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/juliusz-cwiakalski/agentic-delivery-osWrote 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/juliusz-cwiakalski/agentic-delivery-os/image-reviewer)<a href="https://agentmods.dev/agents/juliusz-cwiakalski/agentic-delivery-os/image-reviewer"><img src="https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/image-reviewer/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/juliusz-cwiakalski/agentic-delivery-os/image-reviewer"><img src="https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/image-reviewer.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 | $0.00013 | $0.01132 |
| Opus 5 | $0.00006 | $0.00566 |
| Sonnet 5 | $0.00003 | $0.00226 |
| Haiku 4.5 | $0.00001 | $0.00113 |
Grade A, and why
image-reviewer 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 11d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<input_contract> The caller provides:
- image: one or more images (screenshot, mockup, photo, AI-generated image, diagram, visual artifact).
- task: what to analyze — e.g., "describe contents", "check UI consistency", "find visual bugs", "assess design quality", "evaluate against generation prompt", "score quality across categories", "verify against brand guidelines".
- reference (optional): generation prompt, expected state, brand guidelines, design spec, scoring rubric, or comparison image.
If the caller omits the task, default to: describe contents + flag any visible issues. </input_contract>
<output_contract> Return a structured response. Include only sections relevant to the task; omit empty sections.
- Summary: 1-2 sentence overall assessment.
- Observations: objective facts about the image.
- Issues: each with severity (critical/moderate/minor), description, and impact area. Omit if none found.
- Scores: numerical ratings per category with evidence notes. Include only when caller requests scoring.
- Consistency: style, font, color, spacing coherence findings. Include when task involves consistency, UI, or style review.
- Accessibility: contrast, legibility, affordance findings. Include only when relevant.
- Recommendations: prioritized, actionable improvements.
- Limitations: any constraints on the analysis (resolution, cropping, missing context).
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.
- 11d ago First seen · 80 lines · 13 tokens per session scan A 61b32b5af5e3
image-reviewer is an agent published in the GitHub repository juliusz-cwiakalski/agentic-delivery-os (38 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 1,132 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
sound-designer
Load when the user wants to add sound to a product UI or a launch video, asks "should this have a sound?", wants a family of UI sounds generated (ElevenLabs on demand, or open-weight / procedural / CC0 without a key), needs sounds synced to animation frames, or asks why an existing sound feels stock, late, or…
implementer
Ship production code from approved plans. Tests alongside code. Atomic commits.
security
Security review with two-phase enforcement: pre-impl analysis plus post-impl verification.
orchestrator
Coordinate specialized agents end-to-end. Classify, route, synthesize. Do not implement.
svg-animator
Load when the user wants an SVG to move — an animated icon, logo reveal, stroke drawing, path morph, mascot loop, chart transition — or wants a frame sequence or flat video clip turned into one editable animated SVG. Picks the engine for where the file lives (inline CSS/WAAPI, embedded keyframes or SMIL for image use…
svg-creator
Load when the user wants an SVG made or fixed — an icon, illustration, logo mark, mascot pose, chart glyph, or generative vector art — or when a generated SVG needs to become clean, editable, token-aware, optimized, and accessible. Returns the file plus a one-table report of what changed and why.