agent-harness

by alirezarezvani (GitHub) in alirezarezvani/claude-skills

What it does

Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified

Quoted from the skill's SKILL.md under its MIT license.

Install

git clone --depth 1 https://github.com/alirezarezvani/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills/
cp -r /tmp/claude-skills/engineering/agent-harness/skills/agent-harness ~/.claude/skills/agent-harness

The command copies the skill from the author's repo. SkillTrove does not host it.

Files

• SKILL.md
• assets/harness_manifest.schema.json
• assets/harnesses/business-growth.json
• assets/harnesses/business-operations.json
• assets/harnesses/c-level-advisor.json
• assets/harnesses/commercial.json
• assets/harnesses/compliance-os.json
• assets/harnesses/engineering-team.json
• assets/harnesses/engineering.json
• assets/harnesses/finance.json
• assets/harnesses/loop-library.json
• assets/harnesses/markdown-html.json
• assets/harnesses/marketing-skill.json
• assets/harnesses/marketing.json
• assets/harnesses/product-team.json
• assets/harnesses/productivity.json
• assets/harnesses/project-management.json
• assets/harnesses/ra-qm-team.json
• assets/harnesses/research-ops.json
• assets/harnesses/research.json
• references/agentic_loop_canon.md
• references/domain_harness_design.md
• references/verification_discipline.md
• scripts/goal_compiler.py
• scripts/harness_manifest_builder.py
• scripts/loop_controller.py

Source: https://github.com/alirezarezvani/claude-skills/tree/main/engineering/agent-harness/skills/agent-harness. Checked 2026-10-13.

Similar skills