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/rockyhong/super-bootstrap/helpnpx skills add RockyHong/super-bootstrap --skill helpgit clone --depth 1 https://github.com/RockyHong/super-bootstrapWrote 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/rockyhong/super-bootstrap/help)<a href="https://agentmods.dev/skills/rockyhong/super-bootstrap/help"><img src="https://agentmods.dev/badge/skills/rockyhong/super-bootstrap/help.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 | $0.00093 | $0.00845 |
| Opus 5 | $0.00046 | $0.00423 |
| Sonnet 5 | $0.00019 | $0.00169 |
| Haiku 4.5 | $0.00009 | $0.00085 |
Grade A, and why
help scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help — User-Invoke Skill Discovery Surface
Render an on-demand menu of slash commands the user can invoke in this project. Cold-by-nature user-invoke skills (slash commands the user must remember) need a discovery surface; passive /super-bootstrap:help is the right shape.
Extraction is mechanical (structured JSON + YAML frontmatter), so a bundled script does it in one tool call with zero model tokens; the one judgment in the pipeline — which discovered skills a user would actually invoke — stays with the gateway.
When to Use
- User forgot which slash commands are available
- User just installed a new plugin and wants to see what it added
- User wants to filter by category (
/super-bootstrap:help git,/super-bootstrap:help docs)
Execution (gateway-inline)
When the user invokes /super-bootstrap:help [category]:
- Extract — run the bundled script, passing the project root (the session's working directory —
pwd):python3 "${CLAUDE_PLUGIN_ROOT}/skills/help/assets/render-menu.py" "$(pwd)"(The script body is opaque to the permission engine — the grant to carve is the invocation itself, e.g.Bash(python3 *).) It emits one candidate per line (category<TAB>command<TAB>description) from the installed-plugin registry,enabledPlugins, each enabled plugin's skills, and project.claude/skills. It deliberately over-reports — no filter lives in the script. - Filter to user-invoke — drop rows a user would never type: delegation-only skills (dispatched by other skills or the model, e.g. process/reference skills another skill invokes), hook-fired skills, and reference-material bundles. Keep anything a user plausibly types as a slash command. This is the judgment step; do it from the emitted descriptions — no file reads.
- Render — group surviving rows under their category headers (
[meta][pipeline][git][docs][dev][utils]), one line per skill: command + one-line summary. Header:Available slash commands ({N} total):. A category argument renders only that category; unknown category → list available categories. Anomaly footer: the script's stderr carries an# anomalies:line only when a source emitted fewer rows than it declared or held — render everything after its# anomalies:prefix as a footer line beneath the menu, contents unaltered and itself prefixedincomplete:. A short source is a discovery failure, and without the footer it is indistinguishable from a plugin that ships no commands. No# anomalies:line → no footer. - Fallback —
python3missing on the device: scan the same sources manually with Read/Grep (structure documented in the script header) and render the same shape.
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.
- 3d ago First seen · 36 lines · 93 tokens per session scan A 4d5d1260faeb
help is a skill published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed 6d ago), licensed MIT. It adds 93 tokens to every session and 845 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
cesiumjs-camera
CesiumJS camera control - Camera, flyTo, lookAt, setView, ScreenSpaceCameraController, CameraEventAggregator, flight animation. Use when positioning the camera, creating flyTo animations, constraining user navigation, tracking entities, or converting between screen and world coordinates.
cesiumjs-custom-shader
CustomShader authoring — vertexShaderText and fragmentShaderText against VertexInput, FragmentInput, FeatureIds, Metadata, czmmodelMaterial. Use when reading EXTmeshfeatures or EXTstructuralmetadata property textures/tables, vertex displacement, or shading VoxelPrimitive.
cesiumjs-core-utilities
CesiumJS core utilities and networking - Resource, Color, Event, Request, RequestScheduler, error handling, helper functions, feature detection. Use when fetching remote data, managing HTTP requests, working with colors, handling events, debugging errors, or using utility functions like defined, clone, or…
cesiumjs-materials-shaders
CesiumJS materials and post-processing — Material, Fabric JSON, MaterialAppearance, ImageBasedLighting, PostProcessStage, PostProcessStageLibrary, bloom, depth of field, ambient occlusion, FXAA, tonemapping, BlendingState. Use when defining Fabric materials for entities or primitives, configuring PBR image-based…
cesiumjs-models-particles
CesiumJS models, glTF, and particle effects - Model, KHRmeshoptcompression, CAD glTF extensions, EdgeDisplayMode, ModelAnimation, ModelNode, ParticleSystem, emitters, GPM extensions. Use when loading compressed or CAD-style glTF/GLB models, controlling edge rendering, playing model animations, positioning particles…