### Vault Backend Configuration Examples Source: https://github.com/musonius-dev/praxis/blob/main/base/rules/vault.md Examples of search commands for different vault backends. Ensure the specified backend is running or installed. ```shell obsidian search query="{query}" limit=5 ``` ```shell rg --files-with-matches "{query}" {vault_path} ``` ```shell obsidian search query="{query}" path="01_Projects" limit=5 ``` ```shell rg --files-with-matches "{query}" {vault_path}/01_Projects ``` -------------------------------- ### Install Code Quality Kit Source: https://github.com/musonius-dev/praxis/blob/main/kits/code-quality/KIT.md Executes the installation script for the kit. ```bash bash ~/.claude/kits/code-quality/install.sh ``` -------------------------------- ### Install Praxis from source Source: https://context7.com/musonius-dev/praxis/llms.txt Clone the repository and run the bootstrap script for a symlinked development installation. ```bash # Clone repository git clone https://github.com/arcanesme/praxis.git cd praxis # Run bootstrap installer bash install.sh # Interactive prompts will configure: # - Obsidian vault path # - Identity settings (name, email, work/personal profiles) # - Optional MCP servers (Context7, Perplexity, GitHub) # - Optional quality tools (shellcheck, commitlint) ``` -------------------------------- ### Example Edit Commands Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-prompt/SKILL.md Examples of using the --edit flag to modify project prompts. ```bash /px-prompt --edit elect-azure "Add VITA SEC530 cybersecurity standard to domain expertise" ``` ```bash /px-prompt --edit maximus "Update CEO to new name" ``` ```bash /px-prompt --edit praxis "Add Python to tech stack" ``` -------------------------------- ### List Installed AI-Kits Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-kit/SKILL.md Lists all installed AI-Kits by reading their manifest files. Displays kit name, status, and associated domain. Cross-references with configuration for installation status. ```bash Kit Status Domain web-designer inactive Design system → components → accessibility → lint ``` -------------------------------- ### Set up Praxis for development Source: https://github.com/musonius-dev/praxis/blob/main/README.md Clones the repository and installs it using symlinks to allow for immediate reflection of local edits. ```bash git clone https://github.com/arcanesme/praxis.git cd praxis bash install.sh ``` -------------------------------- ### Manage Praxis installation via npx Source: https://context7.com/musonius-dev/praxis/llms.txt Use these commands to install, update, verify, or remove the Praxis harness. ```bash # Fresh install npx @esoteric-logic/praxis-harness@latest # Update existing installation npx @esoteric-logic/praxis-harness@latest update # Verify installation integrity npx @esoteric-logic/praxis-harness@latest health # Remove Praxis files from ~/.claude/ npx @esoteric-logic/praxis-harness@latest uninstall ``` -------------------------------- ### Output Format Example Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-doc-lint/SKILL.md Displays the expected output structure for the linting process. ```text px-doc-lint: {filename} Type: {Design Doc | ADR | README | General} [PASS] frontmatter valid [PASS] no trailing whitespace [BLOCK] missing required section: ## Tradeoffs [WARN] header level skip at: ### Details Result: BLOCK (1 error, 1 warning) ``` -------------------------------- ### Show Phase Transition Report Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-prompt/SKILL.md Example output of a successful phase advancement report. ```text PHASE ADVANCE: irs-masterfile ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Previous: Shaping Current: Mid Capture PAMASI: P → A (Approach stage) Deal Type: recompete Gate Check (Shaping → Mid Capture): I Customer & Mission ✓ GREEN XI Competitive ✓ GREEN II Architecture ○ Not yet scored (expected at Mid Capture) New Intel: • Draft RFP posted on SAM.gov (2026-03-15) • Industry day scheduled for April 20 • Amendment 1 added CMMC L2 requirement Updated Files: ✓ prompt-config.yaml (phase: Mid Capture) ✓ references/irs-masterfile-intel.md (new findings appended) ✓ space-instructions-perplexity.md (research domains updated) Next Gate: Pre-Proposal — requires all 11 GREEN at mid-capture level ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ ``` -------------------------------- ### Praxis Configuration File Source: https://context7.com/musonius-dev/praxis/llms.txt Example of the praxis.config.json file, which stores machine-specific configuration settings. ```json { "version": "3.6.0", "vault_path": "/Users/dev/Documents/Obsidian/DevVault", "vault_backend": "obsidian", "vault_name": "DevVault", "repo_path": "/Users/dev/repos/praxis", "installed_kits": ["web-designer", "api"], "identity": { "name": "Jane Developer", "role": "Senior Engineer", "domains": "cloud, security, APIs", "work": { "email": "jane@company.com", "path_match": "Projects/Work", "gitconfig": "~/.gitconfig-work", "ssh_key": "~/.ssh/id_ed25519_work" }, "personal": { "email": "jane@personal.com", "path_match": "Projects/Personal", "gitconfig": "~/.gitconfig-personal", "ssh_key": "~/.ssh/id_ed25519" } }, "installed_at": "2024-01-01T00:00:00Z", "updated_at": "2024-01-15T00:00:00Z" } ``` -------------------------------- ### List Installed AI-Kits Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-kit/SKILL.md Lists all installed AI-Kits by reading manifest files. It displays the kit name, its current status (active/inactive), and the domain it applies to. It also cross-references with the Praxis configuration file to show the installation status. ```APIDOC ## /kit:list ### Description List all installed kits by reading `~/.claude/kits/*/KIT.md` manifests. Print a table showing the Kit name, Status, and Domain. ### Method GET ### Endpoint /kit:list ### Parameters None ### Response #### Success Response (200) - **kits** (array) - A list of installed kits, each with `name`, `status`, and `domain`. ### Response Example ```json { "kits": [ { "name": "web-designer", "status": "inactive", "domain": "Design system → components → accessibility → lint" } ] } ``` ``` -------------------------------- ### Install Praxis Harness Source: https://github.com/musonius-dev/praxis/blob/main/README.md Initializes the Praxis harness by copying rules, commands, skills, and kits to the local environment. Requires Node.js 18+. ```bash npx @esoteric-logic/praxis-harness@latest ``` -------------------------------- ### Example Deal Confirmation Card Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-prompt/SKILL.md This is an example of the confirmation card displayed after research findings are processed, showing key deal details and created files. ```text DEAL: irs-masterfile ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Agency: IRS (from USASpending) Program: Individual Masterfile Modernization Incumbent: Accenture Federal Services (from FPDS) Value: $2.1B ceiling (from SAM.gov) Type: recompete (auto-detected — incumbent found) Phase: Mid Capture NAICS: 541512 Vehicle: GSA Alliant 2 Status: Active — recompete expected FY2026 Confidence: HIGH (SAM.gov + FPDS data) Maximus PP: 2 contracts at IRS (from USASpending) Gaps: Key personnel [RESEARCH NEEDED] ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Files created: ✓ system-prompt.md (2,480 chars) — compiled from profile ✓ space-instructions-perplexity.md (3,976 chars) — deal-specific research domains ✓ references/irs-masterfile-intel.md ✓ knowledge/maximus-corporate.md ✓ knowledge/maximus-corporate.md [Deploy] [Advance phase] [Edit intel] [Re-research] ``` -------------------------------- ### Bootstrap Instructions for Resuming After Compaction Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-compact/SKILL.md These instructions guide the user on how to re-bootstrap the session after compaction has been triggered. It involves reading the checkpoint, active plan, specific files, and resuming the defined next step. ```text Compact checkpoint saved. Triggering compaction. After compaction, re-bootstrap: 1. Read {vault_path}/plans/{YYYY-MM-DD}-compact-checkpoint.md 2. Read the active plan: {plan-filename}, milestone: {milestone-name} 3. Re-read only files listed in "Active Working Set" above 4. Resume: {next step} ``` -------------------------------- ### Vault Output Path Example Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-complexity-audit/SKILL.md Example of the output path for the debt audit when run with `--write-vault` or during a quarterly scan. The filename includes the current date. ```plaintext Output path: {vault_path}/specs/debt-audit-{YYYY-MM-DD}.md ``` -------------------------------- ### Structured Debugging Source: https://context7.com/musonius-dev/praxis/llms.txt Initiates a test-first debugging workflow. Includes an example of a failing test case for Go. ```bash # Start structured debugging /px-debug ``` ```go func TestCreateUser_EmptyInput(t *testing.T) { resp := makeRequest("POST", "/api/users", "{}") assert.Equal(t, 400, resp.StatusCode) } ``` -------------------------------- ### Infrastructure Kit Example: KIT.md Frontmatter Source: https://github.com/musonius-dev/praxis/blob/main/docs/creating-a-kit.md Manifest frontmatter for an infrastructure kit, detailing its name, version, description, activation, deactivation, and a planned skills chain for different phases. ```yaml --- name: infrastructure version: 1.0.0 description: Infrastructure as Code — Terraform, Azure, compliance, drift detection activation: /kit:infrastructure deactivation: /kit:off skills_chain: - phase: plan skills: [] status: planned - phase: apply skills: [] status: planned --- ``` -------------------------------- ### AI-Kit Directory Structure Source: https://github.com/musonius-dev/praxis/blob/main/docs/architecture.md Defines the standard directory structure for an AI-Kit, including manifest, installation scripts, and domain-specific rules and commands. ```bash ~/.claude/kits// KIT.md ← Manifest install.sh ← Dependency installation teardown.sh ← Clean removal rules/ ← Domain-specific rules commands/ ← Domain slash commands ``` -------------------------------- ### Vault Search Commands Source: https://context7.com/musonius-dev/praxis/llms.txt Provides examples for searching the project vault using different backends. The Obsidian backend requires Obsidian to be running, while Ripgrep is a fallback. ```bash # Vault search (automatic in /discuss, /discover) # Uses configured backend from praxis.config.json # Obsidian backend (requires Obsidian running): obsidian search query="circuit breaker" limit=5 # Ripgrep fallback: rg --files-with-matches "circuit breaker" {vault_path}/ # Search is non-blocking — warns and continues if backend unavailable ``` -------------------------------- ### Manage Praxis Installation Source: https://github.com/musonius-dev/praxis/blob/main/README.md Commands for maintaining, verifying, or removing the Praxis installation. ```bash npx @esoteric-logic/praxis-harness@latest update # re-copy from latest npm version npx @esoteric-logic/praxis-harness@latest health # verify install integrity npx @esoteric-logic/praxis-harness@latest uninstall # remove Praxis-owned files from ~/.claude/ ``` -------------------------------- ### Deploy Platform Sequentially Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-prompt/SKILL.md A template for deploying deal configurations to Claude Projects, Perplexity Spaces, and Claude Code. ```text DEPLOY: dha-tricare ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ [1/3] Claude Projects → Copied system-prompt.md to clipboard (5,824 chars) → Paste at: claude.ai/projects → Set project instructions Upload these as project knowledge files: references/dha-tricare-intel.md (deal intelligence) knowledge/maximus-corporate.md (corporate reference) Press Enter when done... [2/3] Perplexity Spaces → Copied space-instructions-perplexity.md to clipboard (3,965 chars) → Paste at: perplexity.ai → Space Settings → Answer Instructions Upload these as Space sources (Add Sources → Files): references/dha-tricare-intel.md (deal intelligence) knowledge/maximus-corporate.md (corporate reference) Press Enter when done... [3/3] Claude Code → Copied claude-code.md to clipboard (1,842 chars) → Paste as CLAUDE.md in repo root, or push directly Press Enter when done... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ DEPLOYED to 3 platforms. Knowledge files uploaded to Claude Projects and Perplexity Spaces. CLAUDE.md ready for repo. ``` -------------------------------- ### Perplexity Research Query Example Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-prompt/SKILL.md An example query to gather current best practices and standards for a given domain, focusing on recent changes. ```text perplexity_ask: "What are the current best practices and standards for [domain] in 2025-2026? Focus on changes since [last updated date]. Key terminology updates, new frameworks, deprecated standards." ``` -------------------------------- ### Create Project Directory Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-prompt/SKILL.md Use this command to create the necessary directory structure for a new project. ```bash mkdir -p prompts/projects//references ``` -------------------------------- ### Install Script for Dependencies Source: https://github.com/musonius-dev/praxis/blob/main/docs/creating-a-kit.md Shell script to install external dependencies for the AI-Kit, including npm skills and MCP servers. Uses 'set -euo pipefail' for robust error handling. ```bash #!/bin/bash set -euo pipefail echo "=== Praxis: Installing my-kit ===" # npm skills npx skills add author/skill-name -g -y # MCP servers claude mcp add server-name npx -- -y @scope/package@latest echo "=== my-kit installed ===" ``` -------------------------------- ### Technical Discovery Source: https://context7.com/musonius-dev/praxis/llms.txt Starts the structured technical discovery process. ```bash # Run technical discovery /px-discover ``` -------------------------------- ### Run project development and maintenance commands Source: https://github.com/musonius-dev/praxis/blob/main/prompts/personal/praxis/claude-code.md Use these commands to check the project entry point and execute linting scripts. ```bash dev: node --check bin/praxis.js test: node --check bin/praxis.js lint: bash scripts/lint-harness.sh . ``` -------------------------------- ### Render Knowledge Packs Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-prompt/SKILL.md Use this command to render the knowledge packs for the project. ```bash node bin/prompt-knowledge.js ``` -------------------------------- ### Compile Project Prompts Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-prompt/SKILL.md This command compiles the project prompts after configuration and intel files are written. ```bash node bin/prompt-compile.js ``` -------------------------------- ### Verify Praxis installation Source: https://context7.com/musonius-dev/praxis/llms.txt Check that Praxis is correctly loaded and available within a Claude Code session. ```bash # In Claude Code session /help # Should show Praxis skills: # /px-discuss, /px-plan, /px-execute, /px-verify, /px-ship, /px-kit:* # List available AI-Kits /px-kit:list # Check health status npx @esoteric-logic/praxis-harness@latest health ``` -------------------------------- ### Initialize Git Repository Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-scaffold-new/SKILL.md Initializes a new git repository and performs the first commit with the scaffolded CLAUDE.md file. ```bash git init {repo_root} git -C {repo_root} add CLAUDE.md git -C {repo_root} commit -m "chore: initialize project scaffold" ``` -------------------------------- ### Compile All Projects with Diff Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-prompt/SKILL.md Use this command to recompile all projects, including a diff to show changes. Triggered by the /px-prompt --sync command. ```bash node bin/prompt-compile.js --all --diff ``` -------------------------------- ### Commit Message Format Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-ship/SKILL.md Example of a conventional commit message structure. Use this format for clarity and consistency. ```markdown ``` {type}({scope}): {short description} {optional body — what changed and why, not how} ``` ``` -------------------------------- ### Execute /px-plan workflow Source: https://context7.com/musonius-dev/praxis/llms.txt Generate a structured work plan with milestones and dependencies based on the SPEC block. ```bash # Create a plan (consumes SPEC from /discuss) /px-plan # Claude will: # 1. Read SPEC block from conversation or vault # 2. Build milestone list with dependencies # 3. Validate boundaries and checkpoints # 4. Recommend execution_type (tdd | execute | research) # 5. Write to vault: {vault_path}/plans/YYYY-MM-DD_task-slug.md # Example plan structure: # --- # tags: [plan, my-project] # date: 2024-01-15 # status: active # execution_type: tdd # --- # # Plan: Add Circuit Breaker # # ## Objective # Implement circuit breaker pattern for external API calls. # # ## Milestones # - [ ] M1: Define circuit breaker interface — 2024-01-15 # - [ ] M2: Implement breaker logic — 2024-01-16 | depends_on: M1 # - [ ] M3: Add retry with backoff — 2024-01-16 | depends_on: M2 | checkpoint: decision # - [ ] M4: Integration tests — 2024-01-17 | depends_on: M3 | checkpoint: human-verify # # ## Boundaries # - DO NOT CHANGE: auth/, database/, config/ # Output: # ✓ Plan created: /vault/plans/2024-01-15_circuit-breaker.md # ✓ status.md: current_plan updated # ✓ progress.json: milestone added ``` -------------------------------- ### Display Reset Instructions Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-context-reset/SKILL.md Output provided to the user after a successful checkpoint to guide the session resumption process. ```text Context checkpoint saved to: Checkpoint: {vault_path}/plans/{YYYY-MM-DD}-context-checkpoint.md Status: {vault_path}/status.md Progress: {vault_path}/claude-progress.json Run /clear to reset context, then paste this bootstrap prompt: Context reset. Bootstrap: 1. Read project CLAUDE.md 2. Read {vault_path}/plans/{current-plan} 3. Read {vault_path}/plans/{YYYY-MM-DD}-context-checkpoint.md 4. Resume from milestone: {milestone-name} ``` -------------------------------- ### Initialize and Execute Terraform Plan Source: https://github.com/musonius-dev/praxis/blob/main/kits/infrastructure/commands/infra-plan.md Initializes the working directory and generates a plan file with detailed exit codes for automation. ```bash terraform init -input=false terraform plan -out=tfplan -detailed-exitcode ``` -------------------------------- ### Manage MCP Servers via CLI Source: https://github.com/musonius-dev/praxis/blob/main/docs/mcp-servers.md Commands for installing, listing, and removing MCP servers in the Praxis environment. ```bash # Install all (interactive) bash scripts/onboard-mcp.sh all # Install a specific server bash scripts/onboard-mcp.sh context7 bash scripts/onboard-mcp.sh perplexity bash scripts/onboard-mcp.sh github # Check registered servers claude mcp list # Remove a server claude mcp remove ``` -------------------------------- ### Verify Kit Links Source: https://github.com/musonius-dev/praxis/blob/main/docs/runbook.md Lists the contents of the kits directory to verify symlink creation. ```bash ls -la ~/.claude/kits/ ``` -------------------------------- ### Execute /px-discuss workflow Source: https://context7.com/musonius-dev/praxis/llms.txt Initiate the problem framing phase to synthesize scope and deliverables. ```bash # Start the discuss phase /px-discuss # Claude will: # 1. Load minimal context (vault status, project detection) # 2. Ask "What are we working on?" # 3. Search vault for related prior work # 4. Clarify gaps in PROBLEM/DELIVERABLE/ACCEPTANCE/BOUNDARIES # 5. Synthesize a SPEC block # Example SPEC output: # SPEC # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ # PROBLEM: API rate limiting causes cascade failures # DELIVERABLE: Circuit breaker with exponential backoff # ACCEPTANCE: - Unit tests pass # - Load test shows 99.9% success rate # BOUNDARIES: # In: API client module only # Out: Database layer, authentication # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ # Handoff: "Run /plan to continue, or /spec if this needs a design spec first." ``` -------------------------------- ### Update an AI-Kit Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-kit/SKILL.md Updates a specified AI-Kit to its latest version by running its installation script and updating the Praxis configuration file. ```APIDOC ## /kit:update ### Description Updates a specified AI-Kit to its latest version by running its installation script and updating the Praxis configuration file. ### Method POST ### Endpoint /kit:update ### Parameters #### Path Parameters - **name** (string) - Required - The name of the AI-Kit to update. ### Request Body None ### Request Example ```json { "action": "update" } ``` ### Response #### Success Response (200) - **message** (string) - Report on the update results. ### Response Example ```json { "message": "Kit 'web-designer' updated successfully." } ``` ``` -------------------------------- ### Praxis CLI Quick Reference Commands Source: https://github.com/musonius-dev/praxis/blob/main/README.md Commonly used commands for project creation, deal management, and system maintenance. ```bash /px-prompt my-project /px-prompt --deal irs-masterfile /px-prompt --deal benefeds --type recompete /px-prompt --advance irs-masterfile /px-prompt --edit my-project "add NIST 800-53" /px-prompt --refresh my-project /px-prompt --deploy my-project /px-prompt --dashboard /px-prompt --sync /px-prompt --scan my-project ``` -------------------------------- ### Update AI-Kit Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-kit/SKILL.md Updates a specified AI-Kit by running its installation script and updating the configuration file. Reports the results of the update process. ```bash ~/.claude/kits//install.sh ``` -------------------------------- ### Invoke PSScriptAnalyzer Lint Source: https://github.com/musonius-dev/praxis/blob/main/base/rules/powershell.md Runs PSScriptAnalyzer to check for warnings and errors in PowerShell scripts. Ensure PSScriptAnalyzer is installed for this command to work. ```powershell # PSScriptAnalyzer lint (if installed) Invoke-ScriptAnalyzer -Path . -Recurse -Severity Warning,Error ``` -------------------------------- ### Deploy Project Outputs Source: https://github.com/musonius-dev/praxis/blob/main/base/skills/px-prompt/SKILL.md Command to deploy project outputs to various platforms like Claude Projects and Perplexity Spaces. ```bash /px-prompt --deploy ```