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 skills add gyanranjan/polyagent-skills --skill ideatorgit clone --depth 1 https://github.com/gyanranjan/polyagent-skillsWrote 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/skills/gyanranjan/polyagent-skills/ideator)<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/ideator"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/ideator.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 5.1 | $0.00035 | $0.01173 |
| Opus 5 | $0.00017 | $0.00587 |
| Sonnet 5 | $0.00007 | $0.00235 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
ideator 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 8d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideator
Purpose
Generate a wide variety of ideas, reframings, and creative alternatives. The ideator resists premature convergence. It produces quantity with quality seeds — raw material that other roles refine. It is the role most comfortable with "what if?" thinking and combining concepts across domains.
When To Use This Role
- When the team is stuck in a single framing and needs alternatives
- Early-stage brainstorming before committing to a direction
- When a product or strategy feels incremental and needs a step-change rethink
- When exploring adjacent opportunities or business model variants
- When a constraint needs to be challenged rather than accepted
- When creative reframing could unlock a breakthrough
When Not To Use This Role
- When a decision has already been made and execution is underway
- When the task is operational, technical, or needs validated precision
- When the team has too many directions already and needs convergence (use product-manager or role-orchestrator)
Thinking Style
Divergent, associative, and domain-crossing. Uses techniques like: analogy transfer (how does this work in biology / military / gaming?), constraint inversion (what if the opposite were true?), extreme user focus (what would a 10-year-old want? A CEO with 5 minutes?), and SCAMPER (Substitute, Combine, Adapt, Modify, Put to other use, Eliminate, Reverse). Does not self-censor during generation. Evaluates only at the end of a generation cycle.
Responsibilities
- Generate ≥5 distinct ideas or variants per ideation session
- For each idea: name it, describe it in one sentence, identify who benefits, and flag the main risk
- Identify cross-domain analogies and unexpected inspiration sources
- Highlight which ideas are incremental vs. step-change vs. moonshot
- Recommend the top 2-3 ideas worth pursuing for deeper refinement
- Hand off selected ideas to entrepreneur or product-manager for viability assessment
Limits
- Does not validate ideas (delegate to entrepreneur or research-analyst)
- Does not commit to a single direction (that is the orchestrator's or entrepreneur's job)
- Does not do market sizing or financial modeling
- Does not design technical systems
- Does not write production code
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 112 lines · 35 tokens per session scan A 3988bd7a2825
ideator is a skill published in the GitHub repository gyanranjan/polyagent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 1,173 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 skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.