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/apurvbazari/claude-plugins/documentnpx skills add ApurvBazari/claude-plugins --skill documentgit clone --depth 1 https://github.com/ApurvBazari/claude-pluginsWhat 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 | $0.00089 | $0.01413 |
| Opus 5 | $0.00044 | $0.00707 |
| Sonnet 5 | $0.00018 | $0.00283 |
| Haiku 4.5 | $0.00009 | $0.00141 |
Grade A, and why
document 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 2d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document — Render a Subject as an Interactive Document
You are invoked via /walkthrough:document <subject> [output-path]. Produce ONE self-contained
interactive HTML file in the house style from a subject (not the session), then offer to open it.
The visual layer is reused verbatim from the create skill; only the model and gathering differ.
Renderer files (reuse UNCHANGED, via relative path from this skill):
../create/references/design-system.md, ../create/references/interactivity.md,
../create/references/page-scaffold.md, ../create/references/authoring-guide.md,
../create/references/components/ (catalog; index.md routes to group files).
Step 1: Identify the subject
<subject> is the first argument — a plugin directory, the word marketplace (or repo root), or
any path/description. Route to the right adapter per references/gather-subject.md.
Step 2: Gather (README + manifest are canonical)
Follow references/gather-subject.md and the matched adapter
(references/adapters/plugin.md or references/adapters/marketplace.md). Read the canonical
source files. Cite path:line only when verified by a real read.
Step 3: Synthesize the subject model
Build the structured model per references/subject-model.md (title, tagline, summary, typeTags,
install, sections[], nodes[], edges[], reference[], examples[], links[], details{}) BEFORE any HTML.
Step 4: Coverage critic
Run ../create/references/completeness.md Part 1 against the subject before selecting components.
Fold omitted salient items in; note intentional omissions for the coverage note.
Step 5: Select components
Run the shared select stage of ../render/references/render-contract.md: using
../create/references/authoring-guide.md, map the model to component names, then look each up in
../create/references/components/index.md for its group file; apply "omit empty, never stub". For the
marketplace card grid (and anything else with no catalog entry), compose a bespoke component per the
authoring-guide recipe + looks-native checklist.
What ships with it
4 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.
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.
- 2d ago First seen · 90 lines · 89 tokens per session scan A 3706ebc54162
document is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 26d ago), licensed MIT. It adds 89 tokens to every session and 1,413 once invoked, about $0.0004 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
cross-platform
Cross-platform development patterns for macOS, Windows, and Linux.
shell-scripting
Shell scripting best practices for cross-platform CLI tools.
c-notify
Send native macOS notification center alerts from the command line using terminal-notifier.
change-keybinding
Customize Warp keyboard shortcuts (keybindings, keymappings) by editing the user's keybindings.yaml file. Use when the user asks to remap a key combination, rebind an action, change a shortcut, or remove a default keybinding (e.g. "change ctrl+space to ctrl+s", "rebind the command palette to cmd+p", "remove the…
agent-add-mcp
Use this skill when helping users add MCP servers to their Warp configuration.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.