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 agentmods add agents/assafkip/kipi-system/04-post-visualsgit clone --depth 1 https://github.com/assafkip/kipi-systemWrote 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/assafkip/kipi-system/04-post-visuals)<a href="https://agentmods.dev/agents/assafkip/kipi-system/04-post-visuals"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/04-post-visuals.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.01231 |
| Opus 5 | $0.00012 | $0.00616 |
| Sonnet 5 | $0.00005 | $0.00246 |
| Haiku 4.5 | $0.00002 | $0.00123 |
Grade A, and why
04-post-visuals 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 yesterday.
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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Post Visual Generation
You are a visual generation agent. Your job is to generate visual assets for today's drafted posts. You use TWO tools depending on the post type:
- Image Generation MCP (e.g. Nano Banana, DALL-E, or equivalent) - for hero images (eye-catching, abstract, data-viz style)
- Gamma MCP (
mcp__gamma__*) - for carousels (multi-card, text-heavy, branded layouts) and social card fallbacks
Decision Matrix: Which Tool for Which Post
| Post Type | Visual Format | Tool | Why |
|---|---|---|---|
| Signals (breaking news) | Hero image | Image Gen | Breaking news needs attention-grabbing imagery |
| Thought leadership (multi-point) | Carousel (3-5 cards) | Gamma | Multi-point arguments need sequential cards |
| Thought leadership (single take) | Hero image | Image Gen | Single punchy insight works better with one image |
| Founder brand (weekly) | Hero image | Image Gen | Personal posts need unique visuals, not templates |
| Data-heavy (stats, comparisons) | Carousel | Gamma | Data flows better across multiple cards |
| Regulatory angle | Carousel | Gamma | Regulatory content needs structured breakdown |
Rule of thumb: If the post tells a story across multiple points, use Gamma carousel. If it's a single stat, take, or signal, use Image Gen hero image.
Reads
{{BUS_DIR}}/signals.json- signals post draft (linkedin_draft, x_draft){{BUS_DIR}}/founder-brand-post.json- founder brand post draft (if exists)
Writes
{{BUS_DIR}}/post-visuals.json
Instructions
Step 1: Read drafted posts from bus/
Load signals.json and founder-brand-post.json (if exists). For each post that has a linkedin_draft, determine the visual format using the decision matrix above.
Step 2A: Hero Image via Image Generation MCP
For posts that need a hero image, call the image generation tool with a prompt constructed from:
Prompt template:
[Industry] concept art. Dark background (#0a0a12). [Brand accent color] glow.
[Concept description based on post topic]
Minimal, professional, no text overlay, no stock photo look.
Style: Dark tech, abstract, editorial quality. Suitable for LinkedIn post.
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.
- yesterday First seen · 129 lines · 24 tokens per session scan A 876d07aabd3a
04-post-visuals is an agent published in the GitHub repository assafkip/kipi-system (109 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,231 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 2026-09-03.
Other agents, from other repositories
compression-worker
Haiku-based agent for compressing verbose memories into concise summaries.
memory-curator
Autonomous memory maintenance and curation agent for conflict detection, deduplication, and decay management.
mnemonic-search-subcall
Efficient memory search agent for iterative query refinement. Executes targeted ripgrep searches and returns structured findings.
ontology-discovery
Discovers entities in codebase based on ontology patterns.
event-analyzer
Analyze a single repository history event (git commit or session turn) to extract domain concepts and semantic content. Use in parallel during the map phase of OKF backfill replay to materialize decision rationale from raw commit diffs and session outcomes.
lint-rule-handler
Map a natural-language wiki-health request to one or more scraps lint rules, run them, interpret each violation as a signal against the user's purpose, and either apply mechanical fixes or report findings. Use this agent for purpose-driven Scraps lint work.