coreycoto avatar

product-development

v0.10.8

by coreycoto · author: Corey Coto

Owned workflows for understanding, designing, implementing, testing, reviewing and verifying products.

Package we checked

The manifest we fetched is plugins/product-development/plugin.json in coreycoto/agent-plugins. The plugin root is the directory that holds that file. Its $schema is https://agent-plugins.org/schemas/1.0.0/plugin.schema.json. The manifest lists 19 skills and 1 MCP server (product-development-agents). Extension keys: com.openai. Stored mcp.json transports: product-development-agents stdio.

What product-development does, in the publisher's words

This independently selectable plugin provides the first-party phased-refactor skill for evidence-led refactoring. Eighteen curated engineering skills are optional native Vercel dependencies, declared in skills-lock.json. Their source files are not bundled in this plugin. Initialize the selected dependencies in the consumer project's.agents/skills/, where supported clients can discover them directly. Our own plugin skill remains in the portable skills/ directory.

THIRD_PARTY_NOTICES.md identifies upstream authors and retained license copies.

The native skills-lock.json declares optional upstream skills using Vercel Skills CLI 1.7.0's version-1 format: source, sourceType, immutable ref, skillPath and computedHash. It contains only upstream dependencies, not our first-party plugin skills. No custom ledger or client hook is required.

  • Use the consumer project root as the working directory. Installing the plugin does not install these project dependencies. Read the task's local guidance and review which locked skills are wanted.

From the project README, punctuation lightly normalized · Open the README on GitHub

Skills
19
MCP servers
1
Stars
0
License
MIT
Repo created
2026-10-03
Last pushed
2026-11-13
Publisher type
User
Version
0.10.8

Links

Skills · 19

assess-data-quality
capture-solution
check-protocol
design-change
diagnose-problem
engineering-workflow
implement-change
improve-performance
maintain-verification
manage-codex-agents
Set up Product Development's packaged Codex agents and guide native hook review, installation, upgrades and verification.
model-domain
phased-refactor
Refactor a substantial code or test cluster in evidence-backed phases, preserving behavior through caller audits, parity checks, regression tests and measured validation. Use for selected repository-health findings or an explicitly requested broad structural refactor.
prototype-decision
refresh-solutions
rehearse-migration
review-code
test-behavior
understand-codebase
verify-product

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

MCP servers · 1

product-development-agentsstdio
python3 ${PLUGIN_ROOT}/com.openai/codex_agents/server.py

Read from the plugin's own mcp.json. We list environment variable names, never values.

Category

Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Keywords

codex · engineering · skills · agent-workflows

Related by publisher and keywords

  • git-slopcoreycoto

    Agent guidance for the deterministic git-slop repository token-defragmenter.

  • Plan, sequence, deliver and hand off work using consumer policy and gh-steward for GitHub composition.

  • communicationcoreycoto

    Clear agent communication and evidence-preserving document writing and editing.

  • Evidence-based product discovery, prioritization, requirements and decision experiments.

  • engineering-packHarleyBartles

    First-party engineering delivery, release, and observability skills for the Codex marketplace.

  • codex-quota-optimizerhashgraph-online

    A zero-friction Codex usage governor with task-aware routing, soft budgets, focused context, local audits, and layered verification.

Add the verified badge to your README[![Verified by AgentPluginsDirectory.com against Schema 1.0.0](https://agentpluginsdirectory.com/badge.svg)](https://agentpluginsdirectory.com/plugins/product-development)

✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.