Hef.Agent — Testing skill for Claude Code
Route a task by size and coupling — trivial fix, light spec path, or the full pipeline — then run it with planning and task tracking.
How to install Hef.Agent
Installs to ~/.claude/skills/joaoariedi-hefesto-hef.agent/SKILL.md
mkdir -p ~/.claude/skills/joaoariedi-hefesto-hef.agent && curl -fsSL https://raw.githubusercontent.com/joaoariedi/hefesto/HEAD/commands/hef.agent.md -o ~/.claude/skills/joaoariedi-hefesto-hef.agent/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Hef.Agent does
model: opus description: "Route a task by size and coupling — trivial fix, light spec path, or the full pipeline — then run it with planning and task tracking" argument-hint: "development task description"
Route, then run
The pipeline is not all-or-nothing, and every independent review of spec-driven tooling reached the same finding: ceremony that does not scale to the task is the reason teams abandon it. This command decides the path before any work starts.
Task: **$ARGUMENTS**
Alternatives in Testing
- Route Research For Testing — route research for testing skill 9.5k ★
- Spec Driven Develop — Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub 975 ★
- Production Grade — Production Grade — route any build, feature, review, test, harden, ship, or docs request through the 14-agent 175 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Cfn Spec
SPARC Specification phase. Make testable acceptance criteria, edge cases, pre/post conditions, invariants BEFO
Hatch3r Bug Pipeline
Run a known-cause bug fix through a 3-phase test-first pipeline -- reproduce + root-cause, regression-test + f
Wb Dev Live Testing
Load directions via mcpwork-buddywb_run("agent_docs", {"path": "dev/live-testing-directions", "depth": "full"}
E2e Pipeline Test
Run the full Lancet2 pipeline on both test profiles back-to-back. Germline (NA12878 / chr1) then somatic (HCC1
Fec Plan
Unified front-end planning entrance - implementation/architecture plan or testing strategy. The implementation
Quality
Improve test coverage, fix tests, optimize performance, reduce bundle size
Related Agents
Light Review Step3
Stage 3 of the Delphi review pipeline — verify code fixes hold up, revert the ones that don't, then compile. F
Salesforce Repository Analyst
Read-only agent that maps the full impacted execution path (trigger/handler/service/selector/LWC/Flow) for a r
Ruver Fd Triage
Ruver FD router. Classifies goal as feature/bug/chore and picks full_feature vs debug_fix vs light_change. No