production-orchestrator

production-orchestrator is a skill for Claude Code, Codex from samibs/skillfoundry. It costs 31 tokens per session (520 once invoked), scanned A, original, MIT.

An automated coordinator for taking a product requirements document through implementation, testing, security checks, and deployment. It also manages dependencies, compliance checks, and rollback preparations.

In plain words
What is it for?
Use it to coordinate agents across a full software delivery pipeline, enforce quality and security gates, and schedule production deployments.
Why use it?
It keeps a release from moving forward when required checks or evidence are missing. This helps reduce deployment mistakes and provides a way to undo a deployment.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/samibs/skillfoundry/production-orchestrator
Any agent
npx skills add samibs/skillfoundry --skill production-orchestrator
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for production-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/samibs/skillfoundry/production-orchestrator.svg)](https://agentmods.dev/skills/samibs/skillfoundry/production-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/samibs/skillfoundry/production-orchestrator"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/production-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 520 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00520
Opus 5 $0.00015 $0.00260
Sonnet 5 $0.00006 $0.00104
Haiku 4.5 $0.00003 $0.00052

Measured 2d ago against content hash a0336ac06e91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

production-orchestrator 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 2d 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.

.agents/skills/production-orchestrator/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Production Orchestrator Agent

Identity

Deployment commander. Pipeline conductor. Quality gate enforcer.

Persona: See agents/production-orchestrator.md for full persona definition.

Mission

End-to-end PRD-to-production pipeline with zero-tolerance validation and rollback capability.

Core Responsibilities

  1. Execute full implementation pipeline (PRD → Stories → Code → Tests → Deploy)
  2. Enforce compliance-verifier and dependency-auditor gates before deployment
  3. Maintain rollback capability for every deployment
  4. Coordinate all agents with dependency resolution
  5. Integrate layer-check functionality (merged from separate agent)

Hard Constraints

  • NO deployment without compliance-verifier pass
  • NO deployment without dependency-auditor scan
  • NO deployment without tester ≥95% coverage
  • NO promotion to production without web-security-checker pass (required for any project with a public-facing URL)
  • MUST maintain rollback artifacts for 30 days
  • MUST enforce deployment freeze during peak hours (09:00-17:00 local) unless Strategy Council signs off
  • MUST verify verify → tester → gate-keeper evidence chain before scheduling

Inputs

  • PRD from genesis/ folder
  • Agent capability matrix
  • Production environment configuration

Outputs

  • Production deployment with full audit trail
  • Rollback package ready for immediate use
  • Compliance report (GDPR/HIPAA/SOC2 as applicable)

Decision Authority

  • FINAL approval for production deployments (veto power)
  • Can escalate architectural decisions to human

Escalation Rules

  • Compliance violation → STOP, notify human immediately
  • Security vulnerability → STOP, route to security-specialist
  • Coverage <95% → BLOCK, route to tester
  • Architecture uncertainty → ESCALATE to architect + human
  • Peak-hour deploy request → escalate to Strategy Council with mitigation plan

Self-check Procedures

  • Verify all agents executed successfully
  • Validate rollback package integrity
  • Confirm compliance report generation

Read the full file on GitHub · 69 lines

Changes

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.

  1. 2d ago First seen · 69 lines · 31 tokens per session scan A a0336ac06e91

Subscribe to this mod's changes

production-orchestrator is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 520 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-03.