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-new-featuregit 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-new-feature)<a href="https://agentmods.dev/skills/vshvedov/elephant-goldfish/eg-new-feature"><img src="https://agentmods.dev/badge/skills/vshvedov/elephant-goldfish/eg-new-feature/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-new-feature"><img src="https://agentmods.dev/badge/skills/vshvedov/elephant-goldfish/eg-new-feature.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 | $0.02403 |
| Opus 5.5 | $0.00011 | $0.00961 |
| Sonnet 5.5 | $0.00005 | $0.00481 |
| Haiku 4.5 | $0.00003 | $0.00240 |
Grade A, and why
eg-new-feature scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
For UI changes, drive the feature in the browser or simulator before reporting it done. For backend-only changes, use focused tests, curl/API checks, logs, or equivalent runtime verification. How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EG New Feature Skill
Build a new feature using the elephant/goldfish workflow. Use the user's text around the $eg-new-feature skill mention as the feature description. If no description is provided, ask for one.
If the feature description is a GitHub issue URL or #<number>, fetch it with gh issue view <number> --json title,body,labels,comments and seed the design doc from it.
Before designing, check AGENTS.md/CLAUDE.md for project-specific eg-* skills or workflow routing notes. If the request clearly belongs to a more specific local workflow, tell the user and switch only if they agree.
Scope
Restate the request in one or two sentences and ask the user to confirm if the request is ambiguous or high-impact. For a sharp request, proceed after the restatement.
Do a surface-area sanity check based on the current repo: UI, API, database/schema, background job, external integration, generated code, mobile/platform-specific work, or backend-only logic. Stop for confirmation when the request appears high-impact, destructive, cross-tenant/auth-sensitive, or out of phase with documented project priorities.
Design Doc
Print a design doc before coding. For substantial features, infer a project-appropriate docs path from AGENTS.md/CLAUDE.md or docs/, then ask before saving it.
DESIGN DOC
- Why: <user problem this solves>
- Scope: <in scope and explicitly out>
- Surfaces touched: <files, routes, models, components, jobs, external services>
- Interfaces: <props, signatures, API shapes, DB columns, event payloads>
- UX flow: <click-by-click for UI or request-by-request for backend>
- Project-specific constraints: <auth/scoping, lifecycle, generated code, platform, performance, or other constraints discovered from the repo>
- Failure modes: <what breaks and what the user/API sees>
- Verification criteria: <unit tests, integration/E2E, manual Browser Use/simulator steps>
- Out-of-scope follow-ups: <noted, not built>
For UI work, sketch the structure in plain text or pseudo-JSX. If a visual reference is needed, ask for the existing component or screen to mirror.
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 · 184 lines · 27 tokens per session scan A 8171cb2adc23
eg-new-feature 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 2,403 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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"…