glossary

glossary is a skill for Claude Code from AcKeskin/contexture. It costs 77 tokens per session (2,624 once invoked), scanned A, original, MIT.

A project glossary that records important domain terms, their meanings, and the code symbols that represent them. Domain terms are the words a particular business or system uses for its concepts.

In plain words
What is it for?
Defining project vocabulary, linking business terms to code, and giving naming reviews a shared reference.
Why use it?
It reduces misunderstandings and inconsistent naming when the same project words have specific meanings or possible conflicts.

Skill for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: mentions AGENTS.md.

Install

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.

agentmods
npx agentmods add skills/ackeskin/contexture/glossary
Any agent
npx skills add AcKeskin/contexture --skill glossary
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

Made for: Claude Code.

Wrote 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.

agentmods badge for glossary

README.md
[![agentmods](https://agentmods.dev/badge/skills/ackeskin/contexture/glossary.svg)](https://agentmods.dev/skills/ackeskin/contexture/glossary)
Your own site
<a href="https://agentmods.dev/skills/ackeskin/contexture/glossary"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/glossary.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,624 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.02624
Opus 5 $0.00039 $0.01312
Sonnet 5 $0.00015 $0.00525
Haiku 4.5 $0.00008 $0.00262

Measured 2d ago against content hash 144d3febb41b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

glossary 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.

skills/glossary/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

glossary

The domain-vocabulary organ. Captures what a project's words mean — the Ubiquitous Language (DDD) — as a durable project-tier artefact: each load-bearing domain term with a one-line definition, the code symbol(s) that embody it, and a note where terms collide.

The third leg of the "observe-the-codebase-and-write-it-down" set: structure (codemap) + style (extract-conventions) + meaning (this). Codemap says what the modules are; conventions say how the code is styled; the glossary says what the domain nouns and verbs mean. Built to extract-conventions' shape — same author→prime→audit→project loop, same propose-confirm gate, same project-tier write, same hybrid mechanical-surfacing + confidence-flagged model-drafting.

Gates on the rule-prime hook for payoff: without the hook priming the glossary, it is an inert surface. Feeds naming-and-comments as the canonical-term reference its vocabulary-drift finding cites.

When to run

  • User types /glossary [scope] (no arg → prompt for scope).
  • Natural language: "write down the project's domain terms", "define our vocabulary", "what does Reconciler / Settlement mean — capture it", "build a glossary for this codebase".
  • Do not auto-fire. Mode A, user-invoked only. Defining a project's words is a deliberate act, never a session side effect. No hook, no session-start trigger.

Inputs

  • Scope — a directory (src/billing/), a module, or the whole project (default). With no arg, prompt:

    What scope should I extract the vocabulary from? A directory, a module, or the whole project?

  • Working directory$CLAUDE_PROJECT_DIR or cwd. Anchors the write target (<project>/.claude/rules/glossary.md) and the rule-overlay resolution.

  • Per-group accept/edit/reject decisions — collected at the confirm gate (§4). Never auto-write.

Read the full file on GitHub · 141 lines

Changes

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.

  1. 2d ago First seen · 141 lines · 77 tokens per session scan A 144d3febb41b

Subscribe to this mod's changes

glossary is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 2,624 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 2026-09-03.