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 aeonfun/aeon --skill anatomygit clone --depth 1 https://github.com/aeonfun/aeonWrote 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/aeonfun/aeon/anatomy)<a href="https://agentmods.dev/skills/aeonfun/aeon/anatomy"><img src="https://agentmods.dev/badge/skills/aeonfun/aeon/anatomy/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/aeonfun/aeon/anatomy"><img src="https://agentmods.dev/badge/skills/aeonfun/aeon/anatomy.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 | $0.00202 | $0.09332 |
| Opus 5.5 | $0.00081 | $0.03733 |
| Sonnet 5.5 | $0.00040 | $0.01866 |
| Haiku 4.5 | $0.00020 | $0.00933 |
Grade C, and why
anatomy scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$WORK" && mkdir -p "$WORK" && cp -R skills/anatomy "$WORK/anatomy" This is a copy
88% identical to anatomy — 109 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aeon runtime integration
On Aeon this skill runs headless in a GitHub Actions job through the configured harness adapter, and .github/workflows/aeon.yml kills that job at 50 minutes. The rules in this section override any upstream guidance below that conflicts with them (sizing, timings, asking or telling the user, and where files are written). Everything from # Anatomy down is the vendored upstream text, kept verbatim; read it through these rules.
Today is ${today}.
1. Brief
${var} is the illustration brief, for example "how a write-ahead log survives a crash". If ${var} is empty, append ANATOMY_NO_VAR under ### anatomy in memory/logs/${today}.md and exit 0 with no build and no notify: a figure costs real CI time, so a blank default run does nothing.
2. Headless: never ask
Nobody is there to answer. Never ask a question, wait for a choice, or "tell the user" before working. Where the upstream text says to tell, ask or wait for the user, decide yourself and put the decision (size, any downscale) in the notify and the log instead.
3. Time budget and size
Run date at the start and at each step. The whole run (research, build, checks, commit, notify) must fit in about 35-40 minutes so the job is never killed. This replaces upstream workflow step 1 and its estimates:
- Build a Figure or smaller: one mechanism, 40-80 parts, SVG with at most one WebGL layer. Have a page that builds and opens by about minute 15, then deepen it.
- A brief that reads as a Hero or an Epic, or that needs the 3D mode, is downscaled to a Figure that keeps the core of the idea. Never start a Hero, an Epic or a 3D figure on Aeon (the 3D orbit audit alone takes 15-20 minutes). Say in the notify what the full version would add.
- Use the framework-free path (a Node build script writing one standalone HTML page). The runner has no React or TypeScript toolchain for this skill.
- Checks, in order of value: the build,
--auditwhen the figure has pipes, cables or round parts,scripts/lines.mjs, and one desktop plus one phone (390 wide) capture withscripts/capture.mjs. Skip the long close-up sweeps and shader contact sheets when time is short, and say which checks were skipped. - At about minute 30, stop adding detail and run the final checks. At about minute 38, deliver what you have if the page builds and opens, with
--severity warnnaming what is unfinished.
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.
- .gitattributes 89 B
- .gitignore 189 B
- agents/openai.yaml 120 B
- CHANGELOG.md 7.4 KB
- evals/evals.json 8.0 KB
- examples/arcade-cabinet/arcade-cabinet.css 3.1 KB
- examples/arcade-cabinet/build.mjs 50 KB runs code
- examples/arcade-cabinet/live.js 21 KB runs code
- examples/arcade-cabinet/parts.mjs 4.2 KB runs code
- examples/arcade-cabinet/screen.mjs 6.5 KB runs code
- examples/desk-computer/build.mjs 22 KB runs code
- examples/dial-indicator/build.mjs 15 KB runs code
- examples/raptor-engine/build.mjs 69 KB runs code
- examples/raptor-engine/live.js 30 KB runs code
- examples/raptor-engine/raptor.css 6.6 KB
- examples/ripple-tank/build.mjs 31 KB runs code
- examples/ripple-tank/live.js 21 KB runs code
- examples/ripple-tank/model.mjs 4.9 KB runs code
- examples/ripple-tank/ripple.css 1.6 KB
- examples/spot-plate/art.tsx 4.4 KB
- examples/spot-plate/drops.ts 19 KB runs code
- examples/spot-plate/fan.ts 2.7 KB runs code
- examples/spot-plate/figure.tsx 1.1 KB
- examples/spot-plate/geometry.ts 11 KB runs code
- examples/spot-plate/live.tsx 11 KB
- examples/spot-plate/rig.ts 8.0 KB runs code
- examples/spot-plate/spot-plate.css 1.5 KB
- examples/test-rig/art.tsx 7.2 KB
- examples/test-rig/figure.tsx 850 B
- examples/test-rig/geometry.ts 13 KB runs code
- examples/test-rig/live.tsx 17 KB
- examples/test-rig/pose.ts 3.8 KB runs code
- examples/test-rig/rig.ts 5.5 KB runs code
- examples/test-rig/stretch.css 1.2 KB
- examples/test-rig/view.ts 3.0 KB runs code
- examples/turning-dial/build.mjs 31 KB runs code
- examples/turning-dial/dial.css 509 B
- examples/turning-dial/live.js 12 KB runs code
- examples/turning-dial/stress.mjs 19 KB runs code
- kit/audit.mjs 91 KB runs code
- kit/canvas-painter.mjs 27 KB runs code
- kit/gl-shared.mjs 8.7 KB runs code
- kit/gl.mjs 8.6 KB runs code
- kit/iso-kit.mjs 34 KB runs code
- kit/iso-kit.ts 38 KB runs code
- kit/iso.css 7.5 KB
- kit/lathe.mjs 47 KB runs code
- kit/react/draw.tsx 6.4 KB
- kit/react/live.tsx 4.5 KB
- kit/tube.mjs 14 KB runs code
- kit/turn-audit.mjs 56 KB runs code
- kit/turn-build.mjs 64 KB runs code
- kit/turn-fixed.mjs 144 KB runs code
- kit/turn.mjs 137 KB runs code
- LICENSE 1.0 KB
- README.md 23 KB
- references/3d.md 44 KB
- references/craft.md 49 KB
- references/kit.md 66 KB
- references/motion.md 22 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.
- 3d ago First seen · 245 lines · 202 tokens per session scan C 59b568cd65fd
anatomy is a skill published in the GitHub repository aeonfun/aeon (775 stars, last pushed today), licensed MIT. It adds 202 tokens to every session and 9,332 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). It is 88% identical to anatomy, differing in 109 lines, and is treated as a copy.
Other skills, from other repositories
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
blind-spot-pass
Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…
flowcraft-config
Author, validate, and troubleshoot complete FlowCraft configuration: deployment documents (deploy.yaml with the runtime section, inference/workspace/sandbox/tool sub-documents, core/memory contracts, and graph JSON node wiring), craft.yaml application definitions, and plugin.json manifests. Use when writing or…
prompts-chat
Use when searching, installing, or improving AI skills and prompts via prompts.chat or skills.sh. Triggers on skill search, prompt lookup, install skill, improve prompt, prompts.chat.
career-path-planner
Career goal mapping with skill gap analysis, actionable development plans, and milestone tracking. Use when planning career transitions, identifying skill gaps, setting professional development goals, or evaluating career options.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.