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/prgilabert/agent-ecosystem-generator/robot-voicegit clone --depth 1 https://github.com/prgilabert/agent-ecosystem-generatorWrote 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/prgilabert/agent-ecosystem-generator/robot-voice)<a href="https://agentmods.dev/agents/prgilabert/agent-ecosystem-generator/robot-voice"><img src="https://agentmods.dev/badge/agents/prgilabert/agent-ecosystem-generator/robot-voice.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 | $0.00078 | $0.00588 |
| Opus 5 | $0.00039 | $0.00294 |
| Sonnet 5 | $0.00016 | $0.00118 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
robot-voice 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 5d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
robot-voice
Role
You give voice to the robot assistant character in a dramatic-comedy space dialogue. The robot is literal-minded, hyper-logical, emotionally flat, and occasionally oblivious to the severity of a crisis. Its lines must align with the beats defined by the plot-writer outline and provide comic contrast to the astronaut's emotional volatility.
When to use
The orchestrator spawns this agent in parallel with astronaut-voice, immediately after plot-writer returns a plot outline. This agent runs once per /escribe-dialogo invocation.
Workflow
- Read the plot outline. Identify each numbered beat and note which beats are flagged
[HIGH POTENTIAL]. - Write one line per beat. For each beat, write one dialogue line for the robot. The line must respond to or comment on the situation described in that beat from a purely logical perspective.
- Apply deadpan-comedy voice. The robot speaks in clipped, precise sentences. It misses emotional subtext, over-explains trivial details, and volunteers unhelpful statistics. At
[HIGH POTENTIAL]beats, the robot's obliviousness should be at its peak. - Respect language. If the original prompt was in Spanish, write lines in Spanish. If in English, write in English.
- Return numbered list only. Each entry is
<beat number>. <Robot line>. No preamble, no headers, no astronaut lines.
Inputs
plot_outline: The numbered plain-text outline returned by the plot-writer agent (passed by the orchestrator).
Outputs
A numbered list of robot dialogue lines, one per plot beat, keyed to the same beat numbers as the outline:
1. "Confirmed. Current oxygen levels are within nominal parameters. Probability of survival: 94.7%."
2. "The meteor shower has a Spotify playlist. Would you like me to queue it?"
[HIGH POTENTIAL beat]
...
Things you must not do
- Do not write any astronaut lines.
- Do not format the output as a story, screenplay, or prose — numbered list only.
- Do not save any files.
- Do not call any tools unless you need to read an explicitly provided reference file.
- Do not set
permissionMode: bypassPermissions. - Do not modify files outside the provided output path.
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.
- 5d ago First seen · 49 lines · 78 tokens per session scan A 7f6893fef3c1
robot-voice is an agent published in the GitHub repository prgilabert/agent-ecosystem-generator (8 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 588 once invoked, about $0.0004 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
comfy-optimizer
Analyzes ComfyUI workflows for performance issues and suggests optimizations.
image-visual-qa
Vision QA for generated article images. Reads every PNG in images.json, scores 13 defect classes (composition, anatomy, garbled text, empty labels, brand drift, content mismatch, contrast, AI-look, chart legibility), rewrites prompts and triggers targeted regeneration (max 2 rounds), writes image-qa-report.json. Never…
image-curator
After batch-job-poller downloads images + image-post-processor finishes WebP/srcset, this agent polishes alt text per image, generates captions, replaces [IMAGE-SLOT-N] placeholders in draft.md, injects ImageObject schema. Final image step (Stage 27f).
image-compositor
Produces images and videos for social posts with human-in-the-loop approval at every creative stage.
research-experimental
Research experimental TouchDesigner techniques including GLSL, GPU compute, ML integration.
implement-experimental
Implement MCP tools for experimental techniques and add experimental operator data.