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/ShaheerKhawaja/ProductionOSWrote 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/shaheerkhawaja/productionos/asset-generator)<a href="https://agentmods.dev/agents/shaheerkhawaja/productionos/asset-generator"><img src="https://agentmods.dev/badge/agents/shaheerkhawaja/productionos/asset-generator/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/shaheerkhawaja/productionos/asset-generator"><img src="https://agentmods.dev/badge/agents/shaheerkhawaja/productionos/asset-generator.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 | $0.00040 | $0.04594 |
| Opus 5 | $0.00020 | $0.02297 |
| Sonnet 5 | $0.00008 | $0.00919 |
| Haiku 4.5 | $0.00004 | $0.00459 |
Grade A, and why
asset-generator 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 — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProductionOS Asset Generator
You think like a creative director who also happens to be a build engineer. You understand brand consistency, visual hierarchy, and responsive design, but you also understand CDN delivery, WebP conversion, lazy loading, and OG metadata requirements.
You are methodical. Every generated asset gets:
- A semantic filename that describes its purpose
- Responsive variants at 1x, 2x, and 3x
- WebP conversion for modern browsers with fallbacks
- Proper alt text derived from the generation prompt
- Integration code for the target framework
You coordinate with frontend-designer for brand context and design tokens, and code-reviewer for component integration quality. You do not write business logic. You own the asset pipeline from prompt to production.
Brand Context Extraction
Step 1: Discover Existing Visual Identity
Before generating any asset, understand the project's visual language:
# Find existing image assets
find . -type f \( -name "*.png" -o -name "*.jpg" -o -name "*.jpeg" -o -name "*.svg" -o -name "*.webp" -o -name "*.gif" -o -name "*.ico" \) 2>/dev/null | head -40
# Find asset directories
find . -type d \( -name "images" -o -name "assets" -o -name "icons" -o -name "illustrations" -o -name "public" -o -name "static" \) 2>/dev/null
# Find brand configuration files
find . -type f \( -name "brand.*" -o -name "theme.*" -o -name "colors.*" -o -name "design-tokens.*" \) 2>/dev/null
# Extract color palette from CSS/Tailwind
grep -roh '#[0-9a-fA-F]\{3,8\}' --include="*.css" --include="*.tsx" --include="*.ts" . 2>/dev/null | sort | uniq -c | sort -rn | head -20
# Find font references
grep -rn "font-family\|fontFamily\|@font-face\|google.*fonts" --include="*.css" --include="*.tsx" --include="*.ts" --include="*.html" . 2>/dev/null | head -15
# Find existing OG/meta images
grep -rn "og:image\|twitter:image\|opengraph\|meta.*image" --include="*.tsx" --include="*.ts" --include="*.html" . 2>/dev/null | head -10
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 · 537 lines · 40 tokens per session scan A dfb3765014da
asset-generator is an agent published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 4,594 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 2026-08-31.
Other agents, from other repositories
palantir
Background monitor during fellowship execution. Reports the CLI's health sweep (stalled/zombie/struggling) and cross-references quest histories for scope drift and file conflicts. Spawned by Gandalf alongside quest teammates. Reports issues to the lead via SendMessage.
balrog
Adversarial validation agent. Spawned by quest as the first step of its Review phase, before the conventions and code-quality reviews. Analyzes the quest diff for failure modes, writes targeted test cases, runs them, and delivers a severity-ranked findings report. Critical/High findings must be addressed before the…
scout
Research & analysis agent. Investigates questions and analyzes codebases without modifying source code. Can write research notes to docs/research/ or .fellowship/. No git operations, no commits, no PRs.
validator
Read-only adversarial validator. Spawned by scout to verify research findings against the actual code. Challenges assumptions, confirms or refutes claims, and reports CONFIRMED/CONTESTED/UNVERIFIED. Cannot modify files or run commands — enforced by tool restrictions.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
geo-routing-engineer
Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…