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/wrap-up-docsnpx skills add dryvist/claude-code-plugins --skill wrap-up-docsgit 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 | $0.00151 | $0.01838 |
| Opus 5 | $0.00076 | $0.00919 |
| Sonnet 5 | $0.00030 | $0.00368 |
| Haiku 4.5 | $0.00015 | $0.00184 |
Grade A, and why
wrap-up-docs 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wrap-Up Docs
Produce exactly one artifact: a paste-ready prompt for a weaker local LLM that will update documentation. The consuming model sees none of this conversation and must not be asked to infer — the prompt carries every change explicitly, with instructions requiring no judgment beyond writing prose.
Emit the prompt and stop. This skill creates no tracker items, edits no files,
runs no cleanup — /wrap-up owns those. It is the documentation counterpart to
/handoff: same artifact class (self-contained prompt for a context-free
consumer), opposite compression strategy. Where /handoff compresses for a
smart reader, this skill expands for a weak one.
State warning: TaskList contents, plan checklist state, branch state, and any PR facts all change between invocations. Re-gather everything in Step 1; never trust prior outputs from this conversation.
Step 1: Gather live state
Always available:
- The plan file (from the latest
## Plan File Info:<system-reminder>) and its checklist items — context for what was attempted, not the change record. TaskList— completed tasks often name the components changed.- Conversation history (scanned in Step 1c).
1a. Version control — only when the cwd is a repository
Gate the whole step:
git rev-parse --is-inside-work-tree >/dev/null 2>&1
When it fails, skip every git source below, note the skip for the emitted prompt's NOT GATHERED section, and continue on conversation evidence alone. When it succeeds, collect:
- Uncommitted and untracked work:
git status --porcelain. - Branch commits relative to the remote-tracking upstream, when one exists:
git log --oneline '@{upstream}..HEAD'. Empty output means nothing is committed ahead — normal, not an error; conversation SHAs (1c) still cover work committed directly to a synced default branch. - Diff shape against the same upstream:
git diff --stat '@{upstream}...HEAD'. - Associated PRs: fetch candidates with
gh pr list --state all --limit 30 --json number,title,url,state,headRefName,headRefOidand keep those whoseheadRefOidmatches an inventoried commit SHA or whoseheadRefNamematches a branch named in this conversation. Capture full URLs, never bare#123.
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 · 171 lines · 151 tokens per session scan A b3b7e32498a3
wrap-up-docs is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 151 tokens to every session and 1,838 once invoked, about $0.0008 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…
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.…
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…