Artifact Gate

Artifact Gate is a skill for Claude Code from GongShichen/LuminaCode. It costs 19 tokens per session (780 once invoked), scanned A, original, Apache-2.0.

A check that confirms each product-development stage has the required lasting documents before the team moves to the next approval stage.

In plain words
What is it for?
Use it to enforce document requirements at project stages and approval gates.
Why use it?
It prevents teams from advancing while decisions, requirements, or evidence are still missing.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to enforce document requirements at project stages and approval gates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gongshichen/luminacode/artifact-gate
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.

Any agent
npx skills add GongShichen/LuminaCode --skill artifact-gate
Clone the repo
git clone --depth 1 https://github.com/GongShichen/LuminaCode

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 Artifact Gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/gongshichen/luminacode/artifact-gate/github.svg)](https://agentmods.dev/skills/gongshichen/luminacode/artifact-gate)
Your own site
<a href="https://agentmods.dev/skills/gongshichen/luminacode/artifact-gate"><img src="https://agentmods.dev/badge/skills/gongshichen/luminacode/artifact-gate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Artifact Gate

Your own site · 80×15
<a href="https://agentmods.dev/skills/gongshichen/luminacode/artifact-gate"><img src="https://agentmods.dev/badge/skills/gongshichen/luminacode/artifact-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 780 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00019 $0.00780
Opus 5.5 $0.00008 $0.00312
Sonnet 5.5 $0.00004 $0.00156
Haiku 4.5 $0.00002 $0.00078

Measured 2mo ago against content hash a0055ae3a55b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Artifact Gate 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 2mo 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.

.Lumina/TEAM/product-development/team-leader/skills/artifact-gate/SKILL.md · 96 lines

What it actually says

Use this skill to prevent "the team talked about it" from replacing durable project artifacts.

Default document set for ordinary software product work:

  • PRD.md
  • UX_DESIGN.md
  • BACKEND_PLAN.md
  • FRONTEND_PLAN.md
  • INTERFACE_CONTRACT.md
  • INTEGRATION_REPORT.md
  • QA_REPORT.md
  • REVIEW_REPORT.md

Gate checks:

  1. Before UX Design

    • PRD.md exists and includes goals, scope, user flow, functional requirements, data requirements, and acceptance criteria.
  2. Before technical plans

    • PRD.md and UX_DESIGN.md exist.
    • Design includes states, interaction flow, copy, accessibility, and platform constraints.
  3. Before implementation

    • BACKEND_PLAN.md and FRONTEND_PLAN.md exist.
    • INTERFACE_CONTRACT.md exists and is acknowledged by both Frontend and Backend.
    • Team Leader has checked plan boundaries and called RecordTeamContract.
    • For CLI/TUI/local tools with persistence, INTERFACE_CONTRACT.md names one concrete storage path resolution and subprocess-visible test isolation mechanism. Reject vague language such as "environment variable or monkeypatch" because monkeypatch does not cross subprocess boundaries. Reject function parameter-only overrides unless the launched CLI/API exposes that parameter through a flag, environment variable, config path, fixture path, or cwd convention.
  4. Before QA/Reviewer

    • Implementation files exist under the project root.
    • INTEGRATION_REPORT.md exists or the Team Leader has explicitly dispatched integration evidence work.
  5. Before completion

    • QA_REPORT.md exists and QA has called SubmitGateVerdict.
    • REVIEW_REPORT.md exists and Reviewer has called SubmitGateVerdict.
    • Required commands and integration smokes in the Team Acceptance Contract have evidence.

If any document is missing:

  • Do not continue as if the stage is complete.
  • Dispatch a recovery task to the owner.
  • If the document is truly not applicable, record the reason in the Team Acceptance Contract or CompleteTeamTask.deferral_reasons.

Embedded helper:

If you want a mechanical check, create this temporary helper inside the project root or run it with python3 - <<'PY' ... PY. Do not rely on a separate file in the skill directory.

#!/usr/bin/env python3
"""Check required product-development stage documents under a project root."""

from __future__ import annotations

import pathlib
import sys


REQUIRED = [
    "PRD.md",
    "UX_DESIGN.md",
    "BACKEND_PLAN.md",
    "FRONTEND_PLAN.md",
    "INTERFACE_CONTRACT.md",
    "INTEGRATION_REPORT.md",
    "QA_REPORT.md",
    "REVIEW_REPORT.md",
]


def main(argv: list[str]) -> int:
    if len(argv) != 2:
        print("usage: check_stage_docs.py <project_root>", file=sys.stderr)
        return 2
    root = pathlib.Path(argv[1]).expanduser().resolve()
    missing = [name for name in REQUIRED if not (root / name).is_file()]
    if missing:
        print("missing stage documents:")
        for name in missing:
            print(f"- {name}")
        return 1
    print("all required stage documents exist")
    return 0


if __name__ == "__main__":
    raise SystemExit(main(sys.argv))
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. 2mo ago First seen · 96 lines · 19 tokens per session scan A a0055ae3a55b

Subscribe to this mod's changes

Artifact Gate is a skill published in the GitHub repository GongShichen/LuminaCode (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 19 tokens to every session and 780 once invoked, about $0.0001 per session on Opus 5.5. 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.