Tracking Backend Worker

What it does

When your agent uses it

• Tasks that involve Time tracking and reporting

Example prompts

• “/tracking-backend-worker”

Workflow steps

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

1. 1Read mission mission.md, mission AGENTS.md, .factory/services.yaml, .factory/library/architecture.md, and…
2. 2Copy the feature's expectedBehavior bullets into a local checklist before editing anything.
3. 3Read only the source docs from the closed set in mission AGENTS.md that actually govern this feature. Do not use unlisted docs.
4. 4Write failing backend tests first at the narrowest effective layer
5. 5Keep backend validation bound to the dedicated opentoggl_test schema. Never point tests at the business schema.
6. 6Implement the backend change only after the new tests fail for the right reason.
7. 7If the feature changes a product rule already described in docs/product/tracking.md, update that doc in the same feature and refresh its…
8. 8Update the status blocks for every directly used source doc you relied on for the feature. Keep exactly one active mission block per…
9. 9Run the narrowest backend test commands during iteration, then rerun the broader backend command(s) touched by the feature.
10. 10Before ending the feature, verify that the handoff commit itself contains the claimed work. Compare the handoff commit diff/stat to the…
11. 11If the feature changes browser-visible behavior indirectly, include one precise manual/API verification step proving the backend truth the…
12. 12In the handoff, explicitly state

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

Tracking Backend Worker loads about 1.2k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 369 words of instructions outside code blocks.

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

~32

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). 369 words, ~1,218 tokens.

name

tracking-backend-worker

description

Update backend timer/time-entry contracts, regressions, and source docs for the timer refactor mission.

{
  "salientSummary": "Updated the tracking contract and backend regressions so running-timer uniqueness is global per user, not per workspace. Added cross-workspace conflict coverage plus a thin current-timer transport proof, and refreshed the tracking PRD status block to reflect the new rule.",
  "whatWasImplemented": "Changed the backend tracking rule so a second running timer cannot be created in another workspace for the same user, kept `GET /me/time_entries/current` as the user-global source of truth, added failing-first Go regressions for the conflict/readback paths, and updated `docs/product/tracking.md` with the new rule plus a canonical mission status block.",
  "whatWasLeftUndone": "",
  "verification": {
    "commandsRun": [
      {
        "command": "go test ./apps/backend/internal/tracking/... -count=1 -parallel 4",
        "exitCode": 0,
        "observation": "Tracking regressions passed with the new global conflict coverage."
      },
      {
        "command": "go test ./apps/backend/internal/bootstrap/... -count=1 -parallel 4",
        "exitCode": 0,
        "observation": "Current-timer transport semantics passed, including idle `200 + null`."
      }
    ],
    "interactiveChecks": [
      {
        "action": "Replayed a two-workspace start conflict against the reused backend and read `/me/time_entries/current` afterward.",
        "observed": "The second start was rejected, no second running row was persisted, and the original running entry stayed current."
      }
    ]
  },
  "tests": {
    "added": [
      {
        "file": "apps/backend/internal/tracking/application/regressions_test.go",
        "cases": [
          {
            "name": "rejects a second running timer across workspaces for the same user",
            "verifies": "VAL-TIMER-001"
          }
        ]
      },
      {
        "file": "apps/backend/internal/bootstrap/...",
        "cases": [
          {
            "name": "returns 200 null when current timer is idle",
            "verifies": "VAL-TIMER-003"
          }
        ]
      }
    ]
  },
  "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/tracking-backend-worker of CorrectRoadH/OpenTickly.

Open the folder on GitHubat commit 5ffd0a0