Skip to content
v0.1.0

Software developer agent and skills for any language: implementing and reviewing code, framework practices for ASP.NET Core and Spring Boot, implementing architecture designs, clean code, refactoring, testing, debugging, secure coding, APIs, production readiness, user interfaces, design patterns, algorithms, relational databases and pragmatic practices.

developer

A software developer agent and fifteen skills for any programming language, usable from Claude Code, GitHub Copilot CLI and Codex. It builds and changes code, and it also works as a consultant: a question gets analysis, and a request to build or change gets the verified change.

SkillUse it for
framework-practicesFramework best practices for the installed version, with deep guidance for ASP.NET Core and Spring Boot, looked up through Context7 or the official docs
implementing-designsTurning ADRs, designs and threat models from architect into enforced, verified code
clean-codeNames, functions, comments, classes, errors, async code, translating ideas across languages
reviewing-codeReviewing diffs and pull requests, and preparing them
refactoringCode smells, the catalog of moves and behavior-preserving changes
testingWhat to test, test levels and doubles, legacy code, flaky tests, TDD
debuggingRoot causes, intermittent and production failures, tools by symptom
secure-codingInjection, access control, secrets, crypto, dependencies
api-designEndpoints, errors, pagination, idempotency, compatibility
production-readinessLogs, metrics, timeouts, retries, safe releases
user-interfacesScreen states, forms, accessibility, front-end behavior
design-patternsWhether a pattern fits, GRASP, modern equivalents, anti-patterns
data-structures-and-algorithmsChoosing structures and algorithms, complexity, profiling
relational-databasesSchemas, SQL, indexes, transactions, migrations
pragmatic-practicesRequirements, estimates, Git, upgrades, documentation, teamwork

developer is both an agent and a skill, so it still works in tools without custom agents. Use the architect agent to plan, design and consult on structure, and developer to implement the plan and consult on code. It hands new structural decisions back to architect. Framework lookups work best with the Context7 MCP server connected; without it the agent uses the official docs, or says that it couldn't check.

Install

You don't need to clone the repo.

Claude Code

claude plugin marketplace add facundomartinezvidal/developer-vault
claude plugin install developer@developer-vault

GitHub Copilot CLI

copilot plugin marketplace add facundomartinezvidal/developer-vault
copilot plugin install developer@developer-vault

Codex

codex plugin marketplace add facundomartinezvidal/developer-vault
codex plugin add developer@developer-vault

In Codex, the plugin provides the skills, and developer:developer holds the agent's instructions, so mention that skill to work in this role. Codex plugins can't ship custom agents yet. To also use it as a Codex subagent, install the plugin and add the agent file:

mkdir -p ~/.codex/agents && curl -fsSL https://raw.githubusercontent.com/facundomartinezvidal/developer-vault/main/plugins/developer/com.openai.codex/agents/developer.toml -o ~/.codex/agents/developer.toml

To get updates, run codex plugin marketplace upgrade developer-vault, or the matching marketplace update command in the other tools.

For a single session from a clone: claude --plugin-dir plugins/developer --agent developer:developer, or the same flags with copilot.

Develop

  • Agent: edit src/developer.md, then run python3 scripts/build_agents.py.
  • References: those listed in scripts/vault_manifest.py come from the vault, via python3 scripts/sync_vault.py <path-to-developer-knowledge>, so don't edit them by hand. The rest are hand-written, and say so at the top.
  • Static validation: create a virtual environment, install requirements-dev.txt, then run python scripts/eval_suite.py validate from this folder. Run python -m unittest discover -s scripts/tests -v for evaluation-accounting checks.
  • Behavioral evaluation: python scripts/eval_suite.py prepare --output /tmp/developer-evaluation, then blind and report. The procedure is the same as in the architect plugin, and is described in AGENTS.md.
  • The scripts do not invoke or bill models. Add --check to the build and sync scripts in CI to catch stale output.