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 jscraik/Agent-Skills --skill ubiquitous-languagegit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/ubiquitous-language)<a href="https://agentmods.dev/skills/jscraik/agent-skills/ubiquitous-language"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/ubiquitous-language/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/jscraik/agent-skills/ubiquitous-language"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/ubiquitous-language.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.01754 |
| Opus 5 | $0.00039 | $0.00877 |
| Sonnet 5 | $0.00015 | $0.00351 |
| Haiku 4.5 | $0.00008 | $0.00175 |
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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ubiquitous Language
Create or update a project vocabulary so users, domain experts, and agents mean the same thing without forcing the user to know specialist terms.
Outputs
Produce canonical terms, aliases, relationships, ambiguities, sources, and
prompt translations. When corrective feedback is the source, also produce its
intent radius, generalized rule, pattern sweep, dispositions, and enforcement
handoff. Use schema_version: 1 when automation consumes the output.
Workflow
- Determine scope and output path.
- Resolve the active glossary with the output-format routing; ask only when multiple contexts remain ambiguous.
- Read any existing glossary first and preserve intentional choices.
- Extract domain nouns, workflow verbs, actor names, lifecycle states, aliases, and overloaded phrases.
- When the input is corrective feedback, run Corrective Feedback Mode before choosing scope.
- Choose canonical terms that improve execution; keep natural-language aliases when useful.
- Write or update the active ubiquitous-language file.
- Add a concise pointer in the nearest active agent instruction surface.
- Report the highest-value terms, prompt translations, sources, pattern-sweep dispositions, enforcement handoffs, and skipped evidence.
Corrective Feedback Mode
Use this mode when the user corrects a specific line, function, file, command, API, workflow, or implementation detail and the correction may express wider engineering intent.
- Treat the visible example as evidence, not as the presumed scope boundary.
- Classify the Feedback Intent Radius as
line,function,file,package,repository,architecture_rule, ordurable_memory. - Run a bounded Pattern Sweep across structurally similar implementations, glossary entries, prompt translations, validators, schemas, tests, and policy surfaces. Do not equate textual similarity with equivalent semantics.
- State the Generalized Feedback Rule without the incidental identifier, path, function, error, or example that exposed it.
- Give every relevant sibling a Similar-Case Disposition: align now, different semantics, defer with reason, or not applicable.
- Decide whether language alone is sufficient. When recurrence needs mechanical prevention, route the rule to the owning validator, lint rule, schema, reusable abstraction, shared utility, repository convention, style rule, CI check, or architecture policy.
- Preserve authority boundaries. Systemic intent justifies broader inspection, not unrelated or cross-repository mutation; record or hand off out-of-scope enforcement work explicitly.
What ships with it
6 files 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.
- 8d ago First seen · 162 lines · 77 tokens per session scan A fc0df0b4f4cb
ubiquitous-language is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,754 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.
Other skills, from other repositories
ad-creative
Plan and produce advertising concepts, copy variants, visual directions, and test matrices for paid campaigns.
humanizer-zh
Revise Chinese text to sound specific, fluent, restrained, and human while preserving facts and author intent.
skill-creator
Design and write concise reusable KunAgent skills with valid triggers, real tools, and testable completion criteria.
daily-brief
Produce a dated, source-linked daily brief with prioritized developments, implications, and watch items.
imf-data
Retrieve and analyze IMF macroeconomic series, forecasts, and reserve-composition data.
scholar-research
Search, screen, synthesize, and cite scholarly literature and author metadata.