# revfactory/harness **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/revfactory-harness).** _How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._ 9,337 stars · 1,344 forks · Apache-2.0 ## Links - GitHub: https://github.com/revfactory/harness - Homepage: https://revfactory.github.io/harness/ - awesome-repositories: https://awesome-repositories.com/repository/revfactory-harness.md ## Topics `claude-code` `claude-code-plugin` `harness` `harness-engineering` ## Description Harness is a framework that turns a plain-language description of a project or domain into a team of specialized AI agents. Each agent gets a defined role, tool restrictions, and a model tier suited to its task, and the agent definitions, supporting skills, and a minimal pointer file are written as plain files inside the target project so the same team can be reused in later sessions. Generation follows a fixed six-phase workflow that audits any existing setup, analyzes the task domain, selects a team structure, writes the definitions, and validates the result. What sets it apart is how the teams are organized and run. Work can be arranged in one of six coordination patterns, including pipeline, fan-out and fan-in, expert pool, producer-reviewer, supervisor, and hierarchical delegation. Agents run either as persistent collaborators that exchange messages and share task lists, or as lightweight one-shot subagents. Deterministic scripted workflows are also available, with typed output schemas, budgets, and partial re-runs. Skills use progressive disclosure, exposing a short description by default and loading full instructions or reference material in stages to keep each agent's context small. Quality and maintenance are built in. A catalogue of verification patterns, such as adversarial checks, judge panels, loop-until-dry sweeps, and completeness critics, filters out output that looks plausible but is wrong. Generated setups can be checked with trigger evaluations, dry runs, and with-versus-without comparisons of skills. Over time, a setup can be improved from usage feedback, with every change recorded in a history, and files produced by earlier versions can be detected and upgraded to the current format. The repository also includes five worked example teams covering research, fiction, webtoon creation, code review, and migration, along with orchestrator templates for both team mode and subagent mode. ## Tags ### Artificial Intelligence & ML - [Team Generation from Descriptions](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-team-catalogs/team-generation-from-descriptions.md) — Turns a plain-language project or domain description into a team of specialized agents, each with a defined role, tools, and one of six architecture patterns. ([source](https://revfactory.github.io/harness-animation/)) - [Agent Team Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-team-generators.md) — Generates a team of specialized AI agents from a plain-language project description, writing roles, tool restrictions, and skills as reusable files in the project. - [Agent Team Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agents/agent-team-orchestration.md) — Turns a plain-language project or domain description into a team of specialized agents, each with a defined role, without hand-writing definitions. ([source](https://github.com/revfactory/harness#readme)) - [Agent Orchestration Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-orchestration-frameworks.md) — Coordinates agents through six architecture patterns, including pipeline, fan-out and fan-in, and supervisor, in persistent team mode or one-shot subagent mode. - [Agent Team Architecture Patterns](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-team-architecture-patterns.md) — Offers six team patterns, including pipeline, fan-out and fan-in, expert pool, producer-reviewer, supervisor, and hierarchical delegation, to match task structure. ([source](https://github.com/revfactory/harness/blob/main/CHANGELOG.md)) - [Agent Team Coordination Patterns](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-team-coordination-patterns.md) — Offers six coordination patterns for arranging agent teams, including pipeline, fan-out and fan-in, expert pool, producer-reviewer, supervisor, and hierarchical delegation. - [Agent Workflow Orchestrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-workflow-orchestrations.md) — Runs agent steps as scripted pipelines and parallel branches with typed output schemas, budgets, partial re-runs, and isolated worktrees. ([source](https://github.com/revfactory/harness#readme)) - [Agent Harnesses](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-harnesses.md) — Builds a complete set of agents and skills from a project description by following a guided six-phase workflow. ([source](https://github.com/revfactory/harness/blob/main/CHANGELOG.md)) - [Phase-Based Generation Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-application-orchestrators/agent-orchestration/phase-based-generation-pipelines.md) — Generates agent files through a fixed six-phase workflow: auditing, analyzing the domain, selecting a structure, writing definitions, and validating. - [Persistent Collaborating Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/persistent-collaborating-agents.md) — Keeps named agents alive across turns, exchanging messages and sharing task lists so specialists retain context during iterative feedback and negotiation. ([source](https://revfactory.github.io/harness/)) - [Judge Panels and Completeness Critics](https://awesome-repositories.com/f/artificial-intelligence-ml/adversarial-draft-critics/judge-panels-and-completeness-critics.md) — Ships a catalogue of verification patterns such as adversarial checks, judge panels, and completeness critics that filter plausible but wrong agent output. - [Agent Execution Modes](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-execution-modes.md) — Runs agents either as persistent collaborators sharing messages and task lists, or as lightweight one-shot subagents returning only final results. - [Agent Setup Evolution](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-setup-evolution.md) — Improves agent setups from usage feedback, records every change in a history, and upgrades files from earlier versions to the current format. - [Agent Setup Evolution from Feedback](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-setup-evolution-from-feedback.md) — Improves agent setups over time by generalizing usage feedback into fixes applied to agents, skills, and coordinators, recording every change in a history. - [Agent Skill Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-skill-configurations/skill-quality-validators/agent-skill-generators.md) — Creates agent skills that reveal detail in stages so each agent loads only the instructions it needs and keeps context small. ([source](https://github.com/revfactory/harness#readme)) - [Self-Evolving Agent Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-skill-frameworks/self-evolving-agent-frameworks.md) — Improves agents, skills, and coordinators from usage feedback, records every change in a history log, and upgrades legacy files to the current format. - [Progressive Disclosure Loaders](https://awesome-repositories.com/f/artificial-intelligence-ml/automated-skill-loading-systems/progressive-disclosure-loaders.md) — Skills expose a short description by default and load full instructions or reference material in stages, keeping each agent's context small. - [Role-Based Agent Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-model-definitions/custom-agent-flow-definitions/role-based-agent-definitions.md) — Defines each agent's role with tool restrictions, such as read-only reviewers, plus a standard section on how to re-invoke the agent. ([source](https://github.com/revfactory/harness/blob/main/CHANGELOG.md)) - [Feedback-Driven Agent Setup Evolution](https://awesome-repositories.com/f/artificial-intelligence-ml/feedback-driven-agent-setup-evolution.md) — Captures the gap between initial and current setup, generalizes usage feedback, and applies fixes to agents, skills, and coordinators with a recorded change history. ([source](https://github.com/revfactory/harness#readme)) - [Typed Scripted Workflows](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-workflow-orchestrations/python-script-orchestrators/typed-scripted-workflows.md) — Provides deterministic scripted workflows with typed output schemas, budgets, and partial re-runs so handoffs between steps need no output parsing. - [Output Verification Loops](https://awesome-repositories.com/f/artificial-intelligence-ml/model-output-verifications/output-verification-loops.md) — Includes loop-until-dry sweeps and verification patterns that iteratively check and refine model output to remove plausible but incorrect results. - [Subagent Delegation](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-orchestration/subagent-delegation.md) — Dispatches lightweight one-shot subagents in parallel for fire-and-forget tasks where only final results are returned to the lead. ([source](https://revfactory.github.io/harness/)) - [Reusable Instruction Skills](https://awesome-repositories.com/f/artificial-intelligence-ml/reusable-instruction-skills.md) — Writes reusable skills that load detail in stages so each agent reads only needed instructions, keeping context small. - [Workspace Skill Authoring](https://awesome-repositories.com/f/artificial-intelligence-ml/workspace-skill-authoring.md) — Generates skill files that describe how each task is performed, loading a short description by default and full instructions when needed. ([source](https://revfactory.github.io/harness-animation/)) ### Testing & Quality Assurance - [Agent Output Verification Patterns](https://awesome-repositories.com/f/testing-quality-assurance/agent-output-verification-patterns.md) — Provides a catalogue of verification patterns, including adversarial checks, judge panels, loop-until-dry sweeps, and completeness critics, to filter plausible but wrong output. ([source](https://github.com/revfactory/harness/blob/main/CHANGELOG.md)) - [Automated Agent Quality Assurance](https://awesome-repositories.com/f/testing-quality-assurance/automated-agent-quality-assurance.md) — Filters plausible but wrong agent team results using adversarial checks, judge panels, completeness critics, and with-versus-without skill comparisons. - [Agent Output Verifications](https://awesome-repositories.com/f/testing-quality-assurance/validation-verification/input-validation/agent-input-and-output-validators/automated-assertion-validators/action-result-validators/outcome-assertions/agent-output-verifications.md) — Offers a catalogue of verification patterns such as adversarial checks, judge panels, and completeness critics that filter plausible but wrong agent output. - [Model Output Quality Evaluations](https://awesome-repositories.com/f/testing-quality-assurance/model-output-quality-evaluations.md) — Filters plausible but wrong results using adversarial verification and judge panels, and tests skills with trigger evaluations, dry runs, and with-versus-without comparisons. ([source](https://github.com/revfactory/harness/blob/main/README.md)) ### Development Tools & Productivity - [Modular Skill Authoring](https://awesome-repositories.com/f/development-tools-productivity/modular-skill-authoring.md) — Provides a process for authoring reusable skills that reveal detail in stages while documenting how each task is done. ### DevOps & Infrastructure - [Multi-Step Workflow Orchestration](https://awesome-repositories.com/f/devops-infrastructure/automated-workflow-orchestration/multi-step-workflow-orchestration.md) — Runs scripted pipelines and parallel fan-outs with typed schemas, budgets, and partial re-runs for verification loops and large jobs. ([source](https://revfactory.github.io/harness/)) - [Agent Configuration Files](https://awesome-repositories.com/f/devops-infrastructure/configuration-management/file-based-configuration/agent-configuration-files.md) — Writes agent roles, skills, and a minimal pointer file as plain files in the target project so the same team can be reused later. ### Software Engineering & Architecture - [Agent Execution Mode Selection](https://awesome-repositories.com/f/software-engineering-architecture/execution-control/agent-execution-mode-selection.md) — Guides choosing between scripted workflows, persistent collaborating agents, and one-shot subagents by how predictable the control flow is. ([source](https://github.com/revfactory/harness#readme)) - [Project Agent File Writers](https://awesome-repositories.com/f/software-engineering-architecture/project-context-managers/on-demand-context-loading/skill-files/project-agent-file-writers.md) — Writes agent definitions, skills, and a minimal pointer file recording the trigger rule and change history directly inside the target project for reuse. ([source](https://github.com/revfactory/harness/blob/main/README.md)) ### Part of an Awesome List - [Generators and Meta Harnesses](https://awesome-repositories.com/f/awesome-lists/ai/generators-and-meta-harnesses.md) — Meta-skill that generates domain-specific agent teams and skills. - [Autonomous Coding Agents](https://awesome-repositories.com/f/awesome-lists/devtools/autonomous-coding-agents.md) — Team-architecture factory for designing domain-specific agent teams.