Contribute a public change to Harness Anything from a GitHub issue through an isolated worktree, scoped tests, manifest-selected gates, a complete PR body, review triage, and maintainer merge. Use when a human or coding agent is preparing or updating a contribution to this repository.
A setup skill for adding Harness Anything to a project that has never used it before. Harness Anything is a project task and tracking system, but the description does not explain its specific features.
Diagnose and migrate a Harness Anything ledger from a machine that does not have the current Harness installed. Use when a project's harness/ ledger predates the current generation, when daemon attach fails because a current ledger has pre-S4 doc cuts, or when a user asks to upgrade, migrate, replay, or repair an old…
Create, review, or update Harness Anything preset-manifest/v3 packages, including profiles, completion gate selection, template selections, output shapes, script entrypoints, capability declarations, package validation, and preset tests. Use when authoring or migrating a Harness Anything preset.
Create, review, or update Harness Anything verticals. Use when designing vertical-definition JSON, declarative completion sources and gates, template catalogs, entity kinds, package scaffolds, projection schemas, and preset layering for a new Harness Anything domain such as coding, QA, docs, design, or operations.
A skill for coordinating work among multiple AI agents through defined roles, task delegation, checks, and model selection. It also covers adding models to the coordination system.
★not rated 232▲
+3
changed 3d agoA73 tokens
AGPL-3.0
An installation guide for connecting Harness Anything to a chosen coding agent. It checks the environment, obtains the source, installs dependencies, links the skills into the agent's user directory, and starts project setup.
Define domain completion sources and task gates in vertical and preset packages, including artifact-only command checks, JSON Schema predicates, artifact bindings, closeout defaults, manual witnesses, validation, and submit/reject/repair behavior. Use when adding a domain completion gate or diagnosing a completion…
Run and interpret a read-only retrospective over Harness ledger projections, then prepare evidence-backed mechanism fixes, deletion candidates, or time-bounded rule proposals for human adjudication.
Develop or review Harness Anything GUI pages and shared components using its existing design system, entity navigation, motion preferences, and background Electron verification. Use for packages/gui work and GUI-specific agent missions.
A workflow for creating and updating a single self-contained HTML page that explains a task. It chooses a page structure for coding, research, writing, or operations work and uses supplied task context.
Create or update a Harness Anything business Agent — a declared identity with its own instructions, prompts, skills, role, preset, runtime targets, and permission mode — instead of only naming a model. Use when a user asks to create an agent, define a new worker/commander/reviewer, give an agent its own job, or split…
Write or revise a project skill for a Harness Anything Agent — a SKILL.md with frontmatter, real trigger conditions, executable steps, and an explicit deletion budget, discovered from the workspace or harness skill roots. Use when a user wants to add a skill, teach an Agent a procedure, turn a repeated manual sequence…
Turn one delivery into a bounded, evidence-backed proposal to change your own instructions, prompts, skills, or tool scripts — including what to delete. Use at the end of a delivery turn, or when the owner resumes a delivered Agent with "how would you do better next time / what tool would you give yourself / what…
A set of working methods for teams building long-running software projects with coding agents such as Codex or Claude Code. It covers project setup, planning, documentation, delivery, reviews, and automation.
Use when creating, reviewing, improving, or installing Coding Agent Harness preset packages for repeatable task families.
★not rated 59 3mo agoA25 tokens
AGPL-3.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: