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 adtn0810/truestack --skill truestack-explain-plaingit clone --depth 1 https://github.com/adtn0810/truestackWrote 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/adtn0810/truestack/truestack-explain-plain)<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-explain-plain"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-explain-plain/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/adtn0810/truestack/truestack-explain-plain"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-explain-plain.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 | $0.00182 | $0.01200 |
| Opus 5 | $0.00091 | $0.00600 |
| Sonnet 5 | $0.00036 | $0.00240 |
| Haiku 4.5 | $0.00018 | $0.00120 |
Grade A, and why
truestack-explain-plain 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 10d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
truestack-explain-plain
Working code the user can't follow teaches nothing. The set's skills close their reports with a one-line "explain it simply" footer — but a footer is not a lesson. This skill fires when the explanation is the deliverable: what was built, why it's shaped that way, how the piece the user points at behaves — in plain English a junior developer can absorb, remember, and reuse. It is translation, not investigation: it explains what is already known or readable in place, and digs up nothing new.
When to use (and when not)
- Automatically, after every build, fix, or design task — no request needed. Say what was done and why, sized to the change: substantial work gets the full lesson, a trivial change gets two plain sentences in the close. Either way it is one close — never the sibling's footer and a lesson stacked on top of each other.
- Whenever the user asks to understand — "what does this do", "why did you build it that way", "walk me through it" — or signals confusion. "I don't get it" fires this skill, never a defense of the previous answer.
- Not this skill: producing a verified model of an unfamiliar or shared artifact, or an upgrade path from it → truestack-reverse-engineering; a question about a third-party system with nothing shared to open → truestack-deep-research. When comprehension needs real investigation first, chain them — investigate, then explain the findings plainly. Reading the one file the user points at is translation; needing to chase its imports, callers, or an unfamiliar system to answer is investigation — chain it through truestack-reverse-engineering first.
1. Big picture first
Open with the what and the why in one or two sentences a beginner could repeat back. The reader who stops after the opening still leaves holding the idea; detail comes after, never instead.
2. Plain English — jargon pays a tax
No technical term unless it earns its place, and every term that stays gets a one-line definition at first use: "middleware — code that runs on every request before your route handler sees it." Expert framing that assumes prior knowledge is the failure mode, not a style choice.
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.
- 10d ago First seen · 87 lines · 182 tokens per session scan A 37dc7f871cac
truestack-explain-plain is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 182 tokens to every session and 1,200 once invoked, about $0.0009 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
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.