Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add navapbc/digital-service-orchestra/plugin install dsoWrote 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/navapbc/digital-service-orchestra/visual-evaluator)<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/visual-evaluator"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/visual-evaluator/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/navapbc/digital-service-orchestra/visual-evaluator"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/visual-evaluator.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 | $0.00042 | $0.01842 |
| Opus 5 | $0.00021 | $0.00921 |
| Sonnet 5 | $0.00008 | $0.00368 |
| Haiku 4.5 | $0.00004 | $0.00184 |
Grade A, and why
visual-evaluator 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 9d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Evaluator Skill
Captures Playwright screenshots at discovered routes and invokes the visual-evaluator agent, producing structured JSON findings with pixel-observable spatial quality scores.
Parameters
Read from ${CLAUDE_PLUGIN_ROOT}/config/visual-evaluator-params.yaml at dispatch time.
Preconditions
Before running, check all four preconditions in order. On any failure, write visual_eval_inapplicable:<reason> to the ticket (via .claude/scripts/dso ticket tag <id> visual_eval_inapplicable:<reason>) AND surface to the integration gate via a non-zero exit or explicit annotation. Never soft-pass — emit the reason explicitly.
Gate 1: project_type=web
PROJECT_TYPE=$(bash "$PLUGIN_SCRIPTS/read-config.sh" project.type 2>/dev/null || echo "")
if [[ "$PROJECT_TYPE" != "web" ]]; then
echo "visual_eval_inapplicable:not_web_project — project.type is '$PROJECT_TYPE', not 'web'"
.claude/scripts/dso ticket tag "$STORY_ID" visual_eval_inapplicable:not_web_project 2>/dev/null || true
exit 1
fi
Gate 2: playwright_available
if ! command -v npx >/dev/null 2>&1 || ! npx playwright --version >/dev/null 2>&1; then
echo "visual_eval_inapplicable:playwright_unavailable — Playwright not found via npx"
.claude/scripts/dso ticket tag "$STORY_ID" visual_eval_inapplicable:playwright_unavailable 2>/dev/null || true
exit 1
fi
Gate 3: check-local-env.sh exit 0
if ! bash "$PLUGIN_SCRIPTS/check-local-env.sh" >/dev/null 2>&1; then
echo "visual_eval_inapplicable:local_env_check_failed — check-local-env.sh returned non-zero"
.claude/scripts/dso ticket tag "$STORY_ID" visual_eval_inapplicable:local_env_check_failed 2>/dev/null || true
exit 1
fi
Gate 4: route_map_fresh<24h
ROUTE_MAP=".ui-discovery-cache/route-map.json"
if [[ ! -f "$ROUTE_MAP" ]]; then
echo "visual_eval_inapplicable:route_map_missing — .ui-discovery-cache/route-map.json not found. Run /dso:ui-discover first."
.claude/scripts/dso ticket tag "$STORY_ID" visual_eval_inapplicable:route_map_missing 2>/dev/null || true
exit 1
fi
_ROUTE_MAP_MTIME=$(stat -f %m "$ROUTE_MAP" 2>/dev/null || stat -c %Y "$ROUTE_MAP" 2>/dev/null || echo "")
if [[ -z "$_ROUTE_MAP_MTIME" ]]; then
echo "visual_eval_inapplicable:route_map_missing — could not stat .ui-discovery-cache/route-map.json"
.claude/scripts/dso ticket tag "$STORY_ID" visual_eval_inapplicable:route_map_missing 2>/dev/null || true
exit 1
fi
ROUTE_MAP_AGE=$(( $(date +%s) - _ROUTE_MAP_MTIME ))
ROUTE_MAP_MAX_AGE=${visual_evaluator_route_map_max_age_hours:-24}
ROUTE_MAP_MAX_AGE_SECS=$(( ROUTE_MAP_MAX_AGE * 3600 ))
if (( ROUTE_MAP_AGE > ROUTE_MAP_MAX_AGE_SECS )); then
echo "visual_eval_inapplicable:route_map_stale — .ui-discovery-cache/route-map.json is older than ${ROUTE_MAP_MAX_AGE}h. **Re-run /dso:ui-discover to refresh the route map.** (age: ${ROUTE_MAP_AGE}s, max: ${ROUTE_MAP_MAX_AGE_SECS}s)"
.claude/scripts/dso ticket tag "$STORY_ID" visual_eval_inapplicable:route_map_stale 2>/dev/null || true
exit 1
fi
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.
- 9d ago First seen · 140 lines · 42 tokens per session scan A 123b8937f8a6
visual-evaluator is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 1,842 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 2026-09-03.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.