Agent Harness Skills
Reusable skills for turning real software repositories into agent-ready engineering environments.
Agent Harness Skills helps teams build the repo-side control layer that coding agents need: clear entrypoints, explicit boundaries, runnable validation, runtime evidence, and reviewable delivery records.
Repository
Canonical Git remote:
git@github.com:yfge/agent-harness-skills.git
Use this remote for git-backed installs and for publishing repository updates. A local clone path can still be used anywhere the installation examples accept <repo-url-or-local-path>.
What It Is
Agent Harness Skills is a reusable skill library for designing repository harnesses.
A repository harness is the engineering layer around a codebase that tells an agent where to start, which rules matter, what boundaries it must respect, how to prove a change is safe, and what evidence should be left behind for review. It is not a separate product runtime. It is the control layer that makes an existing repository easier for agents and humans to operate together.
Use it when a project has grown beyond "read the README and run the tests" and needs a more explicit way for agents to navigate source-of-truth documents, validation commands, runtime traces, quality gates, and delivery records.
The guidance is role-based. AGENTS.md, tasks.md, agent_chats/, and artifacts/runs/ are default artifacts, not mandatory forms. If a repository already has an equivalent issue tracker, review template, validation command, generated report, or runtime artifact system, the skills should map those surfaces first and create defaults only for missing roles.
Why It Exists
Coding agents can edit files quickly, but real repositories need more than fast edits. They need a stable operating surface.
Without a harness, an agent has to infer too much: which document is authoritative, which directories are owned by which subsystem, which checks are meaningful, whether an observed failure maps to a runtime error, and what evidence belongs in a review or delivery record. That creates drift, repeated rediscovery, weak validation, and delivery summaries that cannot be audited.
Agent Harness Skills turns those expectations into reusable repository practices. The goal is not to add ceremony. The goal is to make the important work discoverable, executable, and reviewable.
What It Helps Agents Do
- Find the correct entrypoint and source of truth before making changes.
- Understand architecture, ownership, and dependency boundaries.
- Choose the validation surface that actually proves a change.
- Connect observed runtime behavior to logs, traces, request IDs, screenshots, and artifacts.
- Separate code regressions from environment, external dependency, data, or quota blockers.
- Keep task state and acceptance criteria tied to the change that fulfills them.
- Leave concise delivery records through commits, review notes, ledgers, and handoffs.
- Improve quality incrementally without turning every task into a broad refactor.
Included Skills
The skills form a capability map for building and improving an agent-ready repository:
repo-harness-assessment: assess a repository's current agent/harness maturity and identify the smallest useful next slice.agent-entrypoint-design: design AGENTS.md, mirrored agent files, instruction precedence, and source-of-truth navigation.repo-contracts-and-boundaries: turn architecture and directory boundaries into mechanical checks, baselines, and allowlists.validation-harness-design: design repo validation entrypoints, test matrix, JSON/JUnit outputs, and CI gates.runtime-evidence-and-tracing: design run IDs, request IDs, artifact bundles, runtime traces, and failure evidence.agent-ledger-and-delivery: design collaboration ledgers, delivery evidence summaries, and links between tasks, commits, and reviews.quality-gardening: design quality snapshots, structural metrics, debt thresholds, and generated quality reports.design-doc-and-task-board: coordinate design documents, work-state surfaces such as tasks.md, exec plans, status updates, acceptance criteria, and task-to-change traceability.atomic-commit-discipline: split work into minimal commits, include related task-state updates, verify diffs, run scoped checks, and keep related evidence together.
Shared methodology support:
references/harness-profiles.json: machine-readable repository archetypes and role mappings for library, service, monorepo, CLI/tooling, docs-only, and regulated/high-audit repositories.templates/: neutral starter templates for missing roles such as entrypoints, validation matrices, delivery records, work-state surfaces, runtime evidence summaries, and quality reports.Detected Mapping: every skill output should name the repository's existing equivalent artifacts before recommending new files.
When To Use
Use this repository when you want to:
