Borrowing it
Nothing to install: this file belongs to bex-co/bex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bex-co/bex/main/.claude/skills/mermaid/SKILL.mdgit clone --depth 1 https://github.com/bex-co/bexWrote 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/bex-co/bex/mermaid)<a href="https://agentmods.dev/skills/bex-co/bex/mermaid"><img src="https://agentmods.dev/badge/skills/bex-co/bex/mermaid/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/bex-co/bex/mermaid"><img src="https://agentmods.dev/badge/skills/bex-co/bex/mermaid.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.00757 |
| Opus 5.5 | $0.00015 | $0.00303 |
| Sonnet 5.5 | $0.00007 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
mermaid 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 27d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draw a mermaid architecture diagram in markdown for: $ARGUMENTS
Conventions
- Boxes are services/components:
svc[bex-api]. Use[(...)]for datastores. Humans (user, developer, operator) are triangles:user@{ shape: tri, label: "user" }. - A box that is not a long-running service must say so in its label — readers assume boxes are services and ask "where is this running?". Mark scheduled/ephemeral work (
cron["backup pod (spawned nightly, exits when done)"]) and inert config objects (secret["Secret foo (k8s object, created once)"]). Draw humans as triangles:operator@{ shape: tri, label: "operator" }. Never draw a manual procedure as a peer box of running infrastructure: give runbook/recovery flows their own subgraph whose title says it's manual and where it runs (subgraph "disaster recovery — manual runbook, any docker host"), with the human actor inside. - Arrows are dependency direction:
A --> Bmeans A depends on (calls, reads, deploys to) B — never the reverse. - Concise but to the point: only load-bearing services and edges. No styling, no colors, no legend. Label an edge (
A -->|gRPC| B) only when the relationship isn't obvious. Default toflowchart TB; useLRonly if the graph is much wider than deep. Usesubgraphonly for real boundaries (cluster, node, network, trust zone, automated vs. manual) — subgraphs are how the diagram answers "where does this run?". An edge may target a whole subgraph by id (subgraph cluster["app cluster"]…op --> cluster). - If $ARGUMENTS refers to this repo, read the relevant docs/code first (
docs/ADR002-architecture.mdis the map) — don't diagram from guesswork.
Syntax gotchas that break rendering: quote labels containing (, ), [, {, or -->-like text (a["Queue (SQS)"]); never name a node bare end or graph; subgraph titles with spaces need quotes.
Verify (mandatory, before answering)
- Write the diagram body (no
```mermaidfence) to a.mmdfile in the scratchpad (e.g./tmp/diagram.mmdor the current workspace). - Run:
npx -y @mermaid-js/[email protected] -i <file>.mmd -o <file>.svg— exit 0 means the syntax is valid. (First run downloads a headless browser; that's expected.) The version is pinned deliberately (supply-chain: codex-security #17) — bump it consciously, don't revert to floating. - On failure, read the parse error, fix the diagram, and re-verify. Never output a diagram that hasn't passed.
What ships with it
1 file 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.
- 27d ago Changed 52701b18e256
- 1mo ago First seen · 31 lines · 37 tokens per session scan A 0b9840acc9c8
mermaid is a skill published in the GitHub repository bex-co/bex (574 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 757 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
network-rca
Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect…
kfl
KFL2 (Kubeshark Filter Language) reference. This skill MUST be loaded before writing, constructing, or suggesting any KFL filter expression. KFL is statically typed — incorrect field names or syntax will fail silently or error. Do not guess at KFL syntax without this skill loaded. Trigger on any mention of KFL, CEL…
security-audit
Kubernetes network security audit skill powered by Kubeshark MCP. Use this skill whenever the user wants to audit a cluster for security threats, detect compromised workloads, find malicious traffic patterns, hunt for indicators of compromise (IOCs), check for data exfiltration, identify C2 (command and control)…
install
Kubeshark installation and deployment skill. Use this skill whenever the user wants to install Kubeshark, deploy Kubeshark to a Kubernetes cluster, set up Kubeshark, configure Kubeshark helm values, generate a Kubeshark config file, customize Kubeshark deployment, troubleshoot Kubeshark installation, upgrade…
maroto-pdf
Generate PDFs from Go code with the maroto v2 library — install, program skeleton, page config, grid layout, components (text, image, barcode, QR code, signature), tables and testing. Use when writing or extending Go code that builds a PDF (invoices, reports, certificates) with github.com/johnfercher/maroto.
octo-drive
Octo Drive — spaces, folders, file upload/download, online-document mounts, share links, invites, IM-attachment transfer. Works with a bot token or a user API key; the CLI routes by token kind. Load after octo-shared.