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 wrap-upgit 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/wrap-up)<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/wrap-up"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/wrap-up/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/wrap-up"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/wrap-up.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 | $0.00056 | $0.02653 |
| Opus 5.5 | $0.00022 | $0.01061 |
| Sonnet 5.5 | $0.00011 | $0.00531 |
| Haiku 4.5 | $0.00006 | $0.00265 |
Grade A, and why
wrap-up 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 4d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post-Session Wrap-Up
State warning: TaskList contents, plan checklist state, and any branch or remote-tracking state all change between invocations. Re-gather them from Step 0; never trust prior outputs from this conversation.
/wrap-up has two paths. Step 0 decides which one runs.
| Step 0 outcome | Path |
|---|---|
| Plan complete OR no plan | Path A — retrospective + follow-up prompt; plus repo refresh and branch cleanup when in a repository |
| Plan incomplete | Path B — emit resume blocks; skip Path A cleanup entirely |
The purge-pr focused mode (bottom of this file) bypasses Step 0 entirely.
Delegate the bulk read
Everything this skill reads before it decides is token-heavy and reasoning-light:
the /session-status report, the origin/main..origin/develop promotion log, the
open-PR listing, and the remaining plan/TaskList items Path B groups. Hand that
raw material to the router via the local-subagents skill (ai-delegation)
at the cheapest capable tier — capability small, or a subagent carrying an explicit
lower model: when the input is longer than one call holds. The premium lead
makes the Path A/Path B verdict over the returned table, never the raw dump.
Cap the input: at most 30 promotion-log lines and 30 PRs. Truncate, do not paginate. Exact small-model prompt text: references/path-b-and-purge-pr.md.
Fallback (verbatim from local-subagents): none of the router's failure
paths authorize a silent fallback. "Absorbing the work back into your own
context without saying so is the exact cost delegation was meant to avoid, and
it hides the failure from whoever pays for it." If the router is unreachable, do
the step yourself and say so in the Wrap-Up Summary. Never silently skip it.
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.
- 4d ago Changed c981179d3ff0
- 12d ago Changed cd28cfb4b845
- 24d ago Changed · -97 lines · -40 tokens per session 3b96ab26dd9d
- 1mo ago Changed bb36ddb8f8c4
- 1mo ago Changed · +35 lines 4cb11248203b
- 1mo ago First seen · 303 lines · 96 tokens per session scan A f6c513f8f7e2
wrap-up is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 2,653 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
nav-pilot
Dispatch a Navigator task doc to Pilot as a labeled GitHub issue. Use when user says "dispatch TASK-XX to Pilot", "hand off to Pilot", "send to Pilot", or "queue for Pilot". One-way handoff (Navigator authors the spec, Pilot executes autonomously).
meta-feedback
A feedback reporter that collects bug reports and feature requests, then formats them as GitHub Issues. GitHub Issues are shared records used by development teams to track work and problems.
github-project-management
GitHub project management with issue tracking, project-board automation, and sprint planning. Use when triaging or organizing issues, automating a project board, planning a sprint, or running release/roadmap coordination on GitHub.
feature
Deliver a feature or chore end to end, from branch creation to PR readiness, starting from an issue URL or a plain description.
afkkit
Run a groomed ready GitHub issue through the whole build span unattended, covering worktree, implement, commit, verify-and-review, fix, QA plan, and open PR, so one issue reaches a reviewable PR with no human at the keyboard. Use when the user says "run issue #N unattended" or "work the ready issues while I'm away".…
issuekit
Own the GitHub issue lifecycle in five modes: create issues from a plan or description, start a ready or stacked issue into its own worktree, close one out once its PR merges, sync PR↔issue links and dependents after merge, and triage the tracker for lifecycle, priority, and title gaps. Use when the user says "create…