{"id":51065593,"url":"https://github.com/rajitsaha/100xprism","last_synced_at":"2026-06-23T06:30:29.173Z","repository":{"id":350516400,"uuid":"1206670633","full_name":"rajitsaha/100xprism","owner":"rajitsaha","description":"Production-grade AI development workflows for every coding tool. Works with Claude Code, Cursor, Codex, Windsurf, Copilot CLI, Gemini CLI, and more.","archived":false,"fork":false,"pushed_at":"2026-06-21T04:55:22.000Z","size":10952,"stargazers_count":8,"open_issues_count":11,"forks_count":5,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-21T06:20:16.861Z","etag":null,"topics":["agentic-coding","ai-agents","ai-coding","ai-developer-tools","ai-workflows","antigravity","claude-code","codex","copilot","cursor","developer-tools","devtools","gemini","quality-gates","security-scanning","test-coverage","vibe-coding","windsurf"],"latest_commit_sha":null,"homepage":"https://rajitsaha.github.io/100xprism/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rajitsaha.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":"ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-04-10T06:22:52.000Z","updated_at":"2026-06-21T04:55:26.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/rajitsaha/100xprism","commit_stats":null,"previous_names":["rajitsaha/100x-dev","rajitsaha/100xprism"],"tags_count":16,"template":false,"template_full_name":null,"purl":"pkg:github/rajitsaha/100xprism","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajitsaha%2F100xprism","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajitsaha%2F100xprism/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajitsaha%2F100xprism/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajitsaha%2F100xprism/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rajitsaha","download_url":"https://codeload.github.com/rajitsaha/100xprism/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajitsaha%2F100xprism/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34678932,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-23T02:00:07.161Z","response_time":65,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-coding","ai-agents","ai-coding","ai-developer-tools","ai-workflows","antigravity","claude-code","codex","copilot","cursor","developer-tools","devtools","gemini","quality-gates","security-scanning","test-coverage","vibe-coding","windsurf"],"created_at":"2026-06-23T06:30:28.483Z","updated_at":"2026-06-23T06:30:29.162Z","avatar_url":"https://github.com/rajitsaha.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"assets/100xprism-logo.svg\" alt=\"100xPrism logo\" width=\"120\" /\u003e\n\n# 100xPrism\n\n### Stop vibe coding. Ship production-grade software.\n\n[![Version](https://img.shields.io/github/v/release/rajitsaha/100xprism?style=flat-square\u0026label=version\u0026color=brightgreen)](https://github.com/rajitsaha/100xprism/releases/latest)\n[![npm](https://img.shields.io/npm/v/100xprism?style=flat-square\u0026color=red)](https://www.npmjs.com/package/100xprism)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow?style=flat-square)](LICENSE)\n\n**One source of truth.** 66 modules generate native config for **Claude Code · Cursor · Codex · Windsurf · Copilot · Gemini · Antigravity**. Quality gates run on every commit.\n\n\u003cimg src=\"assets/100xprism-hero.svg\" alt=\"100xPrism — one config, every AI coding tool · 14 plugins, 26 slash commands, 40 auto-trigger skills\" width=\"100%\" /\u003e\n\n\u003c/div\u003e\n\n---\n\n## Install\n\n**npm (any platform — macOS, Linux, Windows):**\n```bash\nnpm install -g 100xprism \u0026\u0026 100xprism install\n```\n\n**curl (macOS / Linux):**\n```bash\ncurl -fsSL https://raw.githubusercontent.com/rajitsaha/100xprism/main/get.sh | bash\nsource ~/.zshrc   # or ~/.bashrc — activates the 100xprism command\n```\n\nEither way, `100xprism install` clones the toolkit to `~/100xprism` and provisions your AI tools. The npm package is a thin launcher — the modules, hooks, and plugins live in that clone, which `100xprism update` keeps current.\n\n\u003e **Windows:** plugin sync works, but native Windows module emit is being reworked ([#54](https://github.com/rajitsaha/100xprism/issues/54)). For full module support today, install under **WSL** with either method above.\n\n**Set up a project:**\n```bash\ncd your-project \u0026\u0026 100xprism init\n```\n\n**Keep up to date:**\n```bash\n100xprism update                    # pull latest, then add/update/remove skills + plugins\n100xprism update --plugins-only     # refresh plugins only (repo already current)\nnpm install -g 100xprism@latest     # (optional) upgrade the launcher itself\n```\n\n`install` and `update` are **fully reconciling**, not append-only — every run:\n- **adds** newly shipped skills, slash commands, and curated plugins,\n- **updates** changed ones in place, and\n- **removes** skills, slash-command aliases, and 100xprism-managed plugins that were deleted or merged upstream.\n\nYour own hand-authored skills/commands and any plugins you enabled yourself are never touched. See [docs/USAGE.md](docs/USAGE.md#keeping-up-to-date) for details.\n\n\u003e **Cloned to a custom path?** The default install lives at `~/100xprism`. If you cloned elsewhere, update your shell + Claude Code config — see [Custom install location](docs/USAGE.md#custom-install-location).\n\n---\n\n## The pipeline\n\n```\n/understand → /context → /issue → /spec → /fix → /commit\n                                                    ↓\n              /techdebt ← /gate → /grill → /pr → /push → /release\n```\n\nEvery `/commit` and `/push` runs a 5-point gate — tests, security, build, Docker, cloud. Nothing ships without passing.\n\n---\n\n## What you get\n\n| | |\n|---|---|\n| **66 modules** | 26 slash commands + 40 auto-trigger skills — see [full reference below](#slash-commands) |\n| **14 Claude Code plugins** | superpowers, playwright, github, hookify, claude-mem, understand-anything, ui-ux-pro-max, motion-framer, and more |\n| **7 database engines** | Postgres, Cloud SQL, Snowflake, Databricks, Athena, Presto, Oracle — one `/db` interface |\n| **27 SaaS CLIs** | `/connect` installs + authenticates GitHub, AWS, Stripe, Supabase, and more from `.env` |\n| **4 project templates** | node-fullstack · node-frontend · python-api · docker-compose |\n| **CI/Release pipelines** | Drop-in GitHub Actions for lint + real-DB tests + E2E + semantic-release |\n\n---\n\n## Token \u0026 value economics\n\nFor a while, the goal was singular: make spec-driven, agentic development as **autonomous** as possible — let the agent plan, build, gate, and ship with less and less human steering.\n\nThat part is mostly working. The harder, more important question is the one that comes next: **what is all this autonomy costing, and what is it worth?** Every agent run spends real money in tokens. So the question is no longer *can it ship* — it's *how much did we spend, and how much value did we add — to a business, or to humanity.*\n\nThis is a first, deliberately humble attempt to **measure both — and to make it visible to everyone**, because watching it isn't one person's job. **It's everybody's responsibility.**\n\n```bash\n100x-tokens   # token economics — what every session, across every repo, is costing\n100x-value    # value economics  — what actually shipped for that spend\n```\n\n- **`100x-tokens`** — one offline, machine-wide dashboard at a single URL: the input/output/cache split, a startup-bloat meter, an *estimated* code-vs-logs-vs-output composition, and $ cost — by project, model, and day. It auto-refreshes every 5 minutes, so a tab left open never goes stale. It also **auto-starts** — a detached singleton launches on shell startup and on `install` / `init` / `update`, so the dashboard is always live without running a command (opt out with `export PRISM_NO_DASHBOARD=1`).\n- **`100x-value`** — tokens measure *cost*; this measures *value*. The dashboard shows **every directory that consumed tokens** (repo or not) plus every agentic project discovered machine-wide via marker files (CLAUDE.md, AGENTS.md, GEMINI.md, .cursorrules, .windsurfrules, .clinerules, .github/copilot-instructions.md) — even with zero Claude token spend. Value is derived tool-agnostically from git history (commits / PRs / files / churn) with a filesystem-mtime fallback, plus cached AI one-line summaries via the local `claude` CLI. Cost is Claude-Code-only (the only tool with local token accounting); directories from other tools show value with `—` cost, never $0. Four inline-SVG charts render in the same URL: a leverage scatter (value vs cost, break-even line), cost-over-time, token-purpose split, and cost-by-directory.\n\nFull guide: [docs/token-optimization.md](docs/token-optimization.md).\n\n---\n\n## Slash commands\n\nThe following 26 slash commands are available. Run them inside Claude Code. In Codex, use the generated repo skill by name instead, for example `$gate`, `$commit`, or `/skills`.\n\n### Lifecycle\n\n| Command | What it does |\n|:--------|:-------------|\n| `/branch` | Create a conventional feature branch (`feat/`, `fix/`, `chore/`) |\n| `/commit` | Gate → stage → conventional commit |\n| `/grill` | Adversarial code review before opening a PR |\n| `/pr` | Gate → push branch → create PR |\n| `/push` | Gate → push → monitor CI → verify production health |\n| `/release patch\\|minor\\|major` | Semantic versioning + publish to PyPI/npm/Docker Hub |\n| `/launch` | Full deploy pipeline in one command |\n\n### Quality\n\n| Command | What it does |\n|:--------|:-------------|\n| `/gate` | **Mandatory** 5-point quality gate (tests, security, build, Docker, cloud) |\n| `/test` | All test layers (unit, integration, E2E) — loops until 95% coverage |\n| `/lint` | Auto-detect and fix all lint errors (ESLint, TypeScript, ruff) |\n| `/security` | Vulnerability + secrets scan, auto-fix where possible |\n| `/cloud-security` | GCP IAM, networking, PII, and compliance scan |\n| `/eval` | Run module evals — check triggers and output quality |\n\n### Engineering\n\n| Command | What it does |\n|:--------|:-------------|\n| `/spec` | Turn a vague request into an implementation-ready spec |\n| `/fix` | Autonomous bug fixer — CI failures, docker logs, Slack pastes |\n| `/orchestrate` | Plan-first methodology for complex multi-step tasks |\n| `/techdebt` | Dead code, duplication, stale TODOs |\n| `/context` | 7-day git + GitHub activity dump — orient before coding |\n| `/update-claude` | Write a CLAUDE.md rule after any correction |\n\n### Data \u0026 Infrastructure\n\n| Command | What it does |\n|:--------|:-------------|\n| `/db` | Query any of 7 database engines from one interface |\n| `/query` | Plain-English analytics — describe what you want, get SQL |\n| `/connect` | Install + auth 27 SaaS CLIs from `.env` |\n\n### Documentation \u0026 Architecture\n\n| Command | What it does |\n|:--------|:-------------|\n| `/docs` | Detect code changes and update documentation |\n| `/issue` | Investigate a bug and create a detailed GitHub issue |\n| `/architect` | Architectural Q\u0026A and decision matrices |\n| `/enterprise-design` | Full technical blueprint — IA, API, data model, stack |\n\n### Auto-trigger skills (39)\n\nThese modules activate automatically when you describe a relevant task — no slash command needed.\n\n| Category | Modules |\n|:---------|:--------|\n| **Marketing copy** | copywriting, copy-editing, cold-email, email-sequence, ad-creative, social-content |\n| **SEO** | seo-audit, ai-seo, programmatic-seo, schema-markup, site-architecture |\n| **CRO \u0026 conversion** | page-cro, signup-flow-cro, onboarding-cro, form-cro, popup-cro, paywall-upgrade-cro |\n| **Growth \u0026 strategy** | content-strategy, marketing-ideas, marketing-psychology, launch-strategy, referral-program, churn-prevention, free-tool-strategy, ab-test-setup, analytics-tracking, pricing-strategy |\n| **Sales** | sales-enablement, competitor-alternatives, paid-ads, revops, product-marketing-context |\n| **Design** | enterprise-design, visual-system-architect, interaction-engineer, figma-translator |\n| **Engineering** | subagents, terminal-setup |\n\n---\n\n## How it works in your tool\n\n| Tool | Generated artifact | Auto-trigger? |\n|:-----|:-------------------|:--------------|\n| **Claude Code** | `~/.claude/skills/\u003cslug\u003e/` + slash command aliases | Yes — per description |\n| **Cursor** | `.cursor/rules/\u003cslug\u003e.mdc` (one file per module) | Yes — per description |\n| **Codex** | `AGENTS.md` + `.agents/skills/\u003cslug\u003e/` + `.codex/hooks.json` | Yes — repo skills |\n| **Antigravity** | `ANTIGRAVITY.md` (core inlined + on-demand index) | Core only |\n| **Windsurf** | `.windsurfrules` (size-budgeted) | Core only |\n| **Copilot / Gemini** | `.github/copilot-instructions.md` / `GEMINI.md` | Core only |\n\nModules with `tier: core` (26) inline into single-file tools; `tier: on-demand` (39) appear as a compact index. In Claude Code, Cursor, and Codex, modules are also available as native skills/rules so full bodies load on demand. Claude Code plugins remain Claude-specific; use Codex `/plugins` for Codex-native plugins.\n\n---\n\n## Common CI traps it fixes\n\n`npm install` 404 inside Docker · `useState(false)` opacity-0 breaking Playwright · integration tests silently excluded from the gate. [Full breakdown →](docs/ci-traps.md)\n\n---\n\n## More\n\n- [Full usage guide](docs/USAGE.md) — daily patterns, multi-project setup, CI templates, project config, troubleshooting\n- [Architecture](docs/v2-refactor.md) — why modules replaced workflows + skills\n- [Token usage \u0026 optimization](docs/token-optimization.md) — audit your plugin/skill footprint and monitor token spend with the local dashboard\n- [Changelog](CHANGELOG.md) · [Roadmap](ROADMAP.md) · [Issues](https://github.com/rajitsaha/100xprism/issues)\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\nBuilt by [Rajit Saha](https://www.linkedin.com/in/rajsaha/) · 23 years in enterprise data at Udemy, Experian, LendingClub, VMware, Yahoo\n\n[![LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-blue?style=for-the-badge\u0026logo=linkedin)](https://www.linkedin.com/in/rajsaha/)\n[![GitHub](https://img.shields.io/badge/GitHub-Follow-black?style=for-the-badge\u0026logo=github)](https://github.com/rajitsaha)\n\nIf this saves you time, **[star the repo](https://github.com/rajitsaha/100xprism)**.\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frajitsaha%2F100xprism","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frajitsaha%2F100xprism","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frajitsaha%2F100xprism/lists"}