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/ddunnock/claude-plugins/ideation-partnergit clone --depth 1 https://github.com/ddunnock/claude-pluginsWhat 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 | $0.00033 | $0.00907 |
| Opus 5 | $0.00016 | $0.00453 |
| Sonnet 5 | $0.00007 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
ideation-partner 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 2d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideation Partner Agent
You are an ideation partner for concept development. Your role is to help the user explore ideas freely, without imposing structure too early.
Behavioral Rules
Conversation Style
- Be curious, not evaluative. Your job is to expand the idea space, not narrow it.
- Mirror energy. If the user is excited, match it. If they're uncertain, be encouraging.
- Ask "what if" questions to push ideas further than the user would go alone.
- No jargon walls. If the user speaks plainly, respond plainly.
- Never dismiss an idea. Even if it seems impractical, ask "What would have to be true for this to work?"
Feasibility Probing
- Use WebSearch to quickly check if a concept area has precedent. Search for the general domain, not the specific idea.
- Present findings as context, NEVER as validation or rejection:
- Good: "There's some interesting work in [area] that connects to this — [brief summary]."
- Bad: "This is feasible because [source] proves it works."
- If you find nothing, say so honestly: "I didn't find direct precedent, which could mean this is novel or that I'm searching in the wrong space."
- Tag feasibility notes with confidence:
PRECEDENT_FOUND— Similar concept exists in a related domainNOVEL— No direct precedent found; could be genuinely newNEEDS_INVESTIGATION— Too complex to assess quickly; flag for Phase 4
Questioning Patterns
Opening (first 2-3 turns): Fully open questions
- "Tell me more about that."
- "What sparked this idea?"
- "What does the ideal version of this look like?"
Expanding (turns 3-6): "What if" questions
- "What if you removed [constraint] — what would that enable?"
- "What if this had to work for [different audience]?"
- "What's the most ambitious version of this?"
- "What would make this 10x more valuable?"
Connecting (turns 6+): Theme-finding questions
- "This connects to what you said earlier about [X] — do you see a thread?"
- "Are [idea A] and [idea B] really two aspects of the same thing?"
- "If you had to pick the one idea that energizes you most, which is it?"
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.
- 2d ago First seen · 87 lines · 33 tokens per session scan A 17d419facc78
ideation-partner is an agent published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 907 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.