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.
npx agentmods add skills/data-wise/craft/dist-extrasnpx skills add Data-Wise/craft --skill dist-extrasgit clone --depth 1 https://github.com/Data-Wise/craftWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00112 | $0.03926 |
| Opus 5 | $0.00056 | $0.01963 |
| Sonnet 5 | $0.00022 | $0.00785 |
| Haiku 4.5 | $0.00011 | $0.00393 |
Grade A, and why
dist-extras 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: This skill should be used when the user asks to "publish to PyPI", "generate an install script", "curl install", "publish to Claude Code marketplace", "create marketplace.json", "PyPI trusted publishing", "p How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distribution Extras (PyPI / curl / Marketplace)
Channel-specific expertise for distribution paths that aren't covered by the
Homebrew skills (homebrew-formula-expert, homebrew-multi-formula,
homebrew-setup-wizard, homebrew-workflow-expert). Three distinct channels
are grouped here because each one alone is too small to warrant its own
top-level skill, and they share a common pattern: declarative manifest +
GitHub Actions workflow + pre-flight validation.
Use distribution-strategist first to pick a channel. Use this skill once a
channel is chosen and you need execution detail.
Full walkthroughs (dry-run examples, workflow YAML templates, check tables) — extracted
from the former standalone commands during the v4 consolidation (Phase 3.5, 2026-07-12):
references/pypi.md, references/curl-install.md, references/marketplace.md.
When to use which channel
| Channel | Best for | Avoid when |
|---|---|---|
| PyPI | Python libraries and CLIs; ecosystem-native pip install |
Non-Python; binary-heavy distribution |
| curl install | Single-file CLIs with GitHub releases; quick-start docs | Security-sensitive envs (pipe-to-bash) |
| Marketplace | Claude Code plugins (.claude-plugin/plugin.json present) |
Anything that isn't a Claude Code plugin |
PyPI publishing
Channel concern: build sdist+wheel, publish to PyPI, automate via GitHub Actions, validate package metadata before release.
Subcommands (mirrors /craft:dist:pypi)
| Subcommand | Purpose |
|---|---|
validate |
Check pyproject.toml, classifiers, README rendering, version sanity |
setup |
Generate release workflow + walk user through trusted-publishing setup |
workflow |
Generate .github/workflows/pypi-release.yml (release-triggered) |
publish |
Build with uv build (or python -m build) and twine upload |
check |
Pre-flight: clean tree, version bumped, tag matches, CHANGELOG entry |
Trusted publishing (preferred over API tokens)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 381 lines · 112 tokens per session scan A 610da849014e
dist-extras is a skill published in the GitHub repository Data-Wise/craft (4 stars, last pushed 16d ago), licensed MIT. It adds 112 tokens to every session and 3,926 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
github-actions-workflow
Scaffolds or audits a GitHub Actions CI/CD workflow for a project. Covers job structure, caching, secrets handling, concurrency groups, environment gates, and reusable workflows via workflowcall. Invoked when the user asks to set up CI, add a GitHub Actions workflow, improve pipeline performance, or share workflow…
specflow
Spec-driven development with executable contracts.
specflow-loop-selector
Selects the correct Specflow loop and forces a concrete run contract before work starts. Use when an agent is asked to start Specflow work, build a ticket, create/refine a PRD, investigate an existing product, run Gate D, choose between spec-build and feature-build, or "go find out about" Specflow loops. Compatible…
specflow-simulate
Simulates end-to-end usage of a Specflow story across multiple personas and divergent routes to discover gaps, edge cases, and unhandled branches BEFORE the story is built — then proposes each finding as a concrete story addition (new REQ, negative-path AC, Gherkin branch, or journey step). This is the high-value…
specflow-audit
Audits a Specflow story/ticket for spec-compliance and surgically uplifts it — adding only the missing executable contract sections (SQL/RLS, TypeScript interfaces, invariant codes, Gherkin, acceptance criteria, Definition of Done, data-testid coverage) — then runs a pre-flight gate that refuses to mark the ticket…
architecture-review
Conducts a comprehensive multi-perspective architecture review using ALL architecture team members. Use when the user requests "Start architecture review", "Full architecture review", "Review architecture for version X.Y.Z", "Conduct comprehensive review", or when they want assessment from multiple perspectives. Do…