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 agentmods add skills/ytvee-dev/webdev-agent-kit/goal-plannernpx skills add ytvee-dev/webdev-agent-kit --skill goal-plannergit clone --depth 1 https://github.com/ytvee-dev/webdev-agent-kitWhat 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 | $0.00040 | $0.01882 |
| Opus 5 | $0.00020 | $0.00941 |
| Sonnet 5 | $0.00008 | $0.00376 |
| Haiku 4.5 | $0.00004 | $0.00188 |
Grade A, and why
goal-planner 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 2d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Planner
Purpose
Create a clear goal contract for standard or deep frontend work before implementation begins.
This skill exists to prevent ambiguous or large requests from turning into unfocused coding. It defines what the user wants, what is in scope, what is out of scope, which constraints apply, and what observable conditions mean the task is done.
When To Use
Use this skill only after AGENTS.md and common/prompt-intent-routing-rules.md classify the task as Standard Workflow or Deep Workflow.
Use this skill when:
- the user asks for a multi-file feature;
- the user asks for a new screen, flow, or frontend capability;
- the user asks for architecture, greenfield project creation, or broad redesign;
- the request is ambiguous enough that implementation would require guessing the goal;
- the task needs a compact goal before execution planning;
- the task needs a durable goal contract because work may span multiple slices.
When Not To Use
Do not use this skill for Lightweight Workflow prompts, including:
- one small bug;
- one obvious typo;
- one obvious type error;
- one small styling adjustment;
- one isolated component change;
- one direct file-scope edit;
- one local refactor with clear boundaries.
Do not use this skill to implement code, install tools, scaffold projects, rewrite architecture, or perform visual QA.
If a lightweight task reveals hidden scope, escalate first using common/prompt-intent-routing-rules.md, then use this skill only if the escalated task is standard or deep.
Required Context
- Read
AGENTS.md. - Read
common/prompt-intent-routing-rules.mdwhen task scale is not obvious. - Read
common/goal-contract.md. - Confirm the workflow level is
Standard WorkfloworDeep Workflow. - Read only project overlays that are needed to understand the goal boundary, such as
project/stack-profile.md,project/architecture-map.md, orproject/design-reference-profile.md. - Read affected source files only when the goal cannot be stated without them.
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.
- 2d ago First seen · 211 lines · 40 tokens per session scan A 2e982a337f5d
goal-planner is a skill published in the GitHub repository ytvee-dev/webdev-agent-kit (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,882 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
shipping-reproducible-results
Package completed data analysis and ML work so an independent recipient can reproduce the claimed results, verify artifact lineage, and operate the handoff within its stated scope. Use when finalizing a project, study, model package, or review bundle; not for deploying to a live system.
actions-reusable-workflows
Wire a repository to the bitwise-media-group/github-workflows reusable workflows — thin, SHA-pinned caller workflows for CI, security (CodeQL) scanning, release (release-please/GoReleaser/Zensical docs), the signature-preserving fast-forward /merge + merge-review-ack + merge-notice flows, and add-to-project — plus the…
go-style
Modern Go code style for stdlib-first programs — error wrapping with %w, sentinel errors, structured logging with log/slog, context threading, consumer-defined interfaces, nil-safe constructors, net/http servers with method-pattern routing, flag/env configuration for services, and cobra commands with viper…
diagnosing-ml-failures
Isolate the root cause of ML performance drops, inconsistent evaluations, prediction errors, and training-serving mismatches across data, labels, splits, pipelines, models, metrics, and runtime behavior. Use when investigating a reproducible failure or regression, not routine model selection or general performance…