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 agentmods add skills/vosslab/vosslab-skills/ideonomy-plainnpx skills add vosslab/vosslab-skills --skill ideonomy-plaingit clone --depth 1 https://github.com/vosslab/vosslab-skillsWrote 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/vosslab/vosslab-skills/ideonomy-plain)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/ideonomy-plain"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/ideonomy-plain.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.02475 |
| Opus 5 | $0.00027 | $0.01238 |
| Sonnet 5 | $0.00011 | $0.00495 |
| Haiku 4.5 | $0.00005 | $0.00248 |
Grade C, and why
ideonomy-plain scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
PICK=$(find ~/.claude/plugins ~/.claude/skills -path '*/ideonomy-plain/bin/pick' -type f 2>/dev/null | head -1) Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
PICK=$(find ~/.claude/plugins ~/.claude/skills -path '*/ideonomy-plain/bin/pick' -type f 2>/dev/null | head -1) How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideonomy-Plain
A skill for expanding ideas using Patrick Gunkel's ideonomy — the science of treating ideas as natural phenomena that can be sliced, negated, recombined, and re-instantiated. Synthesized from Grace Kind's writing on Ideonomy at gracekind.net. All credit for the framework as presented here belongs to Grace Kind and Patrick Gunkel.
This is the plain-text-portable half of a pair. Output is plain Markdown lists, fenced-code-block tables, no Unicode box-drawing — survives every channel, including SMS bridges. For monospace-rich rendering with figlet banners, Unicode box-drawing, density gradients, and visible ideonomy-machinery layers, use the sibling skill ideonomy-rich.
Core principle
Ideas have properties that vary along dimensions. To expand an idea, identify its dimensions and then operate on them — substitute one value for another, negate a definitional property, combine the idea's organon (its structured capture) with another organon, or lift the idea to a higher abstraction and re-instantiate it elsewhere. The expansion is the population of related ideas these operations surface.
How to invoke
Step 1 — pick a method tuple. Run the pick script. It selects a random combination of operators, an organon, and dimension prompts from the catalog under methods/:
# Locate pick (works for any installation method):
PICK=$(find ~/.claude/plugins ~/.claude/skills -path '*/ideonomy-plain/bin/pick' -type f 2>/dev/null | head -1)
bash "$PICK"
# With flags: bash "$PICK" --more / --less / --print / --seed N
The script prints the picks then concatenates the bodies of the selected method files. Read all of it.
Flags:
--more— bigger tuple (3 operators, 2 organons, 5 dim-prompts)--less— smaller tuple (1 operator, 1 organon, 2 dim-prompts)--print— just print the picks; don't cat the bodies--random-org— seed the picker from random.org (network) instead of local entropy--seed N— deterministic pick for a given integer seed
What ships with it
60 files 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.
- agents/openai.yaml 217 B
- bin/pick 5.0 KB
- examples/historical-recipes/atlas-of-perspectives.md 1.7 KB
- examples/historical-recipes/cross-domain-lift.md 1.6 KB
- examples/historical-recipes/dimensional-exhaustion.md 1.7 KB
- examples/historical-recipes/negate-and-lift.md 1.5 KB
- examples/historical-recipes/negation-cascade.md 1.4 KB
- examples/historical-recipes/organon-sandwich.md 1.8 KB
- examples/historical-recipes/property-explosion.md 1.6 KB
- examples/historical-recipes/tree-walk.md 1.9 KB
- examples/walkthrough.md 8.3 KB
- methods/dimension-prompts/age.md 458 B
- methods/dimension-prompts/animacy.md 536 B
- methods/dimension-prompts/autonomy.md 485 B
- methods/dimension-prompts/cardinality.md 391 B
- methods/dimension-prompts/complexity.md 483 B
- methods/dimension-prompts/connectivity.md 491 B
- methods/dimension-prompts/cyclicity.md 393 B
- methods/dimension-prompts/decomposability.md 463 B
- methods/dimension-prompts/direction.md 395 B
- methods/dimension-prompts/discovery-vs-invention.md 540 B
- methods/dimension-prompts/distribution.md 549 B
- methods/dimension-prompts/hierarchicalness.md 551 B
- methods/dimension-prompts/homogeneity.md 532 B
- methods/dimension-prompts/intentionality.md 518 B
- methods/dimension-prompts/longevity.md 515 B
- methods/dimension-prompts/materiality.md 563 B
- methods/dimension-prompts/modularity.md 444 B
- methods/dimension-prompts/naturalness.md 605 B
- methods/dimension-prompts/polarity.md 603 B
- methods/dimension-prompts/predictability.md 483 B
- methods/dimension-prompts/purpose.md 506 B
- methods/dimension-prompts/rate.md 485 B
- methods/dimension-prompts/reversibility.md 542 B
- methods/dimension-prompts/scope.md 445 B
- methods/dimension-prompts/side-effect.md 538 B
- methods/dimension-prompts/size.md 449 B
- methods/dimension-prompts/source.md 532 B
- methods/dimension-prompts/symmetry.md 477 B
- methods/dimension-prompts/visibility.md 462 B
- methods/operators/abstraction-lift.md 2.7 KB
- methods/operators/combination.md 2.0 KB
- methods/operators/cross-domain-reinstantiation.md 2.6 KB
- methods/operators/dimension-identification.md 2.0 KB
- methods/operators/negation.md 2.1 KB
- methods/operators/organon-construction.md 1.9 KB
- methods/operators/substitution.md 1.9 KB
- methods/operators/tree-finding.md 2.4 KB
- methods/organons/atlas.md 1.6 KB
- methods/organons/chart.md 1.6 KB
- methods/organons/cycle.md 1.5 KB
- methods/organons/dictionary.md 1.6 KB
- methods/organons/graph.md 1.5 KB
- methods/organons/lattice.md 1.8 KB
- methods/organons/list.md 1.2 KB
- methods/organons/map.md 1.8 KB
- methods/organons/matrix.md 1.6 KB
- methods/organons/notation.md 1.9 KB
- methods/organons/periodic-grid.md 2.1 KB
- methods/organons/procedure.md 1.7 KB
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 · 136 lines · 54 tokens per session scan C d3c60f1e7d60
ideonomy-plain is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 10d ago), licensed MIT. It adds 54 tokens to every session and 2,475 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…