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 dryvist/claude-code-plugins --skill goalgit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWrote 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/dryvist/claude-code-plugins/goal)<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/goal"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/goal/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/dryvist/claude-code-plugins/goal"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/goal.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 | $0.00055 | $0.01731 |
| Opus 5.5 | $0.00022 | $0.00692 |
| Sonnet 5.5 | $0.00011 | $0.00346 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
goal 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 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.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Emit a single objective statement the reader can act on with no other context. Print it and stop. This skill produces one artifact and takes no other action.
Run it at any point: mid-task, before a handoff, after a pivot, in a scratch directory with no repository. It never blocks on state it cannot find.
Scope
In: one goal statement body, under 4000 characters, printed to the user.
Direct invocation wraps it in a ## Goal statement header (Step 5); the body
itself never contains a heading.
Out: file writes, commits, git or gh calls, network access, plan edits,
task updates. The single command this skill runs is the wc -m measurement in
Step 4, which reads from a heredoc and writes nothing. If you find yourself
running anything else, stop — it is outside this skill's scope.
Step 1: Determine focus
If an argument was supplied, it is the focus. Treat it exactly as
/compact's hint: a steer on what matters, not a full specification. Honor
exclusions in it literally — "ignore the docs work" means no docs criterion,
even if docs work is unfinished.
With no argument, derive focus from these sources, highest weight first:
- The most recent pivot. Where the work changed direction, scope, or approach — a correction, a rejected approach, a new constraint. The current objective lives after the last pivot, not at the top of the session.
- Unfinished plan items. Resolve the plan file from the most recent
## Plan File Info:block in a<system-reminder>— match[^[:space:]]+/\.claude/plans/[^[:space:]]+\.mdand take the latest. Read it and collect unchecked- [ ]items. No such block means no plan file; skip. - Open tasks. Call
TaskList; keep entries whosestatus != "completed".
Skip any source that is absent. All three absent is normal and fine — derive the goal from the conversation alone.
Where sources disagree, the conversation wins. A plan file records what was true when written; the session records what is true now.
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 Changed · -2 lines · -7 tokens per session 92a4192c187a
- 24d ago Changed · +3 lines · -78 tokens per session 0a7f7e499814
- 1mo ago First seen · 162 lines · 140 tokens per session scan A 2ac35eb46417
goal is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,731 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
detect-github-url
Detects when the user pastes or mentions a GitHub URL that may contain Claude skills or plugins. Triggers on messages containing github.com URLs, especially when user says things like "here's a repo", "check out this repo", "load this", "use these skills", "I found these skills", or simply pastes a github.com link.…
example-feature-generator
Generate boilerplate for new features following project conventions. Use when user says "create feature", "add feature", or "new feature scaffolding".
media-gemini-3-image-prompt
A prompt builder for Gemini 3 Pro Image, also known as Nano Banana Pro, Google's image-generation model. It expands a short request into five parts covering the subject, action, setting, composition, lighting, style, and text constraints.
commerce-jtbd-persona
An e-commerce customer-analysis skill that studies reviews and questions to identify why people buy and to create concrete customer profiles. JTBD means “jobs to be done”: the practical goal a customer is trying to accomplish.
data-realestate
A lookup tool for reported South Korean property transactions using Ministry of Land data. It covers sales and rental deals for apartments, officetels, multi-family homes, houses, and commercial or office properties.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.