By notwld
Plan-first existing-project adoption plus production full-stack and security engineering with automatic Ponytail, Superpowers, and Impeccable dependencies.
Safely adopt, audit, production-harden, restructure, or refactor an existing application after Engineering Baseline is installed. Use on first run when `.engineering-baseline-lock.json` has `adoption.status: pending`, and whenever a user asks to make an existing repository production-ready, apply all baseline/security frameworks, correct its directory structure, reduce complexity with Ponytail, or introduce Superpowers without breaking behavior. Begin with read-only context gathering, present findings and required questions, and make no project changes until the user explicitly approves a proposed plan.
Apply a risk-proportionate engineering baseline to software planning, implementation, debugging, review, and verification in any language or stack. Use for coding tasks, project changes, bug fixes, refactoring, and code review; route to installed Ponytail, Superpowers, Impeccable, and Security Review skills when their narrower triggers match.
Design, scaffold, implement, review, and verify production-grade full-stack applications and substantial backend or frontend features. Use when creating an app, API, backend, frontend, dashboard, service, worker, queue, database-backed feature, or production deployment. Enforce scalable API/worker architecture, bounded concurrency, queues, caching, pagination, audit logging, rate limits, Docker and Docker Compose, environment and secret hygiene, consistent reusable UI, understandable end-to-end errors, documentation updates, code review, and production-readiness evidence.
Perform mandatory feature-level threat modeling and security verification using STRIDE, OWASP ASVS 5.0.0 Level 2, OWASP Top 10:2025, NIST CSF 2.0, and NIST SP 800-207 Zero Trust. Use for every new feature and material behavior change, and for reviews involving authentication, authorization, trust boundaries, APIs, untrusted input, sensitive data, secrets, cryptography, files, external URLs, dependencies, infrastructure, logging, or deployment. State mitigations before implementation and verify controls afterward.
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A portable, extensible engineering baseline for Cursor and Claude Code.
It installs these pinned skill bundles automatically:
Paste this into Cursor or Claude Code:
Install the engineering baseline from:
https://github.com/notwld/engineering-baseline
Clone it into a temporary directory, read INSTALL.md, follow its installation
contract for the current project, validate the result, and report every file
changed. Do not modify application source code.
From the target project's root:
git clone https://github.com/notwld/engineering-baseline.git /tmp/engineering-baseline
bash /tmp/engineering-baseline/scripts/install.sh --host cursor --project "$PWD"
Use --host claude, --host both, or --host auto. If no host can be
detected, auto installs for both. The default profile is full.
bash scripts/install.sh --host both --profile full --project /path/to/project
bash scripts/install.sh --host both --project-mode existing --project /path/to/project
bash scripts/install.sh --host both --project-mode new --project /path/to/project
bash scripts/install.sh --host cursor --profile core --dry-run
bash scripts/install.sh --host cursor --skill security-review
bash scripts/update.sh --host both --project /path/to/project
bash scripts/uninstall.sh --project /path/to/project
The installer requires Python 3 and Git. It never replaces an unmanaged skill
unless --force is supplied. Managed installations are recorded in
.engineering-baseline-lock.json so updates and uninstallations are safe.
--project-mode auto detects existing application manifests/source files. Use
the explicit mode only when detection cannot infer the intended workflow.
The native Claude Code plugin also injects the adoption instruction at session
start and denies direct file-edit tools while an installed lock remains
pending. The URL installer is recommended for existing projects because it
creates that project-local lock and installs both host adapters.
When application code already exists, installation records:
{"adoption": {"status": "pending"}}
On the first coding request, Cursor or Claude must invoke
adopt-existing-project and remain read-only. It will:
The adoption state progresses through pending → approved → in_progress → complete. Re-running the installer preserves the current state.
Claude Code can install the baseline and all three upstream dependencies natively:
/plugin marketplace add notwld/engineering-baseline
/plugin install engineering-baseline@notwld-engineering
The baseline plugin declares Ponytail, Superpowers, and Impeccable as dependencies, so Claude Code installs them automatically.
| Profile | Contents |
|---|---|
core | Baseline, Existing-Project Adoption, Ponytail, Superpowers |
frontend | Core plus Impeccable and Production Full-Stack |
full | Frontend plus Security Review and Production Full-Stack |
When the full profile is installed, requests to create or materially change an
application, API, backend, frontend, worker or deployment invoke the
production-full-stack skill. It requires:
npx claudepluginhub notwld/engineering-baseline --plugin engineering-baselineHarness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques