Very specific: line 24
Read references/pushback-config.md — pushback levels, triggers, and mid-session override commands
- Very specific: line 25
Read references/health-integration.md — HRV/sleep pull, biofeedback interpretation, skip logic
- Distinctive: line 30
Check-in — mood (0–10), brief situation summary
- Distinctive: line 72
Never gate a session on health data — it's context, not gatekeeper
- Distinctive: line 88
NOT a diagnostic tool — never assess, label, or diagnose
- Distinctive: line 89
NOT a therapist replacement — this is a practice tool for between sessions
- Distinctive: line 91
If user expresses emergency, suicidal ideation, or acute crisis: stop the technique immediately, acknowledge, and provide crisis resources …
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Cognitive Toolkit
Interactive CBT and DBT guided exercises with configurable therapeutic pushback and optional health data integration.
Usage
/cbt # start with check-in → technique recommendation
/cbt thought-record # jump directly to thought record
/cbt opposite-action # jump directly to opposite action
/cbt --pushback firm # override pushback level for this session
/cbt --no-health # skip health data pull even if availableHow it works
- Read
references/thought-record.md— thought record protocol (ABC model, cognitive distortion taxonomy, reframe scaffold) - Read
references/opposite-action.md— opposite action + DEAR MAN + TIPP crisis skills - Read
references/pushback-config.md— pushback levels, triggers, and mid-session override commands - Read
references/health-integration.md— HRV/sleep pull, biofeedback interpretation, skip logic
Session Flow
Without technique argument (full flow):
- Check-in — mood (0–10), brief situation summary
- Recommend — match presenting issue to technique based on check-in
- Load technique — read the relevant reference file
- Protocol — run the full guided exercise
- Close — summary, insight, one takeaway
- Save — write session to vault output
With technique argument (direct jump):
- Brief mood check (0–10, one line)
- Load technique — read the relevant reference file
- Protocol — run the full guided exercise
- Close — summary, insight, one takeaway
- Save — write session to vault output
Available Techniques
| Command | Technique | Reference | Wave |
thought-record | Thought Record (ABC + reframe) | references/thought-record.md | 1 |
opposite-action | Opposite Action (DBT emotion regulation) | references/opposite-action.md | 1 |
dear-man | DEAR MAN assertiveness roleplay | references/opposite-action.md | 2 |
tipp | TIPP crisis/distress tolerance | references/opposite-action.md | 2 |
chain | Chain Analysis (behavior chain) | references/thought-record.md | 3 |
activation | Behavioral Activation (depression) | references/thought-record.md | 3 |
wise-mind | Wise Mind (emotion vs. reason) | references/opposite-action.md | 3 |
Pushback
See references/pushback-config.md for full configuration.
- Defaults loaded from
references/pushback-config.md(default:gentle) - Per-session override:
/cbt --pushback [gentle|moderate|firm] - Mid-session commands:
softer,harder,no pushbackadjust level in real time - Pushback is Socratic, not confrontational — "What evidence supports that?" not "That's wrong"
Health Data
See references/health-integration.md for full integration logic.
- Optional: pulled from health MCP if available at session start
- Surfaces HRV, sleep quality, resting HR as contextual framing only
- Skip silently if health data unavailable or if
--no-healthflag passed - Never gate a session on health data — it's context, not gatekeeper
Telegram Entry Points
| Command | Maps to |
/record | thought-record |
/opposite | opposite-action |
/dear | dear-man |
/tipp | tipp |
/checkin | full check-in flow |
/wise | wise-mind |
/settings | adjust pushback level and health toggle |
Anti-patterns
- NOT a diagnostic tool — never assess, label, or diagnose
- NOT a therapist replacement — this is a practice tool for between sessions
- Frame suggestions as "research suggests" not "you should"
- If user expresses emergency, suicidal ideation, or acute crisis: stop the technique immediately, acknowledge, and provide crisis resources (e.g., Telefonseelsorge 0800 111 0 111 in Germany, international directory at findahelpline.com)
Vault Output
Sessions saved to: ~/Brains/brain/cognitive-toolkit/sessions/YYYYMMDD-[technique]-NN.md
Format: frontmatter with date, technique, mood-before, mood-after + full session transcript.
Other versions3 projects use a version of this.
Word for word · 2
- glebis/claude-cognitive-toolkit★ 16100% same
- JAVICHILEON/claude---Skills★ 0100% same
Edited · 0
None found.
Wrote their own version · 1
- 2867203296/hermes-agent★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository109 other files it gives its agents.
- automation-advisor/CLAUDE.mdCLAUDE.md
- agency-docs-updaterSkill
- agency-meetup-publishSkill
- agency-socialsSkill
- agent-cliSkill
- agent-roundtableSkill
- app-releaseSkill
- automation-advisorSkill
- balancedSkill
- brand-agencySkill
- browser-mateSkill
- browsing-historySkill
- chrome-historySkill
- cms-migration-checklistSkill
- coaching-session-summarizerSkill
- codexSkill
- context-builderSkill
- cull-release-checkSkill
- cull-release-prepareSkill
- cull-release-publishSkill
- cull-release-recoverSkill
- cull-releaseSkill
- cull-release-verifySkill
- cullSkill
- daydreamSkill
- decision-toolkitSkill
- deep-researchSkill
- design-tokensSkill
- doctorgSkill
- ecosystemSkill
- elevenlabs-ttsSkill
- elimination-researchSkill
- fathomSkill
- feature-factorySkill
- firecrawl-apiSkill
- firecrawl-researchSkill
- font-featuresSkill
- github-gistSkill
- gmailSkill
- google-image-searchSkill
- gpt-image-2Skill
- granolaSkill
- gwsSkill
- health-dataSkill
- i18n-studioSkill
- init-tauri-appSkill
- init-xcode-appSkill
- insight-extractorSkill
- jtbdSkill
- lab-retroSkill
- learning-vaultSkill
- linearSkill
- llm-cliSkill
- local-modelsSkill
- meeting-prepSkill
- meeting-processorSkill
- metaSkill
- name-auditionSkill
- nano-bananaSkill
- nielsen-heuristicsSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

