agentleFS
giolaqgiolaq/tv-build-harness/CLAUDE.md

tv-build-harness

CLAUDE.md4 starsChanged 4 months agoMIT-0View on GitHub

Use this guide to locate the right file before editing. This repo builds TV apps with a phase-based harness, local skills, and verification checks. This file is for contributors changing the repository. For agents driving tv-build as a CLI tool, read AGENTS.md. For CLI behavior changes, also run the affected command, for example: All three paths delegate phase ordering and retries to packages/harness/src/pipeline-engine.ts. Skill frontmatter must keep this contract: applies_to names phases that may load the skill. Keep skill changes…

The file

Show its rules and text

We split this CLAUDE.md into the rules it gives an agent

15 rules. About 0 are common, 7 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this guide to locate the right file before editing.

    line 3
  2. Very specific:

    All three paths delegate phase ordering and retries to packages/harness/src/pipeline-engine.ts.

    line 32
  3. Very specific:

    Add frontmatter with name and applies_to.

    line 66
  4. Distinctive:

    Write concrete instructions, commands, file paths, and failure modes.

    line 67
  5. Very specific:

    Update skills/README.md if the inventory is not generated by your task.

    line 69
  6. Very specific:

    Add the phase spec in packages/harness/src/harness-config.ts.

    line 73
  7. Very specific:

    Add dependencies or exported phase names in packages/harness/src/types.ts when needed.

    line 74
  8. Very specific:

    Add prompt loading in packages/harness/src/phase-prompts.ts and prompt text under packages/harness/prompts/ when needed.

    line 75
  9. Distinctive:

    Add verify checks to the phase spec if the phase has mechanical success criteria.

    line 76
  10. Very specific:

    Add optional screens.json, design.json, run.json, or harness.config.json only when the example uses them.

    line 83
  11. Distinctive:

    Document any required API key or local platform prerequisite.

    line 85
  12. Distinctive:

    Do not add runtime dependencies without documenting why.

    line 89
  13. Very specific:

    Do not edit packages/verification/src/stats/* or golden specs unless the task explicitly asks.

    line 90
  14. Distinctive:

    Do not rewrite prompts or skills opportunistically.

    line 91
  15. Distinctive:

    Keep docs second person, imperative, and concrete.

    line 92

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

TV Build Harness

Use this guide to locate the right file before editing. This repo builds TV apps with a phase-based harness, local skills, and verification checks.

This file is for contributors changing the repository. For agents driving tv-build as a CLI tool, read AGENTS.md.

Repo Map

  • packages/harness/: CLI, orchestrators, phase engine, prompts, local doctor, and run reports.
  • packages/verification/: statistical verification utilities and tests for harness quality.
  • packages/web-ui/: experimental UI package; verify status before relying on it.
  • packages/shared-types/: shared TypeScript types package.
  • skills/: local skill library; each skill lives at skills/<name>/SKILL.md.
  • examples/: runnable input sets such as cooking-shows, fitness-tv, and KMP examples.
  • docs/: current docs plus docs/archive/ for historical planning docs from the IMPROVEMENT_PLAN.md era.

Golden Commands

  • cd packages/harness && yarn typecheck && yarn test
  • cd packages/verification && yarn test when packages/verification changes.

For CLI behavior changes, also run the affected command, for example:

  • cd packages/harness && npx tsx src/index.ts --help

Run Modes

  • run: Anthropic API path backed by packages/harness/src/orchestrator.ts.
  • claude-run: Claude CLI subprocess path backed by packages/harness/src/claude-orchestrator.ts.
  • Strands/provider path: multi-provider path backed by packages/harness/src/strands-orchestrator.ts.

All three paths delegate phase ordering and retries to packages/harness/src/pipeline-engine.ts.

Where Things Live

NeedFile or directory
Add or change a phasepackages/harness/src/harness-config.ts
Add a verify check implementationpackages/harness/src/verification.ts
Add prompt text for a phasepackages/harness/prompts/ and packages/harness/src/phase-prompts.ts
Add or inspect skill loadingpackages/harness/src/skill-library.ts
Add a skillskills/<name>/SKILL.md
Change CLI commandspackages/harness/src/index.ts
Change report outputpackages/harness/src/run-report.ts
Change phase dependencies/typespackages/harness/src/types.ts
Change Vega tooling checkspackages/harness/src/vega-tools.ts
Change Android CLI lifecycle behaviorpackages/harness/src/platforms/android-tv.ts and packages/harness/src/commands/android.ts
Change Android phase knowledgepackages/harness/prompts/android_test_loop.md and skills/android-tv-testing/SKILL.md

Skill frontmatter must keep this contract:

---
name: skill-name
applies_to: [phase_name]
---

applies_to names phases that may load the skill. Keep skill changes additive unless a task explicitly asks for a rewrite.

Recipes

Add A Skill

  1. Create skills/<name>/SKILL.md.
  2. Add frontmatter with name and applies_to.
  3. Write concrete instructions, commands, file paths, and failure modes.
  4. Run cd packages/harness && yarn test.
  5. Update skills/README.md if the inventory is not generated by your task.

Add A Phase

  1. Add the phase spec in packages/harness/src/harness-config.ts.
  2. Add dependencies or exported phase names in packages/harness/src/types.ts when needed.
  3. Add prompt loading in packages/harness/src/phase-prompts.ts and prompt text under packages/harness/prompts/ when needed.
  4. Add verify checks to the phase spec if the phase has mechanical success criteria.
  5. Run cd packages/harness && yarn typecheck && yarn test.

Add An Example

  1. Create examples/<name>/.
  2. Include content.json, brand.json, and prompt.txt.
  3. Add optional screens.json, design.json, run.json, or harness.config.json only when the example uses them.
  4. Validate config with the harness CLI or run the example with --generate-only when model access is available.
  5. Document any required API key or local platform prerequisite.

Editing Rules

  • Do not add runtime dependencies without documenting why.
  • Do not edit packages/verification/src/stats/* or golden specs unless the task explicitly asks.
  • Do not rewrite prompts or skills opportunistically; they are load-bearing.
  • Keep docs second person, imperative, and concrete.
  • To add a verify check to the branding phase, edit packages/harness/src/harness-config.ts.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.