13 stack profiles, 9 mechanical hooks, 9 MCP servers, 8 AI adapters. Everything you need to configure, extend, and debug Tasuki (襟).
.tasuki/, initializes the knowledge graph, and translates to your target AI tool. Takes ~10 seconds..tasuki/ directory structure without scanning. Use when you want to manually configure agents. --minimal creates only essential files.{{PLACEHOLDERS}}, agent frontmatter parseable, hooks executable, capability map consistent..tasuki/agents/ and regenerates the capability map. The Planner will automatically see and route tasks to the new agent on the next pipeline run..tasuki/skills/ and exposes it as a /command in your AI tool. Skills can be auto-triggered in specific pipeline stages or invoked manually..tasuki/ to the target AI tool's format. Can be run after onboarding to add support for a second tool, or after any agent/rule changes.memory-vault/, parses wikilinks, indexes content into local SQLite for vector search. Run after manually editing vault files.--agent to filter by agent tag.memory-vault/ directory structure with all node type subdirectories. Typically called automatically during tasuki onboard.--agent to filter by agent tag.--dry-run to preview what would change.project-facts.md's "Do NOT" section. Every run of the specified agent will see this before starting.--generate to regenerate the static HTML dashboard without opening the browser.--dry-run to preview what would be removed. Cleanup is user-driven — Tasuki never auto-removes.Detection runs entirely in bash — no API calls. Reads actual imports, package files, and directory structure. Not guessing.
from fastapi import in py filesfastapi in requirements.txtdjango.db.models importsmanage.py + settings.pyfrom flask import Flaskflask in requirements.txtnext in package.jsonapp/ or pages/ directory@sveltejs/kit in package.jsonsvelte.config.jssrc/routes/ directorynuxt in package.jsonnuxt.config.tspages/ or app.vueexpress in package.jsonapp.listen( in JS/TS@nestjs/core in package.json@Module decoratorsrails in Gemfileconfig/routes.rbdb/migrate/ directorygin-gonic/gin in go.modgin.Default() in Go filesspring-boot in pom.xml@SpringBootApplicationlaravel/framework in composer.jsonartisan file presentdatabase/migrations/Hooks intercept every Write/Edit call via PreToolUse. Exit code 2 blocks the action. No bypass, no workaround. These are the mechanical enforcement layer — the discipline pillar of Tasuki.
password = "test123"), placeholder comments (# TODO: use env var), or documentation examples. Only real production code patterns.
.tasuki/config/protected-files.txt, which is populated with stack-specific entries during onboard..tasuki/agents/{agent}.md). Ensures every agent operates from its full role definition and memory before making changes.tasuki-plans/{feature}/plan.md exists, implementation code cannot be written. Forces the Planner stage to complete before any code is generated. Skipped in fast mode.When you run tasuki install mcp X, it shows you exactly which stages and agents it connects to.
| MCP | Stage | Agent(s) | Purpose |
|---|---|---|---|
| Taskmaster | 1b | Planner | Parse PRD into per-agent tasks (~50 tokens each vs 2000 for full PRD) (native coordination in Agent Teams, MCP for other tools) |
| Context7 | ALL | All agents | Up-to-date framework documentation — prevents hallucinated API usage |
| Playwright | 2, 5 | QA, Frontend | E2E testing automation and visual regression testing |
| Postgres | 3, 5.5 | DB Architect, Debugger | Schema inspection, data diagnostics, query analysis |
| Figma | 5a | Frontend | Pull design specs directly — exact colors, spacing, component specs |
| Stitch | 5a | Frontend | Generate design preview when no Figma file exists |
| Semgrep | 6, 7 | Security, Reviewer | Static analysis — patterns the human eye misses at scale |
| Sentry | 5.5, 6, 8 | Debugger, Security, DevOps | Error tracking, exception correlation, health checks after deploy |
| GitHub | 7, 8 | Reviewer, DevOps | PR creation, CI status, branch protection checks |
Tasuki's internal format (.tasuki/) is AI-agnostic. Adapters translate to each platform. Claude Code gets the most — it's the only tool with native Agent Teams.
Adapters automatically translate model references. "thinking" and "execution" are tiers, not hardcoded model names.
| Tier | Claude Code | Codex CLI | Gemini CLI | Cursor |
|---|---|---|---|---|
| thinking | claude-opus-4 | o3 | gemini-2.5-pro | claude-sonnet-4 |
| execution | claude-sonnet-4 | o4-mini | gemini-2.5-flash | claude-sonnet-4 |
Running tasuki onboard . on a Django project generates this structure in ~10 seconds. Zero API calls.
tasuki (onboard), tasuki dashboard, and tasuki progress. The rest are power-user tools for debugging, team workflows, and plugin management. Think of it like git — 150+ commands, you use 5.requirements.txt, package.json, and config files. Frontend detector looks for React/Vue/Svelte patterns. Infra detector finds Docker/CI configs. Testing detector finds test frameworks and coverage tools. Everything verified from real files, not guessed.settings.json as PreToolUse events. When Claude tries to Edit or Write a file, the hook script runs first. Exit 0 = allow, exit 2 = block with message. Claude Code enforces this mechanically — the AI cannot bypass it. The 9 hooks: pipeline-trigger (activates on "tasuki"), pipeline-tracker (tracks stages), tdd-guard (blocks edits without tests), security-check (blocks anti-patterns), protect-files (blocks .env/secrets), force-agent-read (blocks edits without reading agent file), force-planner-first (blocks implementation without a plan), teammate-idle (fires when an Agent Teams teammate finishes its task), task-completed (fires when a shared task is marked complete). On other tools: hooks become advisory rules — strongly worded but not physically enforced.tasuki onboard . --target=all and it generates config for all 8 tools simultaneously. Each adapter writes to its own location (CLAUDE.md, .cursor/rules/, .windsurfrules, etc.). They share the same .tasuki/ directory, memory vault, and plans.localhost:8686 with: pipeline progress with animated agent characters, interactive D3.js knowledge graph, cost-per-task table, health score breakdown, agent usage charts, mode distribution, and an activity log showing errors prevented and heuristics applied. Auto-updates when pipeline state changes.tasuki install mcp playwright adds it to .mcp.json and tells you which pipeline stages use it ("Stage 2 QA + Stage 5 Frontend"). tasuki install agent mobile-dev creates the agent file and auto-registers it in the capability map. tasuki plugins shows the full catalog (23 MCPs, 11 skills).Everything above is what you get when you run tasuki onboard .