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 donald-ada/workinggenius --skill domain-glossarygit clone --depth 1 https://github.com/donald-ada/workinggeniusWrote 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/donald-ada/workinggenius/domain-glossary)<a href="https://agentmods.dev/skills/donald-ada/workinggenius/domain-glossary"><img src="https://agentmods.dev/badge/skills/donald-ada/workinggenius/domain-glossary/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/donald-ada/workinggenius/domain-glossary"><img src="https://agentmods.dev/badge/skills/donald-ada/workinggenius/domain-glossary.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 | $0.00057 | $0.00788 |
| Opus 5 | $0.00028 | $0.00394 |
| Sonnet 5 | $0.00011 | $0.00158 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
domain-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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Glossary
One shared language between the user, the agent and the code — Domain-Driven Design's ubiquitous language — living in CONTEXT.md at the repo root: a glossary and nothing else. A term sharpened during one piece of work serves every later one: shorter conversations, consistent naming in code and tests.
Format
# {Project Name}
{One or two sentences on what this project is.}
## Language
**customer**:
{One or two sentences. What it IS, not what it does.}
Killed: *client*, *buyer* — one concept, one word.
**archive**:
Soft-hide; the user can restore it. Settled against permanent deletion in the
exports work — restorability is a support contract.
Killed: *trash*, *delete* — each carried both meanings at once.
- Be opinionated. When several words name one concept, pick the best and name the losers as killed — with what killed them where there was a real fight.
- A fought term keeps its fight. A term that collided carries the collision in one line: what collided, which won, why. A resolution recorded without its collision gets re-litigated.
- Published API names outrank opinion. A misleading name that's public API can't be renamed — define it against its general meaning instead ("not actually a cryptographic salt; the name is API, the definition rules").
- Tight definitions, one or two sentences, of what it is. Project concepts only — general programming concepts don't belong. No implementation details: not a spec, a scratchpad or a decision log — decisions live in their work file, indexed in
.genius/DECIDED.md. - Create lazily, at the first resolved term. Don't hijack: an existing
CONTEXT.mdwith other content keeps it; append the## Languagesection and stay scoped to it.
The discipline
While any conversation is shaping work:
- Collide words with the glossary. The user's term conflicts with an entry → stop and hold the two meanings up side by side: "The glossary says an archived account is restorable, but you're describing permanent deletion — which do you mean?" No building on a word that means two things at once.
- Sharpen fuzzy terms. One word doing two jobs → propose a precise canonical term for each.
- Collide claims with the code. The user says how something works; the code disagrees → surface the contradiction.
- Update inline. The moment a term resolves, write it — not batched at the end. A resolution that isn't written down will be re-litigated.
- The flow's own names get one rendering in the project's language. Where records are written in a language other than English, slice, snapshot, contract, seam, kill-reason, assumed, backlog and the six stage names are terms like any other: rendered differently at each writing they become several words for one concept. Record each once under
## Language, the first time a record is written in that language (setup-working-geniusoffers it), and every record uses that rendering (record-proseskill).
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 Changed · -7 lines 57951d0d98ee
- 5d ago Changed · +1 lines ec322dc4272c
- 10d ago First seen · 52 lines · 57 tokens per session scan A 9f9f4ae74c01
domain-glossary is a skill published in the GitHub repository donald-ada/workinggenius (6 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 788 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 skills, from other repositories
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.
grill
Interrogate a plan or decision one question at a time before capture, keeping a decision-plus-rationale ledger, then route to the right capture skill.
daily-working
End-to-end pipeline: pull a task from the project's task tracker by ID (Redmine or GitHub Issues today, more addable via a new adapter), sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension…
work
Dispatch a tracker ticket into an isolated worktree and drive it autonomously to an open pull request, then stop for review. Pass interactive to brainstorm the ticket with a human before planning it, or a sentence of editorial direction as a rider. Use when asked to work a ticket end-to-end.
batch
Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.