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 ryne2010/harness-engineering-audit --skill visual-target-ingestgit clone --depth 1 https://github.com/ryne2010/harness-engineering-auditWrote 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/ryne2010/harness-engineering-audit/visual-target-ingest)<a href="https://agentmods.dev/skills/ryne2010/harness-engineering-audit/visual-target-ingest"><img src="https://agentmods.dev/badge/skills/ryne2010/harness-engineering-audit/visual-target-ingest/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/ryne2010/harness-engineering-audit/visual-target-ingest"><img src="https://agentmods.dev/badge/skills/ryne2010/harness-engineering-audit/visual-target-ingest.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 | $0.00036 | $0.00256 |
| Opus 5 | $0.00018 | $0.00128 |
| Sonnet 5 | $0.00007 | $0.00051 |
| Haiku 4.5 | $0.00004 | $0.00026 |
Grade A, and why
visual-target-ingest 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 7d 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
visual target ingest
Follow the repository source-of-truth docs. Treat generated images as design-intent evidence, not executable specifications. Do not implement app features, enable real-world effects, use real PII, or weaken tests/invariants.
Workflow
- Locate the relevant visual target pack and canonical product docs.
- For each target, record provenance, viewport, theme, route/surface, visual state, and linked user stories.
- Draft or update
screen.contract.yaml,interactions.yaml,motion.yaml, anddata-requirements.yamlwhere the repo uses those files. - Classify each behavior as
explicit,inferred, orunresolved; include confidence and evidence for inferred behavior. - Stop on unresolved destructive, security-sensitive, payment, auth, live-provider, or data-retention behavior.
- Update the product traceability matrix and list decisions that require approval.
Evidence
Report changed contract files, unresolved assumptions, approval-required inferences, and any visual targets that lack adjacent contracts.
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.
- 7d ago First seen · 22 lines · 36 tokens per session scan A b2c2e16c88a5
visual-target-ingest is a skill published in the GitHub repository ryne2010/harness-engineering-audit (5 stars, last pushed 8d ago), licensed MIT. It adds 36 tokens to every session and 256 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 2026-09-05.
Other skills, from other repositories
animated-readme-logo
Audit, create, transform, or animate verified logo pipelines for GitHub READMEs. Use when a repository needs a new or reconstructed mark, motion specification, SVG animation master, executable animation recipe, static PNG, animated GIF, README-safe markup, reduced-motion fallback, or compatibility review. Do not use…
drawio-diagrams
Create, draw, generate, edit, verify, and export draw.io/diagrams.net .drawio diagrams. Use when the user asks for editable diagrams, flowcharts, architecture, sequence, ER/UML/state, BPMN, SysML, ML/DL, swimlane, timeline, network, icon-rich technical diagrams, or PNG/SVG/PDF exports; do not use for charts/plots or…
create-codex-theme
Create, customize, validate, locally install, and test theme packs for Codex Desktop from generated background artwork, a landscape image, brand palette, or style brief. Use when a user asks to make a Codex theme, generate or convert artwork into a Codex background/theme pack, prepare free or branded theme assets…
fd
Frontend design mode for strong visual direction, UI polish, redesigns, landing pages, and production-grade interface work, including shadcn-based surfaces. Use when the user says /fd or explicitly asks for better design, styling, layout, visual quality, or UX polish.
manage-codex-theme
Install, list, switch, pause, resume, diagnose, visually verify, restore, or uninstall published and local release-candidate themes for Codex Desktop with the Get Codex Theme CLI. Use when a user asks to manage an existing Codex theme, test an exact local pack before publishing, troubleshoot why a theme is not active…
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…