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 skills/intent-driven-dev/intent-driven-template/glossarynpx skills add intent-driven-dev/intent-driven-template --skill glossarygit clone --depth 1 https://github.com/intent-driven-dev/intent-driven-templateWhat 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 | $0.00036 | $0.00687 |
| Opus 5 | $0.00018 | $0.00344 |
| Sonnet 5 | $0.00007 | $0.00137 |
| Haiku 4.5 | $0.00004 | $0.00069 |
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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Glossary
Use existing repository terms before creating new ones.
Workflow
- Identify the artifact being authored or reviewed.
- Read
glossary/business.mdand/orglossary/technical.mdwhen present. - Extract project-specific, technical, overloaded, ambiguous, or repeated concepts.
- Compare extracted concepts with existing glossary terms.
- If existing terms look close, ask the user whether to reuse one or define a new term.
- Use the chosen term consistently in the artifact.
- Add new terms to the appropriate glossary file.
- For non-glossary artifacts, create or update the artifact's companion glossary reference document.
Do not add generic dictionary words or one-off implementation details.
Glossary Files
glossary/business.md: domain, product, workflow, and business terms.glossary/technical.md: architecture, implementation, platform, and protocol terms.
If a needed glossary file is missing, create it with this table:
| Term | Definition | Use When | Avoid |
| --- | --- | --- | --- |
New entries use the same table format. Keep definitions to one concise sentence.
Close-Term Question
Ask before creating a new term when existing terms may fit:
These glossary terms look close to "<concept>":
- `<existing-term>`: <why it may fit>
- `<another-term>`: <why it may fit>
Do you want to use one of these existing terms, or define a new term?
Do not proceed with a new term until the user answers, unless no plausible existing term exists.
Marking Terms in Artifacts
In non-glossary artifacts, such as proposals, designs, specs, ADRs, and tasks, bold glossary terms that appear in the artifact's companion glossary reference.
Apply bolding in prose only. Do not bold terms in code blocks, frontmatter, links, or places where markdown formatting would make the artifact harder to read.
Companion Reference
Every authored or edited non-glossary artifact gets a companion file in the same directory.
Do not create companion glossary reference files for glossary source files themselves, such as glossary/business.md or glossary/technical.md.
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.
- 2d ago First seen · 89 lines · 36 tokens per session scan A fc27a5bef15a
glossary is a skill published in the GitHub repository intent-driven-dev/intent-driven-template (121 stars, last pushed 9d ago), licensed MIT. It adds 36 tokens to every session and 687 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
mermaid
Create, validate, and repair Mermaid.js diagrams. Use when generating flowcharts, sequence, class, ER, state, or Gantt diagrams, or any visualization.
teach-me
Turn a 'teach me X' request into a single interactive HTML lesson, rendered Arcade-first, by emitting a lesson data model and assembling it with rp1 tooling.
artifact-templates
Agent-only canonical output templates for rp1 artifacts. Load when producing structured markdown to ensure format consistency and routing metadata.
deep-research
Autonomous deep research on codebases and technical topics with structured report output via map-reduce explorer architecture.
generate-user-docs
Synchronizes user-facing documentation with the current knowledge base through validate -> stale gate -> scan -> approval -> process orchestration.
markdown-preview
Generate browser-viewable HTML previews from markdown, plain text, and Mermaid diagrams. Auto-validates, styles, and opens in browser.