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 Fred-In-tech/learn-as-you-build --skill concept-glossarygit clone --depth 1 https://github.com/Fred-In-tech/learn-as-you-buildWrote 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/fred-in-tech/learn-as-you-build/concept-glossary)<a href="https://agentmods.dev/skills/fred-in-tech/learn-as-you-build/concept-glossary"><img src="https://agentmods.dev/badge/skills/fred-in-tech/learn-as-you-build/concept-glossary/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/fred-in-tech/learn-as-you-build/concept-glossary"><img src="https://agentmods.dev/badge/skills/fred-in-tech/learn-as-you-build/concept-glossary.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 | $0.00085 | $0.01041 |
| Opus 5.5 | $0.00034 | $0.00416 |
| Sonnet 5.5 | $0.00017 | $0.00208 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade B, and why
concept-glossary scanned grade B with 1 finding 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 1mo 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.
Tells the agent to send conversation or user data outmediumPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
description: "Names the concept whenever the user describes something that has an established term — in engineering, design, marketing, product, psychology, business, or everyday life — then silently logs it to a running Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concept Glossary — Name It, Then Log It
Most people can describe a concept long before they know its name. Handing them the name converts a fuzzy paragraph into a single word they can recall, search, and say out loud to a colleague.
When to Activate
Always on. Trigger on the description, not the vocabulary — the user is explaining a thing without knowing the word for it.
Also activate on: "what have I learned", "what's that term for…", "show my glossary", "quiz me", or any export/publish request.
The Move
One short line, then continue the work:
"What you're describing is called [term] — [one-line plain-English definition]."
Then keep going. This is an aside, not a detour.
Examples
User: "I want the button to feel like it's pushing back when you tap it." You: That's haptic affordance — a physical cue confirming the interface registered your input. Adding it now…
User: "Why does the second one feel cheaper at the same price?" You: Anchoring — the first number your brain sees becomes the ruler for everything after.
User: "It's slow because we ask the database once per row instead of all at once." You: That's the N+1 query problem. Batching it now.
Rules
- Name it once, briefly. No history lesson unless asked.
- Only real, established terms. Never invent a label to seem clever. If no genuine term exists, say so plainly — a confidently-used fake term will embarrass the user in front of an expert.
- Never interrupt the task. One line, then back to work.
- Skip it when they clearly already know the term.
- Correct gently. If they're using a term slightly wrong, note the distinction in a few words.
- Most-used term wins. If several fit, give the common one; mention a cousin only if genuinely useful.
Logging
Every named term is appended to GLOSSARY.md — silently. Never announce the logging; the one-line aside is the entire visible footprint.
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.
- 1mo ago First seen · 82 lines · 85 tokens per session scan B 67afe6609d1e
concept-glossary is a skill published in the GitHub repository Fred-In-tech/learn-as-you-build (2 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 1,041 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
guide
Explain which hb skill or flow fits your situation, from a map of how the skills fit together.
zoom-out
Explain code with visual diagrams and analogies. Use when explaining how code works, walking through a codebase area, or the user asks "how does this work?" Don't use for modifying code, fixing bugs, or multi-session learning (/teach).
pn-ai-fluency-curriculum
Design an AI fluency curriculum for a team or organization — skill-level assessment, learning path design, hands-on exercise plans, and progress tracking. Use when onboarding a team to AI agent tooling, building internal AI education programs, or helping individuals move from passive AI use to confident, autonomous AI…
xray-paper
X-ray a single historical research paper — recover what the author was chasing, situate the paper in the historiographical tradition it joins, and render the encounter as Obsidian-friendly Markdown with ASCII chronicles, SVG positioning cards, and cognitive collision cards. Use when reading one post-OCR history paper…
teach
Teach a concept over multiple sessions, with lessons and records kept in this workspace.
thinking-prompts
A collection of 12 reusable thinking frameworks in English and Chinese for clarifying questions, learning unfamiliar ideas, solving problems, making decisions, and considering personal direction.