Test Platform Worker

What it does

Example prompts

• “/test-platform-worker”

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

1. 1Read mission.md, mission AGENTS.md, .factory/services.yaml, and .factory/library/*.md relevant to runtime/test topology.
2. 2Confirm the feature’s boundary changes before editing anything: ports, schema path, queue prefix rules, CI/local runtime reuse, or…
3. 3Reproduce the current blocker first with the canonical command from .factory/services.yaml.
4. 4If the work touches backend/runtime/schema
5. 5If the work touches website/browser runtime or browser-visible readiness
6. 6Make the minimum infrastructure/config/code changes needed to unblock the shared path.
7. 7Re-run the specific failing command(s), then run the broader shared checks affected by the feature.
8. 8Update shared state if the feature proves factual runtime changes workers need (services.yaml, .factory/library/*, mission AGENTS.md if…
9. 9In the handoff, be explicit about

What it can do on your machine

Read from SKILL.md and the folder at commit 5ffd0a0. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Test Platform Worker loads about 1.2k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 331 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~29

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from CorrectRoadH/OpenTickly at commit 5ffd0a0, republished under its AGPL-3.0 licence (© CorrectRoadH). 331 words, ~1,207 tokens.

name

test-platform-worker

description

Harden shared test infrastructure, runtime readiness, schema setup, and parallel lane behavior.

{
  "salientSummary": "Aligned local validation to reuse 8080/5173, fixed the PG* projection path for pgschema, and made readiness checks depend on reachable HTTP probes instead of startup logs. `go test ./apps/backend/internal/bootstrap/... -count=1` and the browser smoke path are now green.",
  "whatWasImplemented": "Updated runtime/test infrastructure so the mission uses one canonical local path: backend on 8080, website on 5173, external Postgres on 5432 with a dedicated test schema managed by pgschema. Fixed the failing bootstrap/runtime setup, added explicit readiness gating, and verified the browser lane against the real reused runtime.",
  "whatWasLeftUndone": "",
  "verification": {
    "commandsRun": [
      {
        "command": "go test ./apps/backend/internal/bootstrap/... -count=1",
        "exitCode": 0,
        "observation": "Bootstrap tests passed after env/schema alignment changes."
      },
      {
        "command": "PGHOST=localhost PGPORT=5432 PGDATABASE=opentoggl PGUSER=opentoggl pgschema plan --file apps/backend/internal/platform/schema/schema.sql",
        "exitCode": 0,
        "observation": "Plan executed successfully against the external Postgres service."
      },
      {
        "command": "vp run test:e2e:website -- --list",
        "exitCode": 0,
        "observation": "Website E2E inventory is available against the reused local runtime."
      }
    ],
    "interactiveChecks": [
      {
        "action": "Opened the reused website runtime with agent-browser after HTTP probe success and navigated into the shell.",
        "observed": "The site loaded on 5173 and the shell was interactive without readiness races."
      }
    ]
  },
  "tests": {
    "added": [
      {
        "file": "apps/backend/internal/bootstrap/...",
        "cases": [
          {
            "name": "runtime readiness uses canonical PG* projection",
            "verifies": "pgschema and backend startup follow one aligned env path"
          }
        ]
      }
    ]
  },
  "discoveredIssues": []
}

© CorrectRoadH, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .factory/skills/test-platform-worker of CorrectRoadH/OpenTickly.

Open the folder on GitHubat commit 5ffd0a0