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 antoinebou12/uml-mcp --skill archify_sequencegit clone --depth 1 https://github.com/antoinebou12/uml-mcpWrote 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/antoinebou12/uml-mcp/archify_sequence)<a href="https://agentmods.dev/skills/antoinebou12/uml-mcp/archify_sequence"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/archify_sequence/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/antoinebou12/uml-mcp/archify_sequence"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/archify_sequence.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 | $0.00703 |
| Opus 5.5 | $0.00029 | $0.00281 |
| Sonnet 5.5 | $0.00014 | $0.00141 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
archify_sequence 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 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.
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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
archify_sequence diagram (uml-mcp plugin archify)
diagram_type: archify_sequence
Backend: plugin:archify (bundled with uml-mcp, on by default)
Output formats: html, svg
Sequence diagram: participants across the top, lifelines and ordered call and reply messages; dark, light or auto. JSON participants and messages; html or svg
Load the workflow skill uml-mcp-diagrams and the focused guide skill://uml-mcp-guides/archify/SKILL.md. This file is notation only; it does not add an MCP tool.
Example prompt
Sequence diagram of a cache-miss request through web, API, auth, Redis and Postgres.
Notation tips
participants(id,name,role,icon,tone) and orderedmessages(from,to,label,style,note).style: "dashed"marks a reply; a message to the same participant draws a loop;autonumber: truenumbers them.
Styling
Pass theme (auto, dark or light) to generate_uml / generate_uml_image, or set it in the source. auto follows the reader's system in the HTML page and is dark in static SVG and PNG.
Example source
{"title":"Cache miss request sequence","subtitle":"A dashboard request that misses the cache and falls through to Postgres","theme":"auto","preset":"classic","participants":[{"id":"web","name":"Web App","role":"React UI","icon":"browser","tone":"blue"},{"id":"api","name":"API","role":"request handler","icon":"api","tone":"green"},{"id":"auth","name":"Auth","role":"JWT verify","icon":"shield","tone":"red"},{"id":"cache","name":"Redis","role":"cache","icon":"cache","tone":"orange"},{"id":"db","name":"Postgres","role":"source of truth","icon":"database","tone":"purple"}],"messages":[{"from":"web","to":"api","label":"GET /dashboard"},{"from":"api","to":"auth","label":"verify JWT"},{"from":"auth","to":"api","label":"claims ok","style":"dashed"},{"from":"api","to":"cache","label":"read cache"},{"from":"cache","to":"api","label":"miss","style":"dashed"},{"from":"api","to":"db","label":"SELECT widgets","note":"indexed by account"},{"from":"db","to":"api","label":"rows","style":"dashed"},{"from":"api","to":"cache","label":"set cache","tone":"orange"},{"from":"api","to":"api","label":"emit trace"},{"from":"api","to":"web","label":"200 OK","style":"dashed"}]}
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 · 35 lines · 72 tokens per session scan A 3f2d126b2607
archify_sequence is a skill published in the GitHub repository antoinebou12/uml-mcp (109 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 703 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 2026-11-05.
archify_sequence compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| archify_sequenceantoinebou12/uml-mcp | Skill | 109 | yesterday | MIT | A | 72 | Claude Code, Codex |
| html-ppt-zhangzara-block-framenexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 51 | Claude Code, Codex |
| accesslint-scansickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 32 | Claude Code |
| checktw93/Waza | Skill | 7.5k | 5d ago | MIT | A | 41 | Claude Code |
| healthtw93/Waza | Skill | 7.5k | 5d ago | MIT | A | 40 | Claude Code |
| hunttw93/Waza | Skill | 7.5k | 5d ago | MIT | A | 33 | Claude Code |
| thinktw93/Waza | Skill | 7.5k | 5d ago | MIT | A | 39 | Claude Code |