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 cosmix/loom --skill loom-diagramminggit clone --depth 1 https://github.com/cosmix/loomWrote 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/cosmix/loom/loom-diagramming)<a href="https://agentmods.dev/skills/cosmix/loom/loom-diagramming"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-diagramming/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/cosmix/loom/loom-diagramming"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-diagramming.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 | $0.00026 | $0.02175 |
| Opus 5 | $0.00013 | $0.01087 |
| Sonnet 5 | $0.00005 | $0.00435 |
| Haiku 4.5 | $0.00003 | $0.00217 |
Grade A, and why
loom-diagramming scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Quote labels with special characters.** Parentheses `()`, `{}`, `[]`, `#`, `:`, `;`, and quotes inside a label break parsing — wrap the text: `A["fetch(url)"]`, `B["step: parse"]`. For literal special chars inside a How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagramming
Overview
Create maintainable technical diagrams in Mermaid (renders in GitHub, GitLab, and most doc tools). Diagrams live in version control next to code — they must stay in sync or they mislead. This skill covers type selection, syntax, and the parsing footguns that waste the most time.
Choose the diagram type
| Type | Use when | Not when |
|---|---|---|
| Sequence | Interactions over time across participants | Showing static structure |
| Flowchart | Decision logic, process/pipeline steps | Timing between services (use sequence) |
| State | An entity's lifecycle + transitions/guards | Data flow or call order |
| ERD | Data model, tables, cardinality | Runtime behavior |
| Class | OO structure, interfaces, inheritance | Deployment or infra |
| C4 (Context) | System boundary + external actors/systems | Internal code detail |
| C4 (Container) | Deployable units + their tech + data stores | Class-level detail |
Rule of thumb: structure → flowchart/C4/class/ERD; behavior over time → sequence; lifecycle → state. For architecture, prefer C4's layered zoom (Context → Container → Component) over one sprawling diagram.
Gotchas (Mermaid parsing footguns)
These cause silent render failures or garbled output far more often than logic errors.
endis reserved in flowcharts. A lowercase node idendbreaks the parser. UseEnd,END, or quote it:id["end"]. Same care withsubgraph/click/classas bare ids.- Quote labels with special characters. Parentheses
(),{},[],#,:,;, and quotes inside a label break parsing — wrap the text:A["fetch(url)"],B["step: parse"]. For literal special chars inside a quoted label, use HTML entities:#quot;won't work — use",&,#(for#). - Line breaks:
<br/>inside a label, not\n:A["Line one<br/>Line two"]. - Edge labels with special chars must be quoted:
A -->|"retry (max 3)"| B. - Leading
o/xon an edge become arrowheads.A---oBrenders a circle end,A---xBa cross. Add a space (A --- oBis still risky) or rename the node so an edge doesn't touch a bareo/x. - Subgraph direction: set
direction LRinside the subgraph; note that edges crossing subgraph boundaries can override a subgraph's internal direction. - Comments are
%%on their own line. Semicolons are optional line terminators. - C4 diagrams (
C4Context/C4Container) have limited, sometimes experimental layout control and lag other Mermaid features — verify they render in your target tool before committing to them; a plainflowchartwith subgraphs is a robust fallback. - Don't build the giant diagram. Past ~15-20 nodes it's unreadable and un-reviewable. Split by concern or zoom level. One diagram, one idea.
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.
- 6d ago Changed · -20 tokens per session fe0ea6677d51
- 9d ago First seen · 232 lines · 46 tokens per session scan A c9a2663cb7d0
loom-diagramming is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 2,175 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
eval-graphics
Turn an eval study's numbers into on-brand, publish-ready figures using the Newsjack chart room (the eval design system), then validate them with Playwright. For producing the charts in a published eval/data study.
drawio-logical-diagrams
Creates professional logical flow diagrams and logical system architecture diagrams using draw.io XML format (.drawio files). Use when creating: (1) logical flow diagrams showing data/process flow between system components, (2) logical architecture diagrams representing system structure without cloud provider…
aws-drawio-architecture-diagrams
Creates professional AWS architecture diagrams in draw.io XML format (.drawio files) using official AWS Architecture Icons (aws4 library). Use when the user asks for AWS diagrams, VPC layouts, multi-tier architectures, serverless designs, network topology, or draw.io exports involving Lambda, EC2, RDS, or other AWS…
aksel-builder
Expert builder for Aksel, the Nav / @navikt design system — React components, design tokens, layout primitives, theming (light/dark), icons, CSS, the Tailwind preset, version migrations, Figma-to-code. Triggers — Aksel, "using/with aksel", Nav/Navikt, "designsystemet", "design system", @navikt/ds- (e.g.…
aksel-spacing
Lag responsive layouts med Aksel Design System (v8+) - spacing tokens, layout primitives (Box, HStack, VStack, HGrid, Page, Bleed) og ResponsiveProp.
web-design-reviewer
Visuell inspeksjon av nettsider for å identifisere og fikse designproblemer. Trigges av forespørsler som "sjekk designet", "gå gjennom UI-en", "fiks layouten", "finn designfeil". Finner problemer med responsivt design, tilgjengelighet, visuell konsistens og layout, og fikser dem i kildekoden.