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/dryvist/claude-code-plugins/goalnpx skills add dryvist/claude-code-plugins --skill goalgit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWhat 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 | $0.00140 | $0.01761 |
| Opus 5 | $0.00070 | $0.00881 |
| Sonnet 5 | $0.00028 | $0.00352 |
| Haiku 4.5 | $0.00014 | $0.00176 |
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 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 — 162 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 — that belongs to /handoff, not here.
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.
- 2d 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 2d ago), licensed Apache-2.0. It adds 140 tokens to every session and 1,761 once invoked, about $0.0007 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
rspec
This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…
activerecord
This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…
draper-decorators
This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…
mcp-server
This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when…
ratatui-ruby
This skill should be used when the user asks to "create a TUI", "terminal interface", "terminal UI", "ratatui", "ratatui-ruby", "inline viewport", "full-screen terminal app", "terminal widgets", "tui.draw", "tui.pollevent", or mentions RatatuiRuby.run, managed loop, terminal rendering, Tea MVU, or building CLI…
dragonruby
This skill should be used when the user asks to "create a game", "make a game", "game development", "dragonruby", "drgtk", "game loop", "tick method", "sprite rendering", "game state", or mentions args.outputs, args.state, args.inputs, coordinate system, collision detection, animation frames, or scene management.…