agentmods.dev

release-extensions

Release instructions for publishing five related @docs.plus extension packages to npm, the package registry used by JavaScript projects. They define versioning, package metadata, pre-release checks, publishing, and changelog rules.

In plain words
What is it for?
Use them when publishing the extension packages, changing their versions, preparing a release, or writing their changelogs.
Why use it?
They reduce mistakes when releasing a coordinated group of packages with shared technical and documentation requirements.

Skill for Claude CodeCodex

88 4d ago A scan 64 tokens original MIT
View the source file docs-plus/docs.plus
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/docs-plus/docs.plus/release-extensions
Any agent
npx skills add docs-plus/docs.plus --skill release-extensions
Clone the repo
git clone --depth 1 https://github.com/docs-plus/docs.plus

Made for: Claude Code, Codex.

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00064 $0.01842
Opus 5 $0.00032 $0.00921
Sonnet 5 $0.00013 $0.00368
Haiku 4.5 $0.00006 $0.00184

Measured 2d ago against content hash 38d1fb685ea0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release-extensions scanned grade A with 1 finding 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 2d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Use `spawnSync` helper calls, no shell strings, so the OTP stays off the shell command line and out of shell history. The spawned `bun publish` still carries it in its own argv, so `ps` can read it for the life of that
.agents/skills/release-extensions/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Releasing the @docs.plus/extension-* family

RELEASE_POLICY.md at the repo root is authoritative for versioning doctrine. Moved verbatim out of the repo-root AGENTS.md.

Publishing And Releases

Extension Package Contract

  • Publish workspace extensions under the org-owned @docs.plus scope.
  • exports.require.types must point to ./dist/index.d.cts, not .d.ts.
  • sideEffects must include CSS, e.g. ['**/*.css']; do not use bare false.
  • Every scoped package needs publishConfig.access: "public" or bun publish defaults to private and can 402.
  • Package metadata should include homepage, bugs, and discovery-oriented keywords.
  • Public-facing docs follow the family install policy and stay cohesive. Every extensions/extension-*/README.md and CHANGELOG.md uses Bun commands (bun add / bun remove), never npm/yarn/pnpm — even though external consumers could use npm. Install blocks show the plain bun add <pkg> line only. Add no @next soak lines, and never lead an Install block with npm install <pkg>. This mirrors extensions/README.md. Keep the five READMEs at structural parity: shared Install/Contributing/Family boilerplate, and a framework-neutral new Editor Quickstart from @tiptap/core, not React useEditor. Use no per-package marketing taglines, and no chrome in any prose (use "UI"/"shell"/"toolbar", same as the §Code Quality vocabulary rule).
  • Extension publish audits expect all five packages at parity. Parity covers: package-local CONTRIBUTING.md, bunx release lifecycle hooks, README gallery assets via docs:screenshots, CI extension tests, and harness docs centralized in extensions/README.md. The gallery holds a hero plus <details>/<picture> scenes. Use no JS carousels. GitHub/npm READMEs are static HTML only. The cutover and e2e READMEs link to extensions/README.md, and do not duplicate its ports or scripts. Preview collapsible README galleries on GitHub or bunx grip <readme> — VS Code's default Markdown preview often won't render <details>/<picture>.
  • Adding any root re-export through src/index.ts or src/utils/index.ts is a minor release, not a patch.
  • Resolve [Unreleased] to a real version before bun run build, bun pm pack, and bun publish.
  • prepublishOnly runs release-preflight; it asserts:
    • publisher user-agent is bun/*;
    • every dist/... path in the consumer's exports map exists on disk;
    • no literal catalog: leaks into built bundles.

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 64 tokens per session scan A 38d1fb685ea0

Subscribe to this mod's changes

release-extensions is a skill published in the GitHub repository docs-plus/docs.plus (88 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 1,842 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

CollaborationDocumentsGit and workflowWriting and docscollaborative-frameworkcollaborative-researchcollaborative-writingdocumentdocx
Related

Other skills, from other repositories

docx

Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.

zhixuli0406/DuDuClaw · 34 tokens

document-converter

Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown. Provides the agent with conversion strategies for academic and research workflows.

wentorai/Research-Claw · 50 tokens

docx-manipulation

Create, edit, and manipulate Word documents programmatically using python-docx.

claude-office-skills/skills · 20 tokens

add-format

End-to-end checklist for adding a new input or output format to AILANG Parse (docparse). Use when the user says 'add support for X format', 'wire up a new parser', 'add .foo format', 'add a parser for .bar', 'support .baz files', 'ship format X', 'can we parse .qux', 'new format rollout', or mentions a file extension…

sunholo-data/ailang-parse · 183 tokens

landing-page

Create a new AILANG Parse documentation/landing page targeting a specific keyword or topic. Use when user says 'new landing page', 'new page for X', 'create a page about X', 'landing page for keyword X', or wants to add a documentation page to the docs/ site. Also use when the user references long-tail keywords, SEO…

sunholo-data/ailang-parse · 81 tokens

benchmark

Run OfficeDocBench evaluation and refresh benchmark scores across the AILANG Parse website. Use when the user says 'run benchmarks', 'rerun the benchmark', 'refresh benchmark numbers', 'update bench scores', 'regenerate summary.json', mentions OfficeDocBench, asks to evaluate parsers, asks why scores are out of sync…

sunholo-data/ailang-parse · 115 tokens