productionos
ProductionOS — dual-target AI engineering operating system for repo-wide audits, upgrade plans, code reviews, strategic product reviews, security sweeps, UX…
Skill by ShaheerKhawaja
Chalk Labs
Need help deploying productionos?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/shaheerkhawaja-productionos-d767b3
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/productionos
What's inside
- Skill name
productionos- Description
- ProductionOS — dual-target AI engineering operating system for repo-wide audits, upgrade plans, code reviews, strategic product reviews, security sweeps, UX audits, and recursive quality improvement.
- License
- MIT
- Instructions
- 43 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- name: "productionos" does not match folder "ProductionOS"
Files (200)
- marketplace.json · .claude-plugin/
- plugin.json · .claude-plugin/
- agentic-eval.md · .claude/commands/
- auto-mode.md · .claude/commands/
- auto-optimize.md · .claude/commands/
- auto-swarm-nth.md · .claude/commands/
- auto-swarm.md · .claude/commands/
- autoloop.md · .claude/commands/
- brainstorming.md · .claude/commands/
- browse.md · .claude/commands/
- build-productionos.md · .claude/commands/
- context-engineer.md · .claude/commands/
- debug.md · .claude/commands/
- deep-research.md · .claude/commands/
- designer-upgrade.md · .claude/commands/
- devtools.md · .claude/commands/
- document-release.md · .claude/commands/
- frontend-upgrade.md · .claude/commands/
- learn-mode.md · .claude/commands/
- logic-mode.md · .claude/commands/
- max-research.md · .claude/commands/
- omni-plan-nth.md · .claude/commands/
- omni-plan.md · .claude/commands/
- plan-ceo-review.md · .claude/commands/
- plan-eng-review.md · .claude/commands/
- production-upgrade.md · .claude/commands/
- productionos-help.md · .claude/commands/
- productionos-pause.md · .claude/commands/
- productionos-resume.md · .claude/commands/
- productionos-stats.md · .claude/commands/
- productionos-update.md · .claude/commands/
- qa-only.md · .claude/commands/
- qa.md · .claude/commands/
- refine.md · .claude/commands/
- retro.md · .claude/commands/
- review.md · .claude/commands/
- security-audit.md · .claude/commands/
- self-eval.md · .claude/commands/
- session-validate.md · .claude/commands/
- ship.md · .claude/commands/
- tdd.md · .claude/commands/
- ux-genie.md · .claude/commands/
- writing-plans.md · .claude/commands/
- plugin.json · .codex-plugin/
- ci.yml · .github/workflows/
- .gitignore
- .markdownlint.json
- AGENTS.md
- ARCHITECTURE.md
- CHANGELOG.md
- CLAUDE.md
- CODE_OF_CONDUCT.md
- CONTRIBUTING.md
- ETHOS.md
- LICENSE
- README.md
- SECURITY.md
- SKILL.md
- SKILL_REGISTRY.md
- VERSION
- …and 140 more
SKILL.md (first lines)
# ProductionOS ProductionOS is a dual-target AI engineering operating system with 80 agents, 41 commands, and 18 hooks. Use this skill to translate the Claude-oriented workflow specs in this repo into Codex-native execution. ## Start Here 1. Read `README.md` for the product overview and `CLAUDE.md` for the current command catalog. 2. Treat `.claude/commands/*.md` as workflow specs, not literal Codex slash commands. 3. Use `docs/CODEX-PARITY-HANDOFF.md` as the source of truth for target support and parity coverage. 4. Load only the agent files in `agents/` that matter for the chosen workflow. 5. Use `templates/` and `prompts/` only when the selected command or agent points to them. ## Codex Workflow Mapping - `production-upgrade` — Run a repo audit, prioritize high-leverage defects, implement bounded fixes, then validate before reporting. - `review` — Use Codex in review mode and report concrete findings before summaries. - `plan-ceo-review` — Challenge scope, tighten user value, and surface expansion opportunities explicitly. - `plan-eng-review` — Lock architecture, trust boundaries, error paths, and test coverage before implementation. - `security-audit` — Inspect auth, secrets, input handling, and deployment risk with findings-first output. - `designer-upgrade` — Build a UX audit and redesign plan, then route into interface work when needed. - `ux-genie` — Map user flows, identify friction, and translate findings into concrete improvements. - `auto-swarm` — Run the workflow serially by default in Codex, or delegate only when the user explicitly wants parallel work. - `auto-swarm-nth` — Repeat swarm-style execution until gaps close, while translating agent waves into Codex-native orchestration. - `omni-plan` — Chain the major review and execution patterns in a Codex-native sequence without Claude-only assumptions. - `omni-plan-nth` — Iterate the full orchestration loop until quality targets are met or clearly plateau. ## Guardrails - Do not claim Claude-only hooks, slash commands, or marketplace flows can run directly in Codex. - Keep work scoped; do not emulate large multi-agent swarms unless the user explicitly wants that overhead. - Respect the repo's guardrails in `hooks/`, `.claude-plugin/`, `.codex-plugin/`, and `templates/`. - For packaging or install questions, inspect `.claude-plugin/plugin.json`, `.claude-plugin/marketplace.json`, `.codex-plugin/plugin.json`, `package.json`, and `README.md`. ## Output Expectations - Explain which ProductionOS workflow you are mapping. - Use Codex-native tools for implementation, review, planning, or validation. - Verify with the smallest relevant tests or checks before concluding. - Summarize what changed, what was verified, and what still needs human approval.
From ShaheerKhawaja/ProductionOS, MIT.
More from ShaheerKhawaja/ProductionOS
- 0.469score
productionos-document-release
ShaheerKhawaja
Post-ship documentation update — reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
continuous-learning
ShaheerKhawaja
ProductionOS instinct-based learning system.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
frontend-audit
ShaheerKhawaja
ProductionOS frontend quality scanner.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
security-scan
ShaheerKhawaja
ProductionOS security scanner.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
productionos-agentic-eval
ShaheerKhawaja
Niche-agnostic agentic evaluator using CLEAR v2.0 framework — 6-domain assessment, 8 analysis dimensions, 6-tier source prioritization, evidence strength…
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
productionos-auto-mode
ShaheerKhawaja
Idea-to-running-code lifecycle orchestration.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
productionos-auto-optimize
ShaheerKhawaja
Self-improving agent optimization — generates challenger variants of any agent/command, benchmarks against baseline, promotes winners, logs learnings to…
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
productionos-auto-swarm
ShaheerKhawaja
Distributed agent swarm orchestrator — spawns parallel subagent clusters for any task with configurable depth, swarm size, and convergence criteria
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
productionos-auto-swarm-nth
ShaheerKhawaja
Nth-iteration agent swarm — spawns parallel agent waves, evaluates strictly per wave, re-swarms gaps until 100% coverage and 10/10 quality.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
productionos-autoloop
ShaheerKhawaja
Autonomous recursive improvement loop for a single target.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
productionos-brainstorming
ShaheerKhawaja
Idea exploration before building — understand the problem, propose approaches, present design, get approval.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
productionos-browse
ShaheerKhawaja
Headless browser for QA testing, site inspection, and interaction verification.
SkillDFreshness: D★ 8Claude Code +9
Signals
- Stars
- 8
- Forks
- 1
- Open issues
- 0
- Last commit
- Apr 16, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ShaheerKhawaja/ProductionOS
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from ShaheerKhawaja
- 0.469score
continuous-learning
ShaheerKhawaja
ProductionOS instinct-based learning system.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
frontend-audit
ShaheerKhawaja
ProductionOS frontend quality scanner.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
security-scan
ShaheerKhawaja
ProductionOS security scanner.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
productionos-agentic-eval
ShaheerKhawaja
Niche-agnostic agentic evaluator using CLEAR v2.0 framework — 6-domain assessment, 8 analysis dimensions, 6-tier source prioritization, evidence strength…
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
productionos-auto-mode
ShaheerKhawaja
Idea-to-running-code lifecycle orchestration.
SkillDFreshness: D★ 8Claude Code +9 - 0.469score
productionos-auto-optimize
ShaheerKhawaja
Self-improving agent optimization — generates challenger variants of any agent/command, benchmarks against baseline, promotes winners, logs learnings to…
SkillDFreshness: D★ 8Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get productionos running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
productionos skill. Agent Mart. https://agentmart.dev/skills/shaheerkhawaja-productionos-d767b3 (last updated 2026-10-24)