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 OutlineDriven/odin-codex-plugin --skill ubiquitous-languagegit clone --depth 1 https://github.com/OutlineDriven/odin-codex-pluginWrote 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/outlinedriven/odin-codex-plugin/ubiquitous-language)<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/ubiquitous-language"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/ubiquitous-language.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.00742 |
| Opus 5 | $0.00030 | $0.00371 |
| Sonnet 5 | $0.00012 | $0.00148 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
ubiquitous-language 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ubiquitous-language — 95% identical, 1 lines differ
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mine the live conversation for domain-relevant nouns, verbs, and concepts; resolve synonyms and overloaded terms into a canonical, opinionated glossary. Persist the result to UBIQUITOUS_LANGUAGE.md so subsequent sessions inherit the same vocabulary. Re-invocation refines the file in place rather than overwriting.
When a candidate term collides with usage already present in the codebase, dispatch an Explore agent (fd-first discovery, git grep/ast-grep content search) to confirm the dominant naming before recommending a winner. The user supplies domain intent; the codebase supplies factual usage.
Modality vs adjacent skills: This skill extracts glossary from raw conversation when no documented domain language exists yet. Domain-model grilling grills a plan against an already-documented CONTEXT.md/ADRs. Pick ubiquitous-language when you are creating the artifact; pick the grilling workflow when you are stress-testing one. The two compose: build the glossary here, then promote stable terms into CONTEXT.md and let the grilling workflow defend it thereafter.
Process
- Scan the dialogue for domain-relevant nouns, verbs, and concepts. Skip generic programming nouns (array, function, endpoint) unless they carry domain weight.
- Identify three failure modes: same word for different concepts (ambiguity), different words for the same concept (synonyms), vague or overloaded terms.
- Propose canonical terms with explicit aliases-to-avoid. Be opinionated — pick one winner per concept and justify briefly.
- Persist
UBIQUITOUS_LANGUAGE.mdto the working directory using the format inreferences/UBIQUITOUS-LANGUAGE-FORMAT.md. - Emit a short inline summary of additions, renames, and flagged ambiguities so the user can react in-thread.
Rules
- One sentence per definition. Define what the term is, not what it does.
- Group terms into multiple tables when natural clusters exist (subdomain, lifecycle, actor). Force no grouping when a single cohesive table reads cleanly.
- Express relationships with bold term names and explicit cardinality where obvious (
exactly one,one or more,optional). - Flagged ambiguities require a recommendation, not a question. The skill resolves; the user overrides.
- Treat module and class identifiers as glossary candidates only when they carry domain meaning. Prefer abstract domain terms over implementation aliases.
- Include an example dialogue (3–5 exchanges) demonstrating the terms used precisely. The dialogue clarifies boundaries between adjacent concepts.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 41 lines · 59 tokens per session scan A 51d989c217e6
ubiquitous-language is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (15 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 742 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 2026-09-03.
Other skills, from other repositories
git-guardrails-claude-code
Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.
duet
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.
explore
Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Uses a staged 1/3/5 Explore-agent escalation protocol scaled to scope.…
deps-upgrade
Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings…
type-driven
Type-driven development. Use when developing with refined types, state machines encoded in types, or proof-carrying types; enforces totality and exhaustive pattern matching.
design-by-contract
Design-by-Contract (DbC) development. Use when implementing with formal preconditions, postconditions, and invariants across any language.