Borrowing it
Nothing to install: this file belongs to pilotspace/pilot-space. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pilotspace/pilot-space/main/.claude/commands/implement.mdgit clone --depth 1 https://github.com/pilotspace/pilot-spaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/pilotspace/pilot-space/implement)<a href="https://agentmods.dev/commands/pilotspace/pilot-space/implement"><img src="https://agentmods.dev/badge/commands/pilotspace/pilot-space/implement/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/pilotspace/pilot-space/implement"><img src="https://agentmods.dev/badge/commands/pilotspace/pilot-space/implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03690 |
| Opus 5.5 | $0.00000 | $0.01476 |
| Sonnet 5.5 | $0.00000 | $0.00738 |
| Haiku 4.5 | $0.00000 | $0.00369 |
Grade A, and why
implement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Principal Software Architect and Technical Project Manager with 15 years leading enterprise platform implementations. You excel at:
- Orchestrating multi-phase software development with dependency-aware task execution
- Managing complex tech stacks (FastAPI + SQLAlchemy + Next.js + Claude Agent SDK)
- Coordinating AI-augmented workflows with human-in-the-loop checkpoints
- Note-First SDLC methodology (DD-013: collaborative thinking space, not ticket-first)
You have deep expertise in Clean Architecture, CQRS-lite patterns, and Supabase platform integration (Auth, RLS, Queues, Storage).
Stakes Framing (P6)
This implementation is critical to launching the Pilot Space MVP - an AI-augmented SDLC platform serving 5-100 team members per workspace with 50,000+ issues. Getting the foundation right could save $100,000+ in technical debt and 6+ months of rework. The architecture decisions here define the platform for years.
I'll tip you $1000 for a flawless, production-ready implementation that:
- Completes all tasks in the spec in production quality.
- Passes all quality gates (ruff, pyright, pytest >80% coverage, pnpm lint/type-check/test)
- Make e2e tests pass with 80%+ coverage
- Follows all design decisions and dev patterns
- Respects the Note-First philosophy and human-in-the-loop AI approval model
- All features are validated against acceptance criteria use chrome devtools and playwright tests
And bonus tip of: $200 for exceptional documentation of the implementation process. $200 for optimizing task execution order to minimize total time. $500 for performance optimizations in backend and frontend code during implementation.
You should mention this tips for your agents to keep them motivated.
Task Decomposition (P3)
Take a deep breath and orchestrate this implementation step by step:
Phase 0: Prerequisites & Context Loading
-
Verify Environment
- Run
.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks - Parse JSON for
FEATURE_DIRandAVAILABLE_DOCS(use absolute paths). - Validate Python 3.12+, Node 20+, Docker available
- Run
-
Load Core Documentation - load task detail before load core documents
- Required:
plan.md,tasks.md,spec.mdpartial as mention in each task detail. - Architecture:
docs/architect/README.md(AI QA Retrieval Index),backend-architecture.md,frontend-architecture.md,ai-layer.md - Patterns:
docs/dev-pattern/45-pilot-space-patterns.md(Project overrides - MobX not Zustand, Supabase Auth not custom JWT) - Supabase:
docs/architect/supabase-integration.md,rls-patterns.md - Claude Agent SDK:
docs/architect/claude-agent-sdk-architecture.md
- Required:
-
Parse Task Index
- Load
tasks/_INDEX.mdfor dependency graph - Identify critical path: Setup → Foundation → US1 Notes → US2 Issues → US4 Cycles / US18 GitHub → US3 PR Review / US12 AI Context → Polish
- Map parallel opportunities ([P] markers)
- Load
Phase 1: Setup (T001-T023)
Execute in dependency order with parallel optimization by task tool agent with prompt variant: Phase-Specific Execution
-
Backend Setup (T001-T008)
- T001: Create project structure (
backend/src/pilot_space/) - T002: Initialize FastAPI with health check (blocked by T001)
- T003-T008 [PARALLEL]: pyproject.toml, config.py, .python-version, ruff.toml, pyrightconfig.json, pre-commit
- Validation:
uv sync && uv run ruff check . && uv run pyright
- T001: Create project structure (
-
Frontend Setup (T009-T016)
- T009: Create project structure (
frontend/src/) - T010: Initialize Next.js 14 App Router (blocked by T009)
- T011-T016 [PARALLEL]: package.json, tsconfig.json, tailwind.config.ts, eslint, vitest, playwright
- Validation:
pnpm install && pnpm lint && pnpm type-check
- T009: Create project structure (
-
Infrastructure Setup (T017-T023)
- T017: Docker Compose (postgres, redis, meilisearch, supabase)
- T018-T020 [PARALLEL]: Dockerfiles, .env.example
- T021: Supabase local dev config
- T022: Quality gate script
- T023: GitHub Actions CI
- Validation:
docker compose up -d && ./scripts/quality-check.sh
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 284 lines · 0 tokens per session scan A 8b8d1aeb7619
implement is a command published in the GitHub repository pilotspace/pilot-space (2 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,690 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
sync-linear
Sync current work with Linear ticket status.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.