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 cyborg-garden/hermes-agent-mt --skill anatomygit clone --depth 1 https://github.com/cyborg-garden/hermes-agent-mtWrote 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/cyborg-garden/hermes-agent-mt/anatomy)<a href="https://agentmods.dev/skills/cyborg-garden/hermes-agent-mt/anatomy"><img src="https://agentmods.dev/badge/skills/cyborg-garden/hermes-agent-mt/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/cyborg-garden/hermes-agent-mt/anatomy"><img src="https://agentmods.dev/badge/skills/cyborg-garden/hermes-agent-mt/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 | $0.00015 | $0.08434 |
| Opus 5.5 | $0.00006 | $0.03374 |
| Sonnet 5.5 | $0.00003 | $0.01687 |
| Haiku 4.5 | $0.00002 | $0.00843 |
Grade A, and why
anatomy 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 anatomy — 2 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anatomy
This skill builds figures that work like a small instrument on a bench: a heavy base on feet, rails with tick rulers, a carriage on bushings, knurled knobs, coil springs, a dial gauge whose needle moves, and screws drawn as tiny dots. The reader understands the idea because they recognise the machine. Every number the figure shows comes from the same model that moves its parts.
Output is a standalone HTML page (SVG plus optional WebGL layers), a lone .svg, or React/Next.js components. The kit uses only Node built-ins, so there is nothing to npm install.
Running it in Hermes
Skill directory. Hermes expands ${HERMES_SKILL_DIR} to this skill's installed directory. Shell variables don't carry over between terminal calls, so repeat the assignment in every call that uses it:
SKILL_DIR="${HERMES_SKILL_DIR}"
Never build inside the skill directory. Every build.mjs writes its HTML next to itself, and the examples import ../../kit/ and ../../scripts/. Lay out a workspace with the same shape: the user's project if they have one, otherwise a folder they name.
SKILL_DIR="${HERMES_SKILL_DIR}"
WORK="$HOME/figures/pin-lock"
mkdir -p "$WORK/figures"
cp -r "$SKILL_DIR/kit" "$SKILL_DIR/scripts" "$WORK/"
cp -r "$SKILL_DIR/examples/dial-indicator" "$WORK/figures/"
cd "$WORK/figures/dial-indicator" && node build.mjs && node build.mjs --light
Start a new figure by copying the closest example into $WORK/figures/<name>/ and renaming it. Leaving the installed skill untouched keeps hermes skills update from flagging it as locally modified.
The examples ship as source only. Upstream's built pages are 9 MB of generated HTML. Build an example (as above) to open or capture it, since it takes a few seconds.
Looking at your work. The upstream workflow says "read every PNG". In Hermes that means vision_analyze on each capture, and the 4× close-ups use its region crop on a high-DPR capture or a --zoom capture. Ask specific questions ("does the pipe at the flange end on the flange face?"), not "does this look good".
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.
- 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 88 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 6.3 KB
- kit/react/live.tsx 4.0 KB
- kit/tube.mjs 14 KB runs code
- kit/turn-audit.mjs 56 KB runs code
- kit/turn-build.mjs 63 KB runs code
- kit/turn-fixed.mjs 144 KB runs code
- kit/turn.mjs 137 KB runs code
- LICENSE.txt 1.0 KB
- references/3d.md 44 KB
- references/craft.md 49 KB
- references/kit.md 66 KB
- references/motion.md 22 KB
- references/react.md 3.5 KB
- references/verify.md 43 KB
- references/walkthrough.md 5.2 KB
- references/webgl.md 60 KB
- scripts/capture.mjs 12 KB runs code
- scripts/drive.mjs 21 KB runs code
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 · 216 lines · 15 tokens per session scan A c682d42079f2
anatomy is a skill published in the GitHub repository cyborg-garden/hermes-agent-mt (14 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 8,434 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to anatomy, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
show-me
Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
hermes-memory-providers
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Stricter, user-selected override that forces Mnemosyne for all durable memory storage, including small standing rules. Apply it only when the user has consciously chosen this policy; installation, this skill appearing in the skills index, or an ordinary memory task is not that choice. Without it, the default applies…
with-scripts
Bundled Gmail CLI example demonstrating the scripts/ entrypoint + src/ implementation split. Use as a template when your course ships real code that goes beyond a single shell script. Shows how to organize a course bundle that owns its codebase — no runtime package installation, all dependencies stdlib-only. Replaces…
with-paid
Paid-course example showing how to package a self-contained Logion bundle with the marketplace paid license. Use as a starting point when you want a benign course that reads local artifacts, produces a structured report, and exercises the paid publication path end to end.