Imported from marcoemrich/agentic_coding_lab (experiments/runs/2026-09-05_12-42-01_claim-office-example-mapping_v3-basic-tdd-pi_gpt-6-astra-codex-no-thinking-2/AGENTS.md). Install upstream with npx skills add marcoemrich/agentic_coding_lab --skill 2026-09-05_12-42-01_claim-office-example-mapping_v3-basic-tdd-pi_gpt-6-astra-codex-no-thinking-2. Copyright stays with the author.
TDD Experiment Mode (pi)
Complete the coding exercise autonomously using Test-Driven Development.
Read prompt.md, then work through the kata test by test.
Do NOT wait for human approval between phases.
Run the full TDD cycle until all tests pass.
Running Tests
Use pnpm test to run tests.
CLI Entry Point
If the prompt asks for a CLI entry point, create src/cli.ts (reads JSON from
stdin, writes JSON to stdout).
Done Marker
When you are finished, write a file experiment-done.txt whose entire content
is the single word DONE. Do not write any other summary or report file.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
yaml
targets:
- https://api.opensmartroute.ai/api/v1/registry/marcoemrich-agentic-coding-lab-2026-09-05-12-42-01-claim-4b620d/manifest # or paste the manifest below
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "marcoemrich-agentic-coding-lab-2026-09-05-12-42-01-claim-4b620d",
"kind": "skill",
"name": "2026-09-05_12-42-01_claim-office-example-mapping_v3-basic-tdd-pi_gpt-6-astra-cod",
"description": "Complete the coding exercise **autonomously** using Test-Driven Development. Read `prompt.md`, then work through the kata test by test.",
"publisher": "marcoemrich",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Complete the coding exercise **autonomously** using Test-Driven Development. Read `prompt.md`, then work through the kata test by test."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-agents",
"repository": "https://github.com/marcoemrich/agentic_coding_lab",
"path": "experiments/runs/2026-09-05_12-42-01_claim-office-example-mapping_v3-basic-tdd-pi_gpt-6-astra-codex-no-thinking-2/AGENTS.md",
"ref": "dbe13e730fe13e29303dc017c548390849cc411b",
"url": "https://github.com/marcoemrich/agentic_coding_lab/blob/dbe13e730fe13e29303dc017c548390849cc411b/experiments/runs/2026-09-05_12-42-01_claim-office-example-mapping_v3-basic-tdd-pi_gpt-6-astra-codex-no-thinking-2/AGENTS.md",
"key": "marcoemrich/agentic_coding_lab/experiments/runs/2026-09-05_12-42-01_claim-office-example-mapping_v3-basic-tdd-pi_gpt-6-astra-codex-no-thinking-2/AGENTS.md"
}
},
"instructions": "# TDD Experiment Mode (pi)\n\nComplete the coding exercise **autonomously** using Test-Driven Development.\nRead `prompt.md`, then work through the kata test by test.\n\n- Do NOT wait for human approval between phases.\n- Run the full TDD cycle until all tests pass.\n\n## Running Tests\n\nUse `pnpm test` to run tests.\n\n## CLI Entry Point\n\nIf the prompt asks for a CLI entry point, create `src/cli.ts` (reads JSON from\nstdin, writes JSON to stdout).\n\n## Done Marker\n\nWhen you are finished, write a file `experiment-done.txt` whose entire content\nis the single word `DONE`. Do not write any other summary or re",
"cost": {
"context_tokens": 152
}
}
Fetch it by URL: GET /api/v1/registry/marcoemrich-agentic-coding-lab-2026-09-05-12-42-01-claim-4b620d/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
