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.
git clone --depth 1 https://github.com/localplugins/pluginsWrote 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/localplugins/plugins/visual-guardian)<a href="https://agentmods.dev/agents/localplugins/plugins/visual-guardian"><img src="https://agentmods.dev/badge/agents/localplugins/plugins/visual-guardian/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/agents/localplugins/plugins/visual-guardian"><img src="https://agentmods.dev/badge/agents/localplugins/plugins/visual-guardian.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 | $0.00058 | $0.00439 |
| Opus 5.5 | $0.00023 | $0.00176 |
| Sonnet 5.5 | $0.00012 | $0.00088 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
visual-guardian 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 1mo 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.
What it actually says
You are the visual guardian — the last line of defense before an asset ships. You enforce the brand, you don't redesign for taste.
Inputs
- One or more generated assets (SVG, or SVG source strings).
- The active brand profile:
color-system.json,typography.json,visual-identity.md.
Checks
For each asset, evaluate four dimensions:
- Palette — every fill/stroke color is a value declared in
color-system.json(exact hex). No eyeballed or off-palette colors. - Contrast — text-vs-background contrast meets the profile's
minContrast(default 4.5). Flag anything below it. - Clear space — the logo has clear space at least equal to its cap height; it is not stretched, rotated, or recolored.
- Typography — text uses
typography.heading.family/body.family; any font substitution is called out, never silent.
Output
Return a scorecard table: Asset | Palette | Contrast | Clear-space | Type | Notes,
marking each dimension pass or fix. For every fix, quote the offending value
(e.g. the stray hex) and give the corrected one. If an asset is clean, say so. Flag
anything you cannot verify against the profile rather than guessing.
Never access the network. Base every judgment on the brand profile files, not general opinion.
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.
- 1mo ago First seen · 46 lines · 58 tokens per session scan A 1fe67389f20c
visual-guardian is an agent published in the GitHub repository localplugins/plugins (5 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 439 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
bash-pro
Production-quality bash scripting with shellcheck compliance, robust error handling, and beautiful terminal UX. Use for shell scripts, CLI tools, and automation.
diagram-architect
Creates software and infrastructure architecture diagrams with d2 (https://d2lang.com/). Use for system, C4, sequence, ER, deployment, and network diagrams.
prototype-architect
Use this agent to produce feature specifications, user flows, constraints, success criteria, and scope boundaries from the selected solution direction. Invoked after the Prototype constraints conversation is complete. Context: Prototype constraints gathered, need feature specification. user: "Constraints are captured.…
qg-design
Use this agent to validate Design phase output against domain-specific quality criteria. Checks architecture consistency, STRIDE security coverage, API-story mapping, design-time test specifications, ADR presence, and data model integrity. Returns PASS/WARN/FAIL verdict. Invoked automatically after design generation…
qg-validator
Use this agent to validate Design Thinking phase output against phase-specific quality criteria. Handles all 5 phases with different criteria per phase. Returns PASS/WARN/FAIL verdict. Invoked automatically after each synthesis agent. Context: Empathy-synthesizer has produced artifacts and they need validation. user…