Skip to content
harnesspmv0.5.1
Color scheme
Contrast
Color scheme
Contrast

For AI agents

In short

  • This part of the site is for you, an AI coding agent that a person asked to work with harnesspm. It has every step.
  • In a project that already uses harnesspm, read what is installed first. It matches the installed version. This site describes the latest one.
  • Never give yourself permissions. Trust and approval belong to the person.
  • llms.txt lists every page of this site with a Markdown copy.

What is installed

A project that uses harnesspm already gives you this:

Where What
The managed block in AGENTS.md Always-on rules, pointers to other rules, a docs index and scripts for each package. Every line ends with a unit ID.
The skills harnesspm-import, harnesspm-export and harnesspm-improve The steps for using, sharing and improving a harness.
node_modules/.harnesspm/docs/harnesspm/llms.txt The specification, at the installed version.

No block in AGENTS.md means the project does not use harnesspm yet:

  • To use the harness of its dependencies, start with Set up a project.
  • To share a harness from a library, start with Share a harness from your library. It needs only the dev dependency. The skills are then files in node_modules/@tenphi/harnesspm/harness/skills/.

Rules that always apply

  1. Never edit an output. The managed block, CLAUDE.local.md, and the files and links in .claude/, .codex/ and .agents/skills/ are generated. Change the source that npx harnesspm why <ID> names.
  2. Sync after a change. After you change harnesspm.json or a harness file, and after npm install <pkg> or pnpm add <pkg>, run npx harnesspm sync.
  3. Ask before you trust. Do not add a package to trust in harnesspm.json without the person’s agreement. Say what each pending tool does: harness/plugin.json of its package has each script’s description, and "allow": true when it asks to run without a prompt.
  4. Do not grant permissions. When you run harnesspm, new allow rules, hooks and MCP servers stay pending. Ask the person to run npx harnesspm approve in their own terminal. In a Claude Code cloud session, where the person has no terminal, ask them to run the install in the environment’s setup script instead. Do not edit agent settings files to work around it.
  5. Save a change the owner’s way. Read AGENTS.md and CONTRIBUTING.md of the repository that owns the unit. When they say nothing, show the change, ask, and use a branch and a pull request.
  6. Keep added harnesses out of the project. Their outputs are per machine. Never commit them.
  7. Report at the end. Say what you wrote, what is pending, and what the person has to do.

Why rules 3 and 4 are strict: a harness can ship scripts, hooks and MCP servers. They run code on the person’s machine, some of them without a prompt. Trust and safety has the full model.

Pick the task

The person asks to Read
Set up harnesspm, or use what the dependencies ship Set up a project, then Use a package’s harness
Turn on a package’s tools Trust and safety
Fix or drop a rule that comes from a dependency Change upstream units
Remember something, or improve a harness Change upstream units
Share a harness from a library Share a harness from your library, with the package format
Add their own or their team’s harness Add your own or your team’s harness
Work in a monorepo Monorepos
Work in a Claude Code cloud session Cloud sessions
See how agents use the harness Telemetry
Look up a command or a field CLI, harnesspm.json

The specification has every rule behind these pages.