publish

publish is a skill for Claude Code from aidlc-io/aidlc. It costs 45 tokens per session (1,637 once invoked), scanned A, original, MIT.

A release command for a Visual Studio Code extension. It changes the version, updates the changelog, builds the VSIX package, publishes it to two extension marketplaces, then commits and tags the release.

In plain words
What is it for?
Use it to publish a patch, minor, or major extension release after checking the branch, working tree, and marketplace credentials.
Why use it?
It puts the required release checks and publishing steps into one repeatable workflow and stops if a prerequisite or step fails.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is CRITICAL: do NOT just `tsc` and `vsce package` separately. The TS output is unbundled — it `require()`s `@aidlc/core` and `js-yaml`, which aren't shipped with `.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/aidlc-io/aidlc/publish.svg)](https://agentmods.dev/skills/aidlc-io/aidlc/publish)
Your own site
<a href="https://agentmods.dev/skills/aidlc-io/aidlc/publish"><img src="https://agentmods.dev/badge/skills/aidlc-io/aidlc/publish.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,637 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.01637
Opus 5 $0.00023 $0.00818
Sonnet 5 $0.00009 $0.00327
Haiku 4.5 $0.00005 $0.00164

Measured 6d ago against content hash 422709f411fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

publish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/publish/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/publish — release this extension to Open VSX + VS Code Marketplace

End-to-end release flow for this VSCode extension. Every step is mandatory; stop and report if any step fails — do NOT continue past a failure.

0. Parse args

  • Argument may be patch, minor, or major. Default: patch.
  • Reject anything else with a short error.

1. Preflight

Run these checks in parallel and abort on any failure:

  • git rev-parse --abbrev-ref HEAD — must be main.
  • git status --porcelain — must be empty (clean working tree). If dirty, stop and list the dirty files; do not stash.
  • test -n "$OVSX_PAT" (via printenv OVSX_PAT | head -c 4) — must be non-empty. If missing, stop with:

    OVSX_PAT not set. Create a token at https://open-vsx.org/user-settings/tokens then export OVSX_PAT=<token> and retry.

  • test -n "$VSCE_PAT" (via printenv VSCE_PAT | head -c 4) — must be non-empty. If missing, stop with:

    VSCE_PAT not set. Create an Azure DevOps PAT (scope: Marketplace → Manage, org: All accessible) at https://dev.azure.com → User settings → Personal access tokens, then export VSCE_PAT=<token> and retry.

  • Read current version from packages/extension/package.json. The repo-root package.json has no version — it's the monorepo manifest.

2. Compute new version

Semver bump based on arg:

  • patch: x.y.zx.y.(z+1)
  • minor: x.y.zx.(y+1).0
  • major: x.y.z(x+1).0.0

State the old → new version in one line before proceeding.

3. Collect release notes

Get commits since the last tag:

LAST_TAG=$(git describe --tags --abbrev=0 2>/dev/null || echo "")
if [ -n "$LAST_TAG" ]; then
  git log "$LAST_TAG"..HEAD --pretty=format:'- %s'
else
  git log --pretty=format:'- %s'
fi

Filter the output:

  • Drop Merge ..., Bump version ..., Release v..., and any line matching the auto-generated commit from step 7.
  • Keep the rest verbatim as bullet points.

If the list is empty, stop and report: "No commits since $LAST_TAG — nothing to release."

Read the full file on GitHub · 145 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 145 lines · 45 tokens per session scan A 422709f411fe

Subscribe to this mod's changes

publish is a skill published in the GitHub repository aidlc-io/aidlc (58 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,637 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.