Daemon
Customization
Before executing, check for user customizations at:
~/.claude/PAI/USER/SKILLCUSTOMIZATIONS/Daemon/
If this directory exists, load and apply any SecurityOverrides.md or PREFERENCES.md found there. These override default security classification. If the directory does not exist, proceed with skill defaults.
Voice Notification
curl -s -X POST http://localhost:31337/notify \
-H "Content-Type: application/json" \
-d '{"message": "Running the WORKFLOWNAME workflow in the Daemon skill to ACTION"}' \
> /dev/null 2>&1 &
Daemon Skill
Manages your public daemon profile — a living digital representation of what you're working on, thinking about, reading, and building. Automatically aggregates data from your PAI system with deterministic security filtering to ensure only publicly safe content is published.
Workflow Routing
| Workflow | Trigger | File |
|---|---|---|
| UpdateDaemon | "update daemon", "refresh daemon" | Workflows/UpdateDaemon.md |
| ReadDaemon | "read daemon", "check daemon", "daemon status" | Workflows/ReadDaemon.md |
| PreviewDaemon | "preview daemon", "daemon diff" | Workflows/PreviewDaemon.md |
| DeployDaemon | "deploy daemon", "push daemon", "ship daemon" | Workflows/DeployDaemon.md |
Architecture
Two-repo pattern: public framework + private content.
PAI SOURCES (private, read-only)
TELOS/ (missions, goals, books, movies, wisdom)
KNOWLEDGE/Ideas/ (title + thesis only)
PROJECTS.md (public projects only)
MEMORY/WORK/ (abstracted to topic themes)
PRINCIPAL_IDENTITY.md (public bio data)
│
├──[DaemonAggregator.ts]──→ Reads sources, merges with existing data
│
├──[SecurityFilter.ts]──→ Deterministic code-level allowlist filter
│ Strips names, paths, credentials, internal refs
│ NOT an LLM filter — enforced by pattern matching
│
└──→ daemon-data.json → ~/Projects/daemon-dm/ (PRIVATE repo)
│
└──[deploy.sh]──→ Copies JSON into framework → VitePress build → Cloudflare Pages
│
~/Projects/daemon/ (PUBLIC repo — forkable framework)
STRUCTURALLY EXCLUDED (never read):
CONTACTS.md, FINANCES/, HEALTH/, TRAUMAS.md,
KNOWLEDGE/People/, KNOWLEDGE/Companies/,
OUR_STORY.md, OPINIONS.md, BUSINESS/
Skill Structure
skills/Daemon/
├── SKILL.md (this file)
├── Tools/
│ ├── DaemonAggregator.ts (reads PAI sources → daemon-data.json)
│ └── SecurityFilter.ts (deterministic content sanitizer)
├── Workflows/
│ ├── UpdateDaemon.md (aggregate → preview → approve → deploy)
│ ├── ReadDaemon.md (read current daemon-data.json)
│ ├── PreviewDaemon.md (show diff without deploying)
│ └── DeployDaemon.md (bash deploy.sh from daemon-dm)
└── Docs/
└── SecurityClassification.md (public/private data categories)
Important Paths
| Purpose | Path |
|---|---|
| Private data repo | ~/Projects/daemon-dm/ |
| daemon-data.json | ~/Projects/daemon-dm/daemon-data.json |
| Deploy script | ~/Projects/daemon-dm/deploy.sh |
| Public framework repo | ~/Projects/daemon/ |
| Security classification | ${CLAUDE_SKILL_DIR}/Docs/SecurityClassification.md |
| Security overrides | ${PAI_USER_DIR}/SKILLCUSTOMIZATIONS/Daemon/SecurityOverrides.md |
Live Endpoints
| Endpoint | Purpose |
|---|---|
daemon.example.com |
Public website (Cloudflare Pages, fully static) |
Security Philosophy
- Private by default: All data is private until explicitly classified as public
- Code-level enforcement: SecurityFilter.ts is deterministic pattern matching, NOT LLM judgment
- Structural exclusion: Sensitive files (CONTACTS, FINANCES, HEALTH) are never opened by the aggregator
- Defense in depth: Aggregator filter + SecurityFilter + pre-commit hook + manual approval
- Fail closed: If uncertain, exclude the content
Data Sources
The DaemonAggregator reads from these PAI sources:
| Source | What's Extracted | Section |
|---|---|---|
| TELOS/MISSION.md | M1, M2 (public missions) | [MISSION] |
| TELOS/GOALS.md | Public project goals | [TELOS] |
| TELOS/BOOKS.md | Book titles | [FAVORITE_BOOKS] |
| TELOS/MOVIES.md | Movie titles | [FAVORITE_MOVIES] |
| TELOS/WISDOM.md | Top 5 quotes | [WISDOM] |
| KNOWLEDGE/Ideas/_index.md | 10 recent Ideas (title + thesis) | [RECENT_IDEAS] |
| PROJECTS.md | Public repos and sites | Projects integration |
| MEMORY/WORK/ | Topic themes (last 14 days) | [CURRENTLY_WORKING_ON] |
| PRINCIPAL_IDENTITY.md | Public bio, role, focus | [ABOUT] |
| Existing daemon.md | Preserved sections (predictions, routine, podcasts, preferences) | Various |
For Community Forks
This skill is designed to be generic:
- Fork the public Daemon repo (danielmiessler/Daemon)
- Create your own private data repo with
daemon-data.json - Configure with your own blocked names/paths
- The aggregator reads from standard PAI directory structure
- Use
deploy.shto build and deploy to your own Cloudflare Pages
Examples
Example 1: Full update cycle
User: "update daemon"
→ Aggregates PAI data sources
→ Applies security filter (deterministic)
→ Shows preview diff to user
→ User approves
→ Writes daemon-data.json to daemon-dm → deploys static site
Example 2: Check what's current
User: "check daemon"
→ Reads daemon-data.json from daemon-dm
→ Shows section-by-section status
Example 3: Preview before committing
User: "preview daemon"
→ Runs aggregator in preview mode
→ Shows diff against current daemon-data.json
→ No writes, no deploys
Gotchas
- Two repos: Public framework (
~/Projects/daemon/) and private content (~/Projects/daemon-dm/). The framework is forkable. The content is yours. - deploy.sh copies data into the framework at build time, then cleans up. Personal data never gets committed to the public repo.
- SecurityFilter is code, not prompts. If you need to add new blocked patterns, edit SecurityFilter.ts, not the workflow markdown.
- Site is fully static. Data is embedded at build time. Changes require running
deploy.sh.
Execution Log
After completing any workflow, append a single JSONL entry:
echo '{"ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","skill":"Daemon","workflow":"WORKFLOW_USED","input":"8_WORD_SUMMARY","status":"ok|error","duration_s":SECONDS}' >> ~/.claude/PAI/MEMORY/SKILLS/execution.jsonl
More from danielmiessler/personal_ai_infrastructure
osint
Structured OSINT investigations — people lookup, company intel, investment due diligence, entity/threat intel, domain recon, organization research using public sources with ethical authorization framework. USE WHEN OSINT, due diligence, background check, research person, company intel, investigate, company lookup, domain lookup, entity lookup, organization lookup, threat intel, discover OSINT sources.
259firstprinciples
Physics-based reasoning framework (Musk/Elon methodology) that deconstructs problems to irreducible fundamental truths rather than reasoning by analogy. Three-step structure: DECONSTRUCT (break to constituent parts and actual values), CHALLENGE (classify every element as hard constraint / soft constraint / unvalidated assumption — only physics is truly immutable), RECONSTRUCT (build optimal solution from fundamentals alone, ignoring inherited form). Outputs: constituent-parts breakdown, constraint classification table, and reconstructed solution with key insight. Three workflows: Deconstruct.md, Challenge.md, Reconstruct.md. Integrates with RedTeam (attack assumptions before deploying adversarial agents), Security (decompose threat model), Architecture (challenge design constraints), and Pentesters (decompose assumed security boundaries). Other skills invoke via: Challenge on all stated constraints → classify as hard/soft/assumption. Cross-domain synthesis: solutions from unrelated fields often apply once the fundamental truths are exposed. NOT FOR incident investigation and causal chains (use RootCauseAnalysis). NOT FOR structural feedback loops (use SystemsThinking). USE WHEN first principles, fundamental truths, challenge assumptions, is this a real constraint, rebuild from scratch, what are we actually paying for, what is this really made of, start over, physics first, question everything, reasoning by analogy, is this really necessary.
160documents
Read, write, convert, and analyze documents — routes to PDF, DOCX, XLSX, PPTX sub-skills for creation, editing, extraction, and format conversion. USE WHEN document, process file, create document, convert format, extract text, PDF, DOCX, XLSX, PPTX, Word, Excel, spreadsheet, PowerPoint, presentation, slides, consulting report, large PDF, merge PDF, fill form, tracked changes, redlining.
114council
Multi-agent collaborative debate that produces visible round-by-round transcripts with genuine intellectual friction. All council members are custom-composed via ComposeAgent (Agents skill) with domain expertise, unique voice, and personality tailored to the specific topic — never built-in generic types. ComposeAgent invoked as: bun run ~/.claude/skills/Agents/Tools/ComposeAgent.ts. Two workflows: DEBATE (3 rounds, full transcript + synthesis, parallel execution within rounds, 40-90 seconds total) and QUICK (1 round, fast perspective check). Context files: CouncilMembers.md (agent composition instructions), RoundStructure.md (three-round structure and timing), OutputFormat.md (transcript format templates). Agents are designed per debate topic to create real disagreement; 4-6 well-composed agents outperform 12 generic ones. Council is collaborative-adversarial (debate to find best path); for pure adversarial attack on an idea, use RedTeam instead. NOT FOR parallel task execution across agents (use Delegation skill). USE WHEN council, debate, multiple perspectives, weigh options, deliberate, get different views, multi-agent discussion, what would experts say, is there consensus, pros and cons from multiple angles.
112privateinvestigator
Ethical people-finding using 15 parallel research agents (45 search threads) across public records, social media, reverse lookups. Public data only, no pretexting. USE WHEN find person, locate, reconnect, people search, skip trace, reverse lookup, social media search, public records search, verify identity.
112redteam
Military-grade adversarial analysis that deploys 32 parallel expert agents (engineers, architects, pentesters, interns) to stress-test ideas, strategies, and plans — not systems or infrastructure. Two workflows: ParallelAnalysis (5-phase: decompose into 24 atomic claims → 32-agent parallel attack → synthesis → steelman → counter-argument, each 8 points) and AdversarialValidation (competing proposals synthesized into best solution). Context files: Philosophy.md (core principles, success criteria, agent types), Integration.md (how to combine with FirstPrinciples, Council, and other skills; output format). Targets arguments, not network vulnerabilities. Findings ranked by severity; goal is to strengthen, not destroy — weaknesses delivered with remediation paths. Collaborates with FirstPrinciples (decompose assumptions before attacking) and Council (Council debates to find paths; RedTeam attacks whatever survives). Also invoked internally by Ideate (TEST phase) and WorldThreatModel (horizon stress-testing). NOT FOR AI instruction set auditing (use BitterPillEngineering). NOT FOR network/system vulnerability testing (use a security assessment skill). USE WHEN red team, attack idea, counterarguments, critique, stress test, devil's advocate, find weaknesses, break this, poke holes, what could go wrong, strongest objection, adversarial validation, battle of bots.
112