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/davekilleen/dex/compound-docsnpx skills add davekilleen/Dex --skill compound-docsgit clone --depth 1 https://github.com/davekilleen/DexWhat 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 | $0.00017 | $0.03359 |
| Opus 5 | $0.00009 | $0.01680 |
| Sonnet 5 | $0.00003 | $0.00672 |
| Haiku 4.5 | $0.00002 | $0.00336 |
Grade A, and why
compound-docs 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 3d ago First seen · 511 lines · 17 tokens per session scan A 508c65f5118a
compound-docs is a skill published in the GitHub repository davekilleen/Dex (474 stars, last pushed yesterday), with no licence file. It adds 17 tokens to every session and 3,359 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
review-code
Deep code quality review for the inspecto monorepo. Use this skill whenever the user wants to review, audit, or assess the quality of code in the inspecto project — even if they just say "check this file", "is this well written", "review my implementation", or "does this follow the architecture?". Accepts a file path…
vscode-ext-analyze-params
Analyze the parameter signature of a specific VSCode extension command by reverse-engineering the minified extension.js source code. Given an extension ID and a command name, extracts the registerCommand callback's formal parameters, infers types from runtime type-checking patterns (typeof, Array.isArray), and checks…
vscode-ext-context
Extract raw source code context around a specific VSCode extension command's registerCommand call. Outputs the surrounding N characters of minified code for manual inspection. Use when the user wants to see the actual source code around a command registration, needs to understand the internal implementation details…
vscode-ext-list-commands
List all commands registered by a VSCode extension, including hidden ones not declared in package.json. Given an extension ID (e.g. anthropic.claude-code), finds the installed extension, extracts declared commands from package.json and runtime-registered commands from extension.js. Use when the user asks: what…
project-brain
Triggers (all require explicit user request — do NOT activate just because a brain/ folder exists): (1) The user wants to set up project-level memory ("set up project brain", "scaffold project context", "init project brain", "建项目脑"). (2) The user is in a directory containing brain/ AND explicitly asks to resume /…
inspecto-onboarding-codex
Use when Codex should install or set up Inspecto in the current frontend project through the shared onboarding workflow.