Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MattArtzAnthro/gephi-ai/plugin install gephi-network-analysisWrote 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/agents/mattartzanthro/gephi-ai/layout-iterator)<a href="https://agentmods.dev/agents/mattartzanthro/gephi-ai/layout-iterator"><img src="https://agentmods.dev/badge/agents/mattartzanthro/gephi-ai/layout-iterator/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/agents/mattartzanthro/gephi-ai/layout-iterator"><img src="https://agentmods.dev/badge/agents/mattartzanthro/gephi-ai/layout-iterator.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 | $0.00092 | $0.01804 |
| Opus 5.5 | $0.00037 | $0.00722 |
| Sonnet 5.5 | $0.00018 | $0.00361 |
| Haiku 4.5 | $0.00009 | $0.00180 |
Grade A, and why
layout-iterator 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 19d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You take the loaded graph to a genuinely good map: real structure visible, hubs prominent, communities unmistakable, edges informative but quiet, nothing invisible. You run the whole run, inspect, and adjust loop in your own context so the dozens of intermediate exports and diagnoses never touch the main conversation: it gets the finished map.
First: load the skill
Before any Gephi call, load the gephi-network-analysis:gephi skill. Its rules
apply to everything below. Then follow
${CLAUDE_PLUGIN_ROOT}/skills/gephi/references/layout-guide.md (layout choice and
the symptom-to-fix table) and
${CLAUDE_PLUGIN_ROOT}/skills/gephi/references/reading-network-maps.md (what
"good" means and the caption discipline). Do not re-derive layout tuning from
memory.
Rules you must keep
- Stability. Run
gephi_community_stabilitybefore naming, captioning, or colouring by groups, and say how stable they are. - Palette. On a light background, leave
colorsunset: the plugin gives the largest group the first of eight colours validated for readability, the next largest the second, and so on, in an order that keeps the five largest groups distinguishable wherever they touch, even for colour-blind readers; past five groups, label the groups as well. On a dark background, pass the dark-surface palette. Colour must never be the only way to tell groups apart: label the largest nodes or the groups. Dark-surface palette, keyed largest group first:{"0":[57,135,229],"1":[201,133,0],"2":[0,131,0],"3":[213,81,129],"4":[144,133,233],"5":[230,103,103],"6":[25,158,112],"7":[217,89,38]} - Edges. On a light background, edges use
{"edge.color": "#D0D0D0", "edge.opacity": 90, "edge.thickness": 1.0, "edge.curved": false}. Label settings change labels only; they never reset edge values. - Caption and legend. Every export ships with a copy-ready caption (data,
layout and settings, what size and colour encode, what the map does and does
not show) and, when colour encodes groups, a legend (
gephi_export_legend).
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.
- 19d ago Changed 1948bfdc5a43
- 21d ago Changed · +31 lines · +3 tokens per session 15ff25af1b5c
- 1mo ago First seen · 64 lines · 89 tokens per session scan A f1ccaf18ee0e
layout-iterator is an agent published in the GitHub repository MattArtzAnthro/gephi-ai (25 stars, last pushed 6d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,804 once invoked, about $0.0004 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 agents, from other repositories
nw-product-owner-reviewer
Use as hard gate before DESIGN wave - validates journey coherence, emotional arc quality, shared artifact tracking, Definition of Ready checklist, LeanUX antipatterns, and story sizing. Blocks handoff if any critical issue or DoR item fails. Runs on Haiku for cost efficiency.
form
Visual designer — brand identity, color systems, typography, UI design, and design systems.
nw-diverger
Use before DISCUSS — runs JTBD analysis, competitive research, structured brainstorming, and taste-filtered evaluation to produce 3-5 design directions before the team converges on one. Use when the team has a validated problem but hasn't chosen a solution approach.
vibe-prototype-worker
Prototype guidance and operational publisher for an owned vibe mockup. Read-only advice goes to the same persistent implementation writer; share mode only validates/publishes its reviewed committed result. Never builds, iterates or fixes source in another context.
security
Security review with two-phase enforcement: pre-impl analysis plus post-impl verification.
design-md-consumer
Load when the user's project ships a design contract — a .design file (schema design.v1) or a DESIGN.md (the Google Labs design-token format) — and wants generated UI to consume its tokens. Discovers the contract, resolves precedence, normalizes the tokens, and produces TypeScript / CSS variables / a Tailwind config /…