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 skills add GongShichen/LuminaCode --skill artifact-gategit clone --depth 1 https://github.com/GongShichen/LuminaCodeWrote 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.
[](https://agentmods.dev/skills/gongshichen/luminacode/artifact-gate)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.mdUX_DESIGN.mdBACKEND_PLAN.mdFRONTEND_PLAN.mdINTERFACE_CONTRACT.mdINTEGRATION_REPORT.mdQA_REPORT.mdREVIEW_REPORT.md
Gate checks:
-
Before UX Design
PRD.mdexists and includes goals, scope, user flow, functional requirements, data requirements, and acceptance criteria.
-
Before technical plans
PRD.mdandUX_DESIGN.mdexist.- Design includes states, interaction flow, copy, accessibility, and platform constraints.
-
Before implementation
BACKEND_PLAN.mdandFRONTEND_PLAN.mdexist.INTERFACE_CONTRACT.mdexists 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.mdnames 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.
-
Before QA/Reviewer
- Implementation files exist under the project root.
INTEGRATION_REPORT.mdexists or the Team Leader has explicitly dispatched integration evidence work.
-
Before completion
QA_REPORT.mdexists and QA has calledSubmitGateVerdict.REVIEW_REPORT.mdexists and Reviewer has calledSubmitGateVerdict.- 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))
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.
- 2mo ago First seen · 96 lines · 19 tokens per session scan A a0055ae3a55b
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.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.