Skip to main content
plugin

agent-harness · phuryn — Claude Code plugin: features and installation

The agent-harness Claude Code plugin organizes agent instructions, hooks, and persistent work status. Its skills handle session handovers and turn session friction into setup changes.

MIT ★ 741 updated 2026-11-14

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add phuryn/product-engineering
/plugin install agent-harness@product-engineering
Open on GitHub

What agent-harness does

agent-harness bundles six skills for maintaining an agent setup. Some activate on their own: they maintain AGENTS.md and CLAUDE.md, enforce rules through Claude Code hooks, and keep work status available across sessions. flight-deck maintains a status board and a log for each work area.

Two skills are started manually at the end of a session. handover checks files and running processes before writing a note for the next session. retro turns session problems into changes to instructions, routing, hooks, or scripts; it can also conclude that no setup change is warranted.

windows-agent-shell covers agent failures and silent file corruption in Git Bash, PowerShell, and cmd.

What it helps with

  • carry long-running work status across sessions
  • prepare a handover with current facts and the next concrete action
  • turn session findings into instruction or hook changes
  • address agent failures in Windows shells
  • maintain instructions for different kinds of agent work

Example prompts for the agent

  • Write a handover for the next session: /agent-harness:handover.
  • Review what went wrong in this session and suggest a setup change: /agent-harness:retro.
  • Update the agent instructions for this area of work.

How to install agent-harness

Plugin marketplace

/plugin marketplace add phuryn/product-engineering
/plugin install agent-harness@product-engineering

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about agent-harness

How do I install agent-harness in Claude Code?

Run these commands in order: /plugin marketplace add phuryn/product-engineering, then /plugin install agent-harness@product-engineering.

What does agent-harness do?

It provides skills for agent instructions, hooks, persistent work status, session handovers, and Windows shell issues.

Which agent-harness skills do I start manually?

Start handover or retro at the end of a session with /agent-harness:handover or /agent-harness:retro. The other skills activate on their own.

Source text

agent-harness · MIT
# agent-harness — make your own agent setup reliable

The machinery around the agent: instructions met at the moment they apply, rules held by code instead of prose, state that survives the context window, and the shell traps that break agents on Windows.

## Install

```bash
claude plugin marketplace add phuryn/product-engineering
claude plugin install agent-harness@product-engineering
```

Codex, Cursor and other agents: see the collection's root `README.md`.

## Skills (6)

**You start them**, at the end of a session (`/agent-harness:<skill>` in Claude Code, `$agent-harness:<skill>` in Codex):

- **handover** — The note the next session starts from: the objective, what is true now, the evidence actually obtained, what is left, the open decisions and the next concrete action, reconciled with the disk and the running processes before it is written.
- **retro** — A session's learnings, built into your setup: what went wrong and why, then an improved instruction, route, hook or script, checked where it applies, or "no setup change warranted".

**They start on their own:**

- **agent-instructions** — Writing and maintaining the instruction file every session reads (AGENTS.md / CLAUDE.md): a general section and a product section, a router keyed by what the agent is doing, progressive disclosure, receipts, and the passes that keep it short and true.
- **guardrail-hooks** — Turning a rule an agent must remember at the decisive moment into a code path: Claude Code hooks that ask before one-way doors or block a wrong commit identity, with templates to adapt.
- **flight-deck** — Two files per area of work — a STATUS board rewritten in place and a LOG appended to — so long-running work stays legible across context compaction; and the owner's page, one shared page holding only what needs the human, under a short status, with several areas of work as tabs, each with a board of its key items.
- **windows-agent-shell** — The Windows (Git Bash, PowerShell, cmd) traps that make coding agents fail or silently corrupt files, and the wider class of works-here-breaks-there.

## Author

Paweł Huryn — [The Product Compass](https://www.productcompass.pm)

© Paweł Huryn · MIT · phuryn/product-engineering

Similar plugins

All plugins for Agent setup: memory, context, orchestration →

agent-harness by other authors comes first.

agent-harness Alireza Rezvani agent-harness — a Claude Code plugin that turns any skills domain folder into a bounded agentic loop with a hard close gate. The cycle runs execute → verify → close and blocks completion until every task is verified or explicitly waived. ★ 30,251repo stars eval-harness affaan-m eval-harness — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that brings eval-driven development into every agent session: success criteria go in before any code, results are scored with pass@k and pass^k. CX Codex +1 6,500installs pydantic-ai-harness pydantic pydantic-ai-harness — a skill to extend Pydantic AI agents with coding, file, and command execution, sandboxed isolation (Modal, E2B, Sprites), and cross-session memory. CX Codex +1 3,300installs harness-creator walkinglabs harness-creator is a Claude Code skill that builds, audits, and fixes scaffolding for coding agents. It generates agent instructions, state files, and verification gates to prevent task drift. CX Codex +1 2,600installs test-harness zernie test-harness — a Claude Code skill that tests your harness — hooks, skills, settings, CLAUDE.md. Two of three test tiers run free on every commit with no API key. CX Codex +1 2,100installs everything-claude-code-harness reason-machines everything-claude-code-harness — a skill for Claude Code, Codex, Cursor, GitHub Copilot, and Gemini CLI that layers subagents, slash commands, lifecycle hooks, security scanning, and language-specific rules onto your agent setup. CX Codex +1 1,800installs debug-my-harness zernie debug-my-harness reads the local .vigiles/runs.jsonl ledger to explain why an agent harness misbehaved. Use it when a skill stopped firing, a hook let something through, or a subagent broke its tool contract. CX Codex +1 1,500installs

From the same set51

The whole set →
app-lifecycle The app-lifecycle skill for Claude Code and Codex maps a SaaS product’s path from idea to production into stages with completion criteria. It activates for questions about the current stage, next steps, or whether a stage is done. CX Codex +1 ★ 741repo stars codex-agents The codex-agents Claude Code skill brings Codex CLI in as a second agent for implementation and independent review. It responds to requests to consult Codex and to decisions with competing options. CX Codex +1 ★ 741repo stars independent-review The independent-review Claude Code skill runs an independent code review before a release and after fixes. The reviewer must start in a session that did not build the change. CX Codex +1 ★ 741repo stars work-humanizer work-humanizer is a Claude Code plugin that revises work writing with an AI-like tone while preserving its meaning. It can also interview the writer and shape a piece from their answers. ★ 741repo stars app-stack The app-stack Claude Code plugin guides SaaS development from idea to production with Next.js, Supabase, Clerk, and Netlify. Its skills cover product stages, authorization, UI, analytics, and more. ★ 741repo stars agent-teams The agent-teams Claude Code plugin guides task delegation and lets coding agents act as peers, builders, or independent reviewers. Use it to brief a delegate or work with Codex CLI, Grok CLI, or headless Claude Code. ★ 741repo stars ai-shipping The ai-shipping Claude Code plugin documents AI-built apps and checks changes before release. Its ship-check command brings documentation, reviews, and test coverage into one workflow. ★ 741repo stars product This Claude Code plugin helps decide what to build before development starts. It turns idea research, hypotheses and key screens into a draft for the product owner to review. ★ 741repo stars

Project sponsors

Companies that keep this analytics open