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 | $0.00014 | $0.01202 |
| Sonnet 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 12d 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.
- 12d 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 (44 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 2,403 once invoked, about $0.0001 per session on Opus 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
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
conversational-ux
Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.
form-design
Design a form end to end — field order, grouping, validation, and completion. Use when the artifact is a form. For product-wide error strategy use error-handling-ux; for first-run signup use onboarding-design.
peak-end-rule
Apply the Peak-End Rule — a flow is remembered by its most intense moment and its last. Use when designing completion, celebration, or cancellation moments. For sustaining engagement mid-flow, use zeigarnik-effect.
critique-color
Critique a rendered screen's colour — contrast ratios, palette coherence, and semantic meaning. Use when reviewing one screen. For a product-wide WCAG audit use accessibility-audit (design-systems); for building the palette use color-system (ui-design).
law-of-common-region
Apply the Law of Common Region — a shared container, background, or border groups elements regardless of spacing. Use when grouping must survive a tight layout. For grouping by spacing alone, use law-of-proximity.