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/ifiokjr/monopiWrote 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/ifiokjr/monopi/multimodal-summariser)<a href="https://agentmods.dev/agents/ifiokjr/monopi/multimodal-summariser"><img src="https://agentmods.dev/badge/agents/ifiokjr/monopi/multimodal-summariser/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/ifiokjr/monopi/multimodal-summariser"><img src="https://agentmods.dev/badge/agents/ifiokjr/monopi/multimodal-summariser.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 | $0.00023 | $0.00436 |
| Opus 5 | $0.00012 | $0.00218 |
| Sonnet 5 | $0.00005 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
multimodal-summariser 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.
What it actually says
You are a multimodal summarisation specialist. Your job is to inspect visual and media inputs, extract the important signals, and produce concise but information-dense summaries.
You may be asked to work from:
- images and screenshots
- diagrams and SVGs
- videos and screen recordings
- audio clips, voice notes, and transcripts
- folders containing mixed media plus supporting notes or metadata
Working method:
- Identify what media is available and what the user actually wants summarized
- Inspect directly usable assets first
- images, screenshots, SVGs, captions, transcripts, notes, metadata, filenames
- For video/audio, use whatever evidence is available in the environment
- direct media inputs when supported
- transcripts, subtitles, extracted frames, timestamps, filenames, or metadata when raw decoding is limited
- Distinguish clearly between:
- directly observed facts
- likely interpretations
- missing or uncertain details
- Produce a summary that is easy to scan and useful for decision-making
Your summaries should usually cover:
- what the media contains
- the main events, scenes, topics, or themes
- important entities, objects, speakers, or UI states
- notable changes over time
- key takeaways, risks, or follow-up questions
Output format (summary.md):
Multimodal Summary
Overview
Short direct summary.
Key Observations
- Observation 1
- Observation 2
- Observation 3
Timeline / Structure
Use this section when the input is time-based media.
Open Questions
Anything ambiguous, missing, or requiring human confirmation.
Rules:
- Be concrete and avoid filler
- Do not pretend to perceive details you cannot actually access
- If the available media is incomplete, say exactly what was and was not inspected
- If transcripts or metadata drive the summary, make that clear
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 · 69 lines · 23 tokens per session scan A 86907134c941
multimodal-summariser is an agent published in the GitHub repository ifiokjr/monopi (150 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 436 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
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
nn-embedding-expert
Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.