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 Rheinmir/setup --skill dym-archify-repository-evidencegit clone --depth 1 https://github.com/Rheinmir/setupWrote 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/rheinmir/setup/dym-archify-repository-evidence)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-archify-repository-evidence"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-archify-repository-evidence/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/rheinmir/setup/dym-archify-repository-evidence"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-archify-repository-evidence.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 | $0.00072 | $0.01499 |
| Opus 5.5 | $0.00029 | $0.00600 |
| Sonnet 5.5 | $0.00014 | $0.00300 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
dym-archify-repository-evidence 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-archify-repository-evidence — Sơ đồ architecture gắn bằng chứng mã nguồn thật
Vì sao dùng: khi sơ đồ kiến trúc phải chứng minh được nó phản ánh mã thật, không phải trí nhớ của ai đó. Node có bằng chứng tự đánh dấu SRC n trong viewer và mở đúng file + khoảng dòng, ghim vào một commit công khai.
Kết quả nhận được: một HTML architecture trong đó các thành phần dẫn ngược về file/dòng thật, và một cổng fail-closed từ chối render nếu bằng chứng không kiểm chứng được.
Chỉ dành cho architecture. workflow, sequence, dataflow, lifecycle từ chối --repo-root với rc 2.
export A=~/.claude/skills/archify
Ba thứ phải khớp cùng lúc
Đọc từ renderers/shared/repository-evidence.mjs (hàm verifyRepositoryEvidence, dòng 87+):
meta.repository.url— phải là URL GitHub công khai dạnghttps://github.com/owner/repo. URL khác host hoặc khác dạng →repository-evidence/url-invalid.meta.repository.revision— phải là SHA commit đủ 40 ký tự. Rút gọn 7 ký tự bị từ chối:repository-evidence/revision-invalid.--repo-root <path>— phải trỏ vào thư mục top-level của Git checkout, vàorigincủa nó phải khớpmeta.repository.url. Không phải top-level →repository-evidence/root-not-top-level(kèm đúng đường dẫn nên dùng). Origin lệch →repository-evidence/origin-mismatch.
Cấu trúc sources[] trên mỗi component, lấy từ schemas/architecture.schema.json: mảng 1–3 phần tử, mỗi phần tử bắt buộc path (≤240 ký tự), tuỳ chọn line, end_line (số nguyên ≥1), label (≤48 ký tự).
Spec tối thiểu đã chạy xanh thật
Ví dụ này tôi đã soạn và chạy trọn vòng trên chính repo archify:
REV=$(git -C /path/to/archify rev-parse HEAD) # phải là SHA 40 ký tự
cat > evidence.architecture.json <<JSON
{
"schema_version": 1,
"diagram_type": "architecture",
"meta": {
"title": "Archify CLI — evidence probe",
"quality_profile": "showcase",
"repository": {
"url": "https://github.com/tt-a1i/archify",
"revision": "$REV"
}
},
"layout": { "mode": "grid" },
"components": [
{
"id": "cli", "type": "backend", "label": "archify CLI", "row": 0, "col": 0,
"sources": [
{ "path": "archify/bin/archify.mjs", "line": 1, "end_line": 40, "label": "entry" }
]
},
{
"id": "renderer", "type": "backend", "label": "Renderer", "row": 0, "col": 1,
"sources": [
{ "path": "archify/renderers/architecture/render-architecture.mjs", "line": 1, "end_line": 30 }
]
}
],
"connections": [
{ "from": "cli", "to": "renderer", "label": "spawns" }
]
}
JSON
node $A/bin/archify.mjs validate architecture evidence.architecture.json \
--quality showcase --repo-root /path/to/archify
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.
- yesterday First seen · 121 lines · 72 tokens per session scan A ce71472b59a4
dym-archify-repository-evidence is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 72 tokens to every session and 1,499 once invoked, about $0.0003 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 2026-11-07.
dym-archify-repository-evidence compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-archify-repository-evidenceRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 72 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.5k | today | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 2d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 947 | 3d ago | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | yesterday | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | today | MIT | A | 70 | Claude Code |