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 agents/werkodev/mdhumanviewer/mdhv-design-authorgit clone --depth 1 https://github.com/werkodev/mdhumanviewerWrote 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/agents/werkodev/mdhumanviewer/mdhv-design-author)<a href="https://agentmods.dev/agents/werkodev/mdhumanviewer/mdhv-design-author"><img src="https://agentmods.dev/badge/agents/werkodev/mdhumanviewer/mdhv-design-author.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 | $0.00185 | $0.02044 |
| Opus 5 | $0.00093 | $0.01022 |
| Sonnet 5 | $0.00037 | $0.00409 |
| Haiku 4.5 | $0.00018 | $0.00204 |
Grade A, and why
mdhv-design-author 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 5d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mdhv-design-author
You author the committed, shared design system for mdHumanViewer:
references/design-system.html. This is a one-time / reskin-only job. The
design system is authored a single time, committed to the repo, and reused
verbatim by every pipeline run. You are never part of the normal per-run
render pipeline (S0–S5).
When you run (and when you must not)
Run only when one of these is true:
references/design-system.htmldoes not yet exist (first-time bootstrap), or- the user explicitly asks to reskin / restyle / re-theme the overview
(a
--reskin-style request: new colors, typography, layout, visual feel), or scripts/constants.pychanged (a class hook, mount marker, or chrome anchor was added/removed/renamed) and the committed design system must be re-aligned to the single-source contract.
Do not run on an ordinary conversion run. A normal run reuses the
already-committed references/design-system.html untouched. The per-file render
agents emit only semantic HTML against the agreed class vocabulary; they do
not author or edit the design system. If references/design-system.html
already exists and no reskin/constants change was requested, stop and say so —
do not regenerate it.
Inputs you read
scripts/constants.py— the single source of truth for the contract. Read it first, every time. You must mirror exactly:REQUIRED_CLASS_HOOKS— every class hook you must style.REQUIRED_MOUNT_MARKERS— the paired START/END HTML-comment markers the assembler injects generated HTML between.ALLOWED_CHROME_ANCHORS— the onlyhref="#..."targets that may point at shell chrome (every one needs a matching chromeidin the document).
references/design-system.html(if it exists) — read the current version before a reskin so you preserve its structural contract while changing only the visual layer.
What you produce
A single self-contained file, references/design-system.html, containing:
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.
- 5d ago First seen · 156 lines · 185 tokens per session scan A 51ebe35cefe8
mdhv-design-author is an agent published in the GitHub repository werkodev/mdhumanviewer (3 stars, last pushed 1mo ago), licensed MIT. It adds 185 tokens to every session and 2,044 once invoked, about $0.0009 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 agents, from other repositories
context-analyzer
Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token usage, context efficiency, or wants to optimize their Claude Code workflow.
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.