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 OutlineDriven/odin-claude-plugin --skill automatic-freeform-graphs-designgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/automatic-freeform-graphs-design)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/automatic-freeform-graphs-design"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/automatic-freeform-graphs-design/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/outlinedriven/odin-claude-plugin/automatic-freeform-graphs-design"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/automatic-freeform-graphs-design.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 | $0.00047 | $0.00902 |
| Opus 5 | $0.00023 | $0.00451 |
| Sonnet 5 | $0.00009 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
automatic-freeform-graphs-design 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 5d 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.
This is a copy
100% identical to automatic-freeform-graphs-design — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automatic freeform graphs design
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants a looser conceptual graph for exploratory work. |
| Authority | Reversible local: write only one named freeform conceptual graph artifact to the working directory. Do not mutate VCS, credentials, remotes, or published content. Roll back by deleting or overwriting that single file. |
| Side effect | A freeform conceptual graph artifact for exploration, written to the local filesystem. |
| Done | A freeform conceptual graph is generated and can be used for exploration. |
Inputs
- Exploratory topic or problem statement (required): the subject area to map. May be a question, a half-formed idea, a domain, or a set of related concerns.
- Existing notes or fragments (optional): prior concepts, questions, or connections the graph should incorporate.
- Output path (optional): where to write the graph artifact. Defaults to a file in the working directory.
Procedure
- Read the exploratory topic and any supplied notes. Identify the kind of exploration: open-ended question, design-space survey, concept mapping, or unknown-territory scouting. Done when: the exploration type is identified from the topic and notes.
- Extract concepts, questions, unknowns, and hypotheses as candidate nodes. Do not force them into a dependency order: this is exploration, not execution planning. Done when: candidate nodes are extracted without imposing a dependency order.
- Map relationships between nodes as labeled edges. Use relationship types suited to exploration: influences, tensions, supports, contradicts, depends-on-maybe, raises-question-of, and unknown-link. Allow cycles, bidirectional edges, and self-references where the exploration calls for them. Done when: edges are mapped with exploration-suited relationship labels, allowing cycles.
- Mark each node and edge with a confidence marker: certain, suspected, or unknown. Mark open questions explicitly so the graph surfaces what is not yet known. Done when: every node and edge has a confidence marker and open questions are marked.
- Identify clusters of tightly connected nodes and label them as provisional themes. Identify bridges between clusters as high-value exploration targets. Done when: clusters are labeled as themes and bridges are identified as high-value targets.
- Write the graph as a text artifact: a node list with confidence markers, an edge list with relationship labels, a cluster summary, the high-value bridge targets identified in step 5, and a list of open questions. Use a plain-text or markdown format that a human can read and revise without tooling. Done when: the graph artifact is written with all five sections in human-readable format.
- Review the graph against the original topic. Check that it surfaces the key unknowns without imposing a false dependency order. If a region is sparse or missing, add nodes and edges rather than leaving gaps. Done when: the graph surfaces key unknowns and has no false dependency order or sparse gaps.
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.
- 5d ago First seen · 42 lines · 47 tokens per session scan A 14975beed2ee
automatic-freeform-graphs-design is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 47 tokens to every session and 902 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to automatic-freeform-graphs-design, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…