---

Quick start

1. Install (once per machine).

# npm — macOS, Linux, Windows (needs Node.js 18+)
npm install -g 100xprism && 100xprism install

# or curl — macOS / Linux
curl -fsSL https://raw.githubusercontent.com/rajitsaha/100xprism/main/get.sh | bash

Both clone the toolkit to ~/100xprism, set up Claude Code, and let you toggle components (modules, plugins, templates, enforcing hooks). The npm package is a thin launcher; modules, hooks and plugins live in that clone.

2. Set up a project (once per repo).

cd your-project && 100xprism init

init asks which tools you use in the repo (Claude Code, Cursor, Codex, Pi) and writes their files. Commit them so teammates get the same setup on clone.

3. Use it. Restart Claude Code, then run:

/gate      # run the quality gate
/commit    # gate → stage → conventional commit

Two places, two kinds of command. 100xprism … runs in your terminal. /gate, /commit and the other slash commands run inside your AI tool.

---

What you get

68 modules	28 slash commands + 40 auto-trigger skills (task-triggered playbooks: marketing, SEO, CRO, design)
Quality gate	/gate: tests ≥ 95% coverage, security, build, plus Docker and cloud checks when they apply
Enforcing hooks (opt-in)	Block git commit/git push until /gate passes on the current tree; block obvious hard-coded secrets
2 Claude Code plugins	GitHub and security guidance. Other plugins are listed as recommendations, never installed silently
/db	One interface to 7 engines: Postgres, Cloud SQL, Snowflake, Databricks, Athena, Presto, Oracle
/connect	Install and authenticate 27 SaaS CLIs (GitHub, AWS, Stripe, Supabase, …) from .env
4 project templates	node-fullstack · node-frontend · python-api · docker-compose, copied to ~/100x-templates/
CI templates	GitHub Actions: lint, real-DB tests, E2E (ci.yml) and tag-triggered publishing (release.yml)
Token economics	A local dashboard of token spend, cost and delivered work across Claude Code, Codex, Cursor, Pi and Antigravity

---

Lean by default: what sits in your context

A module's description is re-sent to the model on every turn; its body loads only when used. So every installed module costs tokens all the time. 100xPrism installs the minimum by default:

Mode	Installed as native skills	Everything else
must (default)	12 core workflows + 100x-resolver	In a catalog on disk; loaded on demand
profile	must + 18 more: the other 16 slash-command modules, subagents, terminal-setup	38 marketing/design playbooks stay in the catalog
all	All 68 modules	—

The 12 must-have workflows: gate commit push branch pr release test lint security docs eval pair-loop.

Reaching a module that isn't installed. Use the generic route, or just describe the task — the always-loaded 100x-resolver tells the agent where each catalog module lives:

/100x spec               # run the spec workflow
/100x fix-bugs "login returns 403"

Changing the mode. optimize writes your choice and re-emits immediately. Run it from a project root — it also updates that project's generated files.

100xprism optimize --skills=profile   # every slash command becomes native (/spec, /fix, …)
100xprism optimize --skills=all       # every module installed
100xprism optimize                    # back to must
100xprism optimize --dry-run          # preview without changing anything

Estimated always-on description cost (characters ÷ 4, checked in CI — not billed usage):

Tool	all	profile	must
Claude Code, Pi	~4,834	~1,685	~592
Codex	~4,834	~1,666	~573
Cursor	~2,057	~821	~377

Details: docs/token-optimization.md.

---

Slash commands

All 28, grouped by purpose. ★ = installed natively in the default must mode. Run the others as /100x <slug> (slug in brackets where it differs), or switch to --skills=profile to get them all natively.

Lifecycle

Command	What it does
★ /branch	Create a conventional feature branch (feat/, fix/, chore/)
★ /commit	Gate → stage → conventional commit
★ /pr	Gate → push branch → open a PR with AI review
★ /push	Gate → push → watch CI → check production health
★ /release patch|minor|major	Bump version, tag, publish to PyPI/npm/Docker Hub, verify
★ /pair-loop	Coder ↔ reviewer loop across Claude/Codex/Cursor/Pi, with per-round cost
/grill [grill-me]	Adversarial review before a PR
/launch	Full deploy pipeline

Quality

Command	What it does
★ /gate	Quality gate: tests, security, build, Docker, cloud
★ /test	Run every test layer; add tests until coverage ≥ 95%
★ /lint	Detect linters/formatters, run them, fix errors
★ /security	Dependency vulnerabilities + leaked secrets; fix what's fixable
★ /eval	Run a module's evals — does it still trigger and work?
/cloud-security	Cloud IAM, networking, PII and compliance scan

Engineering

Command	What it does
/spec	Turn a vague request into an implementation-ready spec
/fix [fix-bugs]	Fix bugs from CI failures, logs, or a description
/orchestrate	Plan-first method for multi-step tasks
/techdebt	Find dead code, duplication, stale TODOs
/update-claude [update-claude-md]	Turn a correction into a CLAUDE.md rule
/pack	Install or remove optional vendor skill packs (see below)

Data, docs & architecture

Command	What it does
★ /docs	Sync docs with what shipped
/db	Query any of 7 database engines
/query [data-query]	Plain-English analytics → SQL
/connect	Install + authenticate SaaS CLIs from .env
/context [context-dump]	7-day git + GitHub activity summary
/issue	Investigate a bug and file a detailed GitHub issue
/architect	Architecture Q&A and decision matrices
/enterprise-design	Full blueprint: IA, API, data model, stack

Task-triggered playbooks (40). No command — describe the task ("audit SEO on this page") and the agent loads the matching playbook: from the catalog via 100x-resolver by default, or as its own skill in all mode.

Area	Modules
Marketing copy	copywriting, copy-editing, cold-email, email-sequence, ad-creative, social-content
SEO	seo-audit, ai-seo, programmatic-seo, schema-markup, site-architecture
CRO	page-cro, signup-flow-cro, onboarding-cro, form-cro, popup-cro, paywall-upgrade-cro
Growth & strategy	content-strategy, marketing-ideas, marketing-psychology, launch-strategy, referral-program, churn-prevention, free-tool-strategy, ab-test-setup, analytics-tracking, pricing-strategy
Sales	sales-enablement, competitor-alternatives, paid-ads, revops, product-marketing-context
Design & UX	visual-system-architect, interaction-engineer, figma-translator, motion-designer, data-viz, a11y-auditor
Engineering	subagents, terminal-setup

In Codex use skills by name ($gate, $commit) or pick from /skills. In Pi use /skill:gate. In Cursor, ask for the workflow by name ("run the gate workflow").

---

How each tool receives the modules

Tool	Where	What is written
Claude Code	~/.claude/skills/ (global)	One skill per installed module, /100x route, 100x-resolver
Cursor	.cursor/rules/ (per project)	One .mdc rule per installed module; gate is always-on, the rest load when relevant
Codex	project root (per project)	Compact AGENTS.md, .agents/skills/, catalog; hook groups in .codex/hooks.json only with PRISM_HOOKS=1
Pi	.pi/skills/ (per project) or pi install git:github.com/rajitsaha/100xprism	Same must-first selection; gate/secret extensions ship but are off by default
Hermes/OpenClaw	~/.hermes/skills/100xprism/ (global)	One skill per module, descriptions shortened to fit Hermes's ~57-character index limit

install and update run the Hermes adapter automatically when ~/.hermes or the hermes CLI exists. If you install Hermes later, run 100xprism hermes (or wait for your next 100xprism update).

Claude Code plugins are Claude-only. Use Codex /plugins for Codex-native plugins.

Windows: install, init and update work natively for Claude Code, Cursor and Codex. Pi, Hermes, and background token collection need macOS or Linux (WSL works).

---

Keeping up to date

100xprism check                   # is a newer version available?
100xprism update                  # pull latest; add, update and remove generated files
npm install -g 100xprism@latest   # (optional) update the launcher itself

update reconciles: it adds new modules and plugins, updates changed ones, and removes ones that were deleted or merged upstream — in ~/.claude and in every project you ran init in (listed in ~/.100xprism/tracked-projects). Restart Claude Code after updating.

What 100xPrism will and won't delete. It removes only files it can prove it wrote: a generated marker, a manifest entry, a /100xprism/hooks/ path, or an exact v1 file header. Your own skills, commands, hooks, plugins and a hand-written AGENTS.md are never touched. Files removed from a project are first copied to ~/.100xprism/removed-artifacts/<timestamp>/.

Repairing and removing.

100xprism audit                  # report standing context and drift
100xprism audit --fix            # repair dead hook paths, v1 leftovers, missing catalog
100xprism uninstall              # remove skills, aliases, hooks, catalog, links (keeps your data)
100xprism uninstall --projects   # …also generated files in every tracked project
100xprism uninstall --purge      # …also all of ~/.100xprism, including token history

Run 100xprism uninstall before npm rm -g 100xprism. npm's own uninstall hook only stops the dashboard and removes hooks that point into the deleted package.

---

Optional vendor skill packs

Packs are skill sets that matter only to some projects, so they never install by default. Manage them from inside Claude Code:

/pack                    # list packs, install state, and what matches this project
/pack detect             # only packs that match this project
/pack add databricks     # install
/pack remove databricks  # remove only what 100xPrism installed

Where the vendor ships an installer (e.g. databricks aitools install), the pack uses it. Available today: Databricks (Unity Catalog, Asset Bundles, Lakeflow, model serving, vector search).

---

Token, delivery & value economics

Agents spend real money. The dashboard keeps three questions apart: what did it cost, what was delivered, and what was it worth — the last stays "Not measured" until you connect an outcome source. It never invents a value score.

100xprism tokens            # open the local dashboard (http://127.0.0.1:8787)
100xprism tokens --print    # text summary, no server
100xprism tokens --json     # machine-readable report (filter with --tool codex)
100xprism value             # git delivery report for the current directory

• Cost. Claude Code and Codex record exact token counts locally; cost is priced per model from a dated catalog (scripts/pricing.py). Pi is counted when its records carry token counts. Cursor and Antigravity expose no token counts locally, so they are shown as activity only, with cost — (never a made-up $0).
• Delivery. Commits, merged PRs, releases and churn from git, joined to the spend that could be attributed to each directory.
• macOS: install adds a LaunchAgent that collects every minute into a private SQLite store (~/.100xprism/token-economics/), so history survives deleted transcripts. The dashboard needs a per-launch token (the command opens it for you) and stops after 10 idle minutes. Linux/Windows: reports are computed on demand.
• Nothing starts from your shell. Nothing leaves your machine unless you opt in to GitHub PR insights.

Budgets, GitHub insights, content search and every flag: docs/USAGE.md › Monitoring token usage.

---

Built with 100xPrism

Product	Source
100xprism — this toolkit, built with itself	Open source
agentbreeder	Open source
hippokit.ai	Closed source
norulestrends.com	Closed source
reinvestiq.com	Closed source

What it changed

Snapshot taken 2026-08-02 from each repo's git history.

From git history	100xprism	agentbreeder
First commit → first public release	6 days	32 days
Releases shipped	26	17
Median gap between releases	1 day	2 days
Merged PRs	70	171
Commits	204	772
Lines added	78,447	541,370
Peak commits in one day	39	61
Active engineering days	29	53

Across all five products, open and closed source: 3,282 commits · 1,225 merged PRs · 1.78M lines added, by one person.

As an estimate, not a measurement. Nothing was built twice, so there is no counterfactual. Assume a conventional team merges ~2 feature-sized PRs per engineer-week: 1,225 ÷ 2 ≈ 612 engineer-weeks ≈ 11.8 engineer-years. At $85/hr that is roughly $2.1M. PR size varies widely, and assuming 1 or 4 PRs per week moves the figure by 2×. Revenue, retention and customer outcomes are not measured here.

---

Common CI traps it fixes

npm install 404 inside Docker · useState(false) opacity-0 breaking Playwright · integration tests silently skipped. Full breakdown →

---

More

• Usage guide — per-tool details, project config, CI templates, dashboard, troubleshooting
• Token optimization — retention classes, modes, measuring footprint
• Enforcing hooks — gate-on-commit, secret scan, and their switches
• Architecture — why modules replaced workflows + skills
• Changelog · Roadmap · Security · Issues
• Contributing: start with AGENTS.md

---