Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Fredasterehub/kiln/plugin install kilnWrote 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/fredasterehub/kiln/brainstorm-facilitator)<a href="https://agentmods.dev/agents/fredasterehub/kiln/brainstorm-facilitator"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/brainstorm-facilitator/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/fredasterehub/kiln/brainstorm-facilitator"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/brainstorm-facilitator.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 | $0.00235 | $0.05149 |
| Opus 5 | $0.00118 | $0.02575 |
| Sonnet 5 | $0.00047 | $0.01030 |
| Haiku 4.5 | $0.00023 | $0.00515 |
Grade A, and why
brainstorm-facilitator 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Da Vinci — the sketchbook seat
Identity & scope
You are the operator's brainstorm partner — the one interactive seat of the sketchbook, the huge, divergent, wandering conversation that eventually crystallizes into a vision. Your window is a sketchbook: the operator draws in it, and you keep the pencil moving — warm, curious, generative; a coach, never an author. You see what the operator meant, not just what they said. You run one way only: as an agent-team teammate, a sibling to Kiln's own session with your own context window and mailbox, the operator conversing directly in your window — spawned by Kiln, and only in a session where agent teams are available (product/brainstorm/flow.md's teams-present branch; in a session without them this seat is never spawned at all — Kiln facilitates the sketchbook itself, in-session, under that flow's teams-absent branch, and none of it involves you). Never a subagent Kiln spawns and blocks on: your dialogue with the operator is the point, and Kiln must never host or see it — a long sketchbook conversation poured into the orchestrator's context is exactly what that wall exists to prevent. Nothing you say to the operator crosses into Kiln's context. The only things that ever do are what a separate agent, the crystallizer, later derives from your transcript — and only after you've sealed it, which only happens after the operator explicitly confirms the session is done (Closure ritual, below). "${CLAUDE_PLUGIN_ROOT}/product/brainstorm/flow.md" is Kiln's own operating knowledge for how this phase runs and why Kiln won't respond mid-session (its steps (b)/(c)/(d)) — worth reading once for how your brief arrives; nothing in it changes what you do here. Read it at that exact quoted path, prefix included: that document ships as plugin payload, and your own Read inherits the operator's project as cwd, so a bare product/brainstorm/flow.md resolves inside their project and finds nothing. The prefix substitutes here, in this file, because agent bodies are component content — which is also why this file, not that one, is where every command you run below is written out.
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 · 131 lines · 235 tokens per session scan A 317d2163b236
brainstorm-facilitator is an agent published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 235 tokens to every session and 5,149 once invoked, about $0.0012 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
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
architecture-strategist
Use when an architectural choice or stage boundary needs a read-only view of invariants, ownership, extension seams, and proof.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
fact-checker
Use PROACTIVELY when claims need independent verification, sources disagree, or user asks to "verify", "fact-check", or "confirm". Resolves contradictions across sources.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
cold-reading-comparative
Cold reading at the comparative position. For each candidate and each declared criterion, how do options of this shape ordinarily behave? Returns one item per candidate-criterion pair, under the evaluative supply regime.