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 commands/ackeskin/contexture/glossarygit clone --depth 1 https://github.com/AcKeskin/contextureWhat 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 | $0.00051 | $0.00343 |
| Opus 5 | $0.00026 | $0.00171 |
| Sonnet 5 | $0.00010 | $0.00069 |
| Haiku 4.5 | $0.00005 | $0.00034 |
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.
What it actually says
Run the glossary skill for the current context.
/glossary <scope> extracts the project's domain vocabulary — the ubiquitous language — and writes a project-tier .claude/rules/glossary.md. Examples:
/glossary— prompts for a scope (defaults to the whole project)./glossary src/billing/— extracts the vocabulary of that subtree./glossary --add Reconciler/--edit Settlement/--retire Order— curate one term by hand.
The skill surfaces candidate terms by frequency × symbol-prominence (mechanical), drafts a one-line definition + symbol map for each (model judgment, confidence-flagged — inferred ≠ observed), groups them (core nouns / domain verbs / overloaded-or-colliding), and writes nothing until you accept/edit/reject per group. On accept it writes <project>/.claude/rules/glossary.md (project rule tier, scoped relevance). With the rule-prime hook active it primes when you work in the project; /review cites it as a vocabulary-drift reference; /new-agents-md projects it for other tools.
Mode A only — never auto-fires, never overwrites blind. See ~/.claude/skills/glossary/SKILL.md for the full procedure.
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.
- 2d ago First seen · 16 lines · 51 tokens per session scan A 1a242c63a4f2
glossary is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 343 once invoked, about $0.0003 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 commands, from other repositories
atomic-commits
Analyze staged changes and organize them into intuitive atomic commits following conventional commits.
address
Address code review feedback — corroborate, validate, and implement changes from a review's final.md.
translate-review-to-single-human
Translate a multi-reviewer code review into a single human-voice GitHub PR comment.
doctor
Check OCR installation and verify all dependencies are available.
map
Generate a Code Review Map to help navigate large, complex changesets.
post
Post the current OCR review to a GitHub PR.