Backend Test Worker

What it does

When your agent uses it

• Databases work in your project

Example prompts

• “/backend-test-worker”

Workflow steps

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

1. 1Read mission.md, mission AGENTS.md, {repo-root}/.factory/services.yaml, and {repo-root}/.factory/library/architecture.md from this…
2. 2Identify which assertions the feature fulfills, list every expectedBehavior bullet from the
3. 3Write failing Go tests first at the narrowest effective layer
4. 4Use real PostgreSQL, the dedicated test schema, and mission isolation rules
5. 5Prefer direct canonical readback in assertions when the feature is about stopped-entry truth, 200 + null, or invalid-save no-mutation…
6. 6Keep transport smoke thin: only prove the exact API semantic that could drift.
7. 7Run the narrowest backend test packages during iteration, then rerun the broader backend command(s) affected by the feature.
8. 8If any required expectedBehavior bullet or requested regression path turns out to be
9. 9If the feature touches conflict behavior and the exact public rule is still ambiguous, prove consistency and return to orchestrator rather…
10. 10If the requested regression mentions a specific read/write surface such as continue, restart,
11. 11In the handoff, call out

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

Backend Test Worker loads about 1.3k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 421 words of instructions outside code blocks.

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

~27

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

~1.3k

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). 421 words, ~1,308 tokens.

name

backend-test-worker

description

Build and verify real-Postgres Go tests and thin transport smoke for tracking behavior.

{
  "salientSummary": "Added real-Postgres tracking lifecycle tests for stopped-entry create/edit/readback, invalid time rejection, and idle current-timer `200 + null` semantics. Also kept transport smoke thin by proving the current-timer body shape without moving business logic into handler tests.",
  "whatWasImplemented": "Expanded backend coverage for tracking time-entry lifecycle using the dedicated test schema on the shared external PostgreSQL service. The new tests prove canonical direct readback after create and edit, preserve prior state on invalid save attempts, and lock down the documented idle current-timer semantic with a thin HTTP smoke check.",
  "whatWasLeftUndone": "",
  "verification": {
    "commandsRun": [
      {
        "command": "go test ./apps/backend/internal/tracking/... -count=1 -parallel 4",
        "exitCode": 0,
        "observation": "Tracking application tests passed with the new lifecycle coverage."
      },
      {
        "command": "go test ./apps/backend/internal/bootstrap/... -count=1 -run 'TestPublicTrackTracking|TestRouteHandlers'",
        "exitCode": 0,
        "observation": "Thin transport smoke for current-timer semantics passed."
      }
    ],
    "interactiveChecks": [
      {
        "action": "Manually inspected one representative current-timer HTTP response after clearing running state.",
        "observed": "The endpoint returned HTTP 200 with literal null body and the direct read model remained idle."
      }
    ]
  },
  "tests": {
    "added": [
      {
        "file": "apps/backend/internal/tracking/application/update_time_entry_test.go",
        "cases": [
          {
            "name": "rejects invalid stop before start without mutating the persisted entry",
            "verifies": "VAL-ENTRY-003"
          },
          {
            "name": "materializes start plus duration without stop as a stopped entry",
            "verifies": "VAL-ENTRY-005"
          }
        ]
      }
    ]
  },
  "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/backend-test-worker of CorrectRoadH/OpenTickly.

Open the folder on GitHubat commit 5ffd0a0