Make Tracking Issue

What it does

When your agent uses it

• The user asks to open
• Tighten a tracking issue
• Implementation issue
• Work plan in the Remix repository

Example prompts

• “/make-tracking-issue”

Workflow steps

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

1. 1Inspect the relevant code, package metadata, docs, and existing tests until the current state and affected boundaries are concrete.
2. 2Capture decisions already made by the user. Do not reopen them as alternatives or weaken them with speculative language.
3. 3Confirm the target repository from the git remote, search for duplicate issues, and inspect issue templates or labels when they may affect…
4. 4Draft the issue using the structure below, omitting sections that add no value.
5. 5Create or edit the issue with gh, then read it back to verify the title, body, state, and URL.

What it can do on your machine

Read from SKILL.md and the folder at commit 27bd7a4. 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

  Shell commands in SKILL.md call:

  • gh

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

• Network

  No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

  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

Make Tracking Issue loads about 1.3k tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 598 words of instructions outside code blocks.

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

~88

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 remix-run/remix at commit 27bd7a4, republished under its MIT licence (© remix-run). 598 words, ~1,290 tokens.

name

make-tracking-issue

description

Create or revise a GitHub tracking issue for a Remix change, including the target outcome, implementor context, a concise checkbox plan, compatibility concerns, and required gates. Use when the user asks to open, draft, rewrite, or tighten a tracking issue, implementation issue, umbrella issue, or work plan in the Remix repository.

- [ ] Move test-command parsing and help behavior into `@remix-run/cli`.
- [ ] Remove the standalone executable and migrate repository consumers.
- [ ] Update integration and packaging coverage for the new boundary.

- [ ] Add `multiple: true` to `ParseArgsStringOptionSpec` in `parse-args.ts`.
- [ ] Rename `loadConfig(argv, cwd)` to `loadResolvedConfig(options, cwd)`.

- Test-package tests, typecheck, and build pass.
- Package metadata validation passes.
- The packed package exposes the intended API and no removed executable.

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

Files

SKILL.md and 1 other file in .agents/skills/make-tracking-issue of remix-run/remix.

• SKILL.md
• agents/openai.yaml

Open the folder on GitHubat commit 27bd7a4