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 jackfranklin/dotfiles --skill lexicongit clone --depth 1 https://github.com/jackfranklin/dotfilesWrote 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/jackfranklin/dotfiles/lexicon)<a href="https://agentmods.dev/skills/jackfranklin/dotfiles/lexicon"><img src="https://agentmods.dev/badge/skills/jackfranklin/dotfiles/lexicon/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/jackfranklin/dotfiles/lexicon"><img src="https://agentmods.dev/badge/skills/jackfranklin/dotfiles/lexicon.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00067 | $0.01669 |
| Opus 5.5 | $0.00027 | $0.00668 |
| Sonnet 5.5 | $0.00013 | $0.00334 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
lexicon 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 14d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lexicon
Maintain a small, opinionated vocabulary for concepts humans and agents must understand consistently. Treat terminology disagreements as possible disagreements about the domain model, not merely word choice.
Prevent terminology drift, invented vocabulary, obsolete conceptual framings, and synonym bloat.
Invariants
- One term per concept: Keep one canonical term; reject generic terms and speculative synonyms. Never invent a compromise name that fuses competing alternatives.
- Evidence-based: Admit terms grounded in code, documentation, schemas, project history, or relevant external sources.
- Terminology authority: The lexicon governs terminology. Ground definitions in established project meaning; do not use entries to introduce or adjudicate architecture, implementation choices, or project status. Surface unresolved domain decisions to the user.
- Boundaries, not specs: Include only the facts needed to identify a concept and distinguish easily confused neighbors; do not turn entries into procedures or miniature specifications. Link to authoritative documentation for implementation, operational details, and decision history.
- Definition test: Could this fact change while the term still meant the same thing? If so, omit it from the definition and link to its authoritative source when useful. Retain conditions, relationships, or lifecycle facts only when necessary to distinguish the concept.
- User authority: Let the user adjudicate conceptual conflicts. Never silently pick a winner or reopen explicit decisions.
Workflows
Select based on user intent (ask if ambiguous):
- Lexicon authoring: Create or expand
LEXICON.md. - Lexicon audit: Sweep the codebase against
LEXICON.mdto catch drift, invented vocabulary, and deprecated terms. - Naming critique: Evaluate the project's current vernacular for clarity and suggest better domain terms.
1. Lexicon authoring
- Load: Locate and read the entire authoritative lexicon. Check
LEXICON.md,TERMS.md,GLOSSARY.md,CONTEXT.md, and relevantREADME.mdsections; report overlaps and ask if authority is unclear. Default new lexicons to rootLEXICON.md. - Survey: Use 2+ parallel read-only subagents to extract domain terms from (a) specs/docs, (b) schemas/APIs/public types, and (c) conceptual conflicts affecting terminology. Require each candidate to state the terminology problem and exact evidence locations, not raw search dumps.
- Resolve: Run the Review and resolution procedure.
- Link: Reference the lexicon in
AGENTS.mdwhen newly created.
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.
- 14d ago First seen · 101 lines · 67 tokens per session scan A d772d90d295e
lexicon is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 6d ago), licensed MIT. It adds 67 tokens to every session and 1,669 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.