Whats New Catalog

What it does

When your agent uses it

• Bumping the extension version
• Cutting a release
• After adding a new view/tab/section
• The Whats New view looks stale

Example prompts

• “Unreleased”
• “Take me there”
• “t announce what they already found”
• “/whats-new-catalog”

Workflow steps

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

1. 1Run the detector.
2. 2Exit 1 → fix it in catalog.ts directly. These are unambiguous
3. 3Exit 3 → write the entry (see the next section), then re-run.
4. 4Read the "beyond the cap" markers. If something important is below the
5. 5Re-run until clean, then run the unit tests

What it can do on your machine

Read from SKILL.md and the folder at commit 7b4f317. 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:

  • node
  • npm

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

• Network

  No URLs in SKILL.md. Its commands use npm, 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

Whats New Catalog loads about 2k tokens when it runs. Until then it costs about 193 tokens; SKILL.md has 977 words of instructions outside code blocks.

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

~193

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

~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 rajbos/ai-engineering-fluency at commit 7b4f317, republished under its MIT licence (© rajbos). 977 words, ~1,990 tokens.

name

whats-new-catalog

description

Keep the What's New release catalog (vscode-extension/src/whatsNew/catalog.ts) in step with what the extension actually ships. Detects a released version with no catalog entry, an entry left marked "Unreleased" after it shipped, a feature pointing at a view or tab that no longer exists (a "Take me there" button that goes nowhere), and a catalogued tab on a view that never reports being opened — which silently breaks the "don't announce what they already found" rule. Also prints the surface inventory and the CHANGELOG's Unreleased bullets side by side, the two things you read when writing a new entry. Use when bumping the extension version or cutting a release, after adding a new view/tab/section, or when the What's New view looks stale or wrong.

node .github/skills/whats-new-catalog/whats-new-catalog.js          # human-readable
node .github/skills/whats-new-catalog/whats-new-catalog.js --json   # machine-readable

{
  version: '0.18.0',
  date: null,          // a date once it ships; see "At release time" below
  headline: 'One sentence for someone who skipped the details.',
  features: [ /* most important first — the cap truncates */ ],
},

© rajbos, MIT. 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 .claude/skills/whats-new-catalog of rajbos/ai-engineering-fluency.

Open the folder on GitHubat commit 7b4f317