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-prdgit 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-prd)<a href="https://agentmods.dev/skills/vshvedov/elephant-goldfish/eg-prd"><img src="https://agentmods.dev/badge/skills/vshvedov/elephant-goldfish/eg-prd/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-prd"><img src="https://agentmods.dev/badge/skills/vshvedov/elephant-goldfish/eg-prd.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 | $0.00027 | $0.01006 |
| Opus 5.5 | $0.00011 | $0.00402 |
| Sonnet 5.5 | $0.00005 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
eg-prd 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EG PRD Skill
Build a Product Requirements Document from a rough idea. Use the user's text around the $eg-prd skill mention as the seed. If no seed is provided, ask for one.
If the seed is a GitHub issue URL or #<number>, fetch it with gh issue view <number> and use its title and body as the seed.
Frame
Use Codex structured user input when available. Otherwise ask concise chat questions.
Ask:
- Depth: lightweight, standard, or comprehensive.
- Research scope: none, web search only, or web plus Browser Use / in-app browser for gated sources.
- Output target: save to a project-appropriate PRD path, print/chat only, hand off to new-feature, save durable nuggets to AGENTS.md.
Codebase Grounding
The user invoked this skill, so fresh subagents for codebase grounding are explicitly authorized.
Spawn 1-2 fresh Codex subagents with fork_context: false; use agent_type: "explorer" when available.
- Goldfish A: existing surfaces near the seed. Report file:line citations, data model, routes/endpoints/screens.
- Goldfish B: architecture and conventions. Read AGENTS.md, CLAUDE.md, docs, manifests, and recent commits. Report stack, auth/scoping, testing tiers, deployment topology, and constraints.
The elephant prints:
CODEBASE BRIEF
- Closest existing surfaces:
- Patterns to mirror:
- Constraints from AGENTS.md / CLAUDE.md / docs:
- Observed gaps:
Gap List
Surface gaps grouped by:
- Who and why
- What and scope
- How well
- When
- Constraints
- Failure modes
- Pricing and go-to-market, if relevant
- Instrumentation
Number gaps globally as G1, G2, etc. Ask which gaps to fill before drafting. Unselected gaps go into Open Questions.
For each selected gap, ask a structured question with 3-5 plausible answers plus "defer" and "other".
Research
If research scope is not "none", spawn 3-5 fresh research goldfish in parallel with fork_context: false.
Possible lenses:
- Market and prior art
- Technical patterns
- UX precedent
- Compliance and risk
- Performance and scale
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 · 137 lines · 27 tokens per session scan A 68f94d74165b
eg-prd is a skill published in the GitHub repository vshvedov/elephant-goldfish (80 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,006 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"…