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 vshvedov/elephant-goldfish --skill eg-brainstormgit clone --depth 1 https://github.com/vshvedov/elephant-goldfishWrote 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/vshvedov/elephant-goldfish/eg-brainstorm)<a href="https://agentmods.dev/skills/vshvedov/elephant-goldfish/eg-brainstorm"><img src="https://agentmods.dev/badge/skills/vshvedov/elephant-goldfish/eg-brainstorm/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/skills/vshvedov/elephant-goldfish/eg-brainstorm"><img src="https://agentmods.dev/badge/skills/vshvedov/elephant-goldfish/eg-brainstorm.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 | $0.00019 | $0.00804 |
| Opus 5.5 | $0.00008 | $0.00322 |
| Sonnet 5.5 | $0.00004 | $0.00161 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
eg-brainstorm 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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EG Brainstorm Skill
Brainstorm a new concept using the elephant/goldfish workflow inverted: multiple fresh goldfish generate divergent ideas, then the elephant synthesizes.
Use the user's text around the $eg-brainstorm skill mention as the rough idea. If no idea is provided, ask for one.
Frame
Use Codex structured user input when available. Otherwise ask concise chat questions.
Ask:
- Stage: raw concept, hypothesis to validate, picking between options, or feature ideation for existing product.
- Breadth: about 5 deeper concepts, about 10 balanced concepts, or about 20 shallow concepts.
- Web research: broad, focused prior-art/market context, or off.
Seed
Print:
SEED
- The thought: <one sentence from the user's rough idea>
- What I think the user is really asking: <underlying need>
- Stage: <answer>
- Breadth target: <answer>
- Web research: <answer>
- Constraints inferred: <bullets>
- Success looks like: <one sentence>
- Out of scope: <bullets>
Ask whether the seed is right. If not, ask which field needs correction and revise before spawning goldfish.
Parallel Goldfish
The user invoked this skill, so parallel fresh subagents are explicitly authorized.
Pick 3-5 lenses:
- Technical / architectural
- Business / market
- User experience
- Contrarian / pre-mortem
- Market research / prior art
- Adjacent / lateral
- First principles
Spawn each as a fresh Codex subagent with fork_context: false and agent_type: "default". If web research is enabled, tell the goldfish to browse/search and cite sources. If a source requires logged-in browser access, the goldfish must ask the elephant to request user approval before navigating.
Each goldfish gets only:
You are a fresh creative thinker with no prior context. Your lens is <LENS NAME>. Stay in that lens.
SEED:
<PASTE SEED>
Generate <PER-LENS COUNT> distinct concepts. For each:
- Name
- The bet
- Why it could win
- Why it could fail
- Sources, if research was used
End with `lens complete`.
What ships with it
1 file 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.
- 1mo ago First seen · 126 lines · 19 tokens per session scan A 9de550629f6f
eg-brainstorm is a skill published in the GitHub repository vshvedov/elephant-goldfish (74 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 804 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
managing-mcp-servers
Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail runs pi in-process, so there is no pi command to call.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
output-standards
Use this skill when defining or enforcing output formatting standards for agent responses in WrongStack. Triggers: user says "next steps format", "output standard", "response format", "final message format", "standardize next steps".
web-platform-baseline
Use this skill before asserting that a CSS, HTML or accessibility capability is available, unavailable, or the right tool — it carries dated, refreshable platform facts and refuses to let stale knowledge be stated as current. Triggers: user says "container query", "can I use", "browser support", "modern CSS", ":has"…