update-vocabulary

update-vocabulary is a command for coding agents from dsswift/ion. It costs 19 tokens per session (404 once invoked), scanned A, original, MIT.

A command for reviewing confirmed changes to the Ion vocabulary registry and its generated index. Ion is the codebase or toolset whose terms are being tracked.

In plain words
What is it for?
Use it after branch changes or when checking a particular concept, domain, path, or client surface. It examines source evidence, updates the vocabulary files, and regenerates the index.
Why use it?
It helps keep documented names, aliases, and deprecations aligned with the code, without renaming the code itself.

Command

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 commands/dsswift/ion/update-vocabulary
Clone the repo
git clone --depth 1 https://github.com/dsswift/ion

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 update-vocabulary

README.md
[![agentmods](https://agentmods.dev/badge/commands/dsswift/ion/update-vocabulary.svg)](https://agentmods.dev/commands/dsswift/ion/update-vocabulary)
Your own site
<a href="https://agentmods.dev/commands/dsswift/ion/update-vocabulary"><img src="https://agentmods.dev/badge/commands/dsswift/ion/update-vocabulary.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 404 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 $0.00019 $0.00404
Opus 5 $0.00010 $0.00202
Sonnet 5 $0.00004 $0.00081
Haiku 4.5 $0.00002 $0.00040

Measured today against content hash a15e9efd0b1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

update-vocabulary 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 today.

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.

.ion/commands/update-vocabulary.md · 31 lines

What it actually says

You are running the /update-vocabulary command.

Invocation arguments. The raw arguments passed to this invocation (referred to as ARGS throughout this document) are:

$ARGUMENTS

If the block above is empty, inspect changes on the current branch since the merge base with its source branch. Derive vocabulary work only from those changes. If ARGS is not empty, treat it as a concept, domain, path, or client surface and analyze that target.

Follow this procedure in order:

  1. Read docs/vocabulary/terms.json and docs/vocabulary/index.md.
  2. Query the code graph first with graphify query, graphify explain, or graphify path. If graphify is unavailable, fall through to grep and source reads without comment.
  3. Confirm every candidate fact in source. Record a file:line citation for each fact.
  4. Inspect related domains and every other client surface for the same concept.
  5. Classify each finding as a new term, alias, legacy name, rename, deprecation, or no-change.
  6. Update only facts confirmed in source. Never invent a term that is not present in source. Every entry must trace to a real symbol, contract, or user-visible surface.
  7. Run make generate-vocabulary, then make check-vocabulary.
  8. Surface unresolved decisions to the operator with a recommendation for each.

Hard rules

  • Never rename a code symbol, contract field, wire event, or public API as part of this command. Vocabulary registry changes are documentation-layer only. Report a needed code rename as a recommendation. It requires a separate explicit operator request.
  • Do not add an entry until its source fact is confirmed.
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. today Changed · -1 lines a15e9efd0b1a
  2. 5d ago First seen · 32 lines · 19 tokens per session scan A f1adf146fb98

Subscribe to this mod's changes

update-vocabulary is a command published in the GitHub repository dsswift/ion (4 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 404 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 2026-08-31.