Borrowing it
Nothing to install: this file belongs to auerbachb/claude-code-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/auerbachb/claude-code-config/main/.claude/skills/wrap/SKILL.mdgit clone --depth 1 https://github.com/auerbachb/claude-code-configWrote 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/auerbachb/claude-code-config/wrap)<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/wrap"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/wrap/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/auerbachb/claude-code-config/wrap"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/wrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 947 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Excessive Agency · line 32 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00052 | $0.19092 |
| Opus 5.5 | $0.00021 | $0.07637 |
| Sonnet 5.5 | $0.00010 | $0.03818 |
| Haiku 4.5 | $0.00005 | $0.01909 |
Grade A, and why
wrap 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 28d 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 — 986 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wrap up the current PR and session. This is the "we're done here" command that handles final verification through merge, root-main sync, follow-up detection, a full-session sweep for loose ends, and lessons.
/wrap accepts an optional PR reference as its argument — a full URL, #N, owner/repo#N, or a bare number N. When invoked with no argument it resolves the target PR through the inference cascade in Step 1.1 (current branch → thread context → session-state). An explicit argument bypasses all inference.
/wrap does not delete the running worktree or its branch — leaving the thread alive so it can keep working. Stale worktrees and stale local/remote branches are reaped out-of-band by /pm-clean, which calls stale-cleanup.sh.
When to use /wrap vs /merge
- Use /wrap at end-of-session. Handles merge + root-main sync + follow-up detection + lessons.
- Use /merge for a quick mid-session merge when you'll keep working. Skips follow-up detection and lessons.
- /wrap includes everything /merge does, plus follow-ups and lessons. Don't run both.
- Phase C invokes this skill after gate and AC verification; keep merge, main-sync, follow-up, and cleanup behavior here so Phase C and
/wrapcannot drift. - Target PR:
/wrapoperates on the PR resolved in Step 1.1. Pass an explicit reference (/wrap <URL>,/wrap #N,/wrap N) to wrap a PR that is not on the current branch — common in orchestration threads that ran/fixpr <URL>against another worktree. With no argument, Step 1.1's cascade infers the PR. - Callers of the
/wrap #Nform: Phase C (phase-c-merger),/pr-monitor-and-manage(merge-ready fleet PRs), and/pm's one-shot forgotten-PR triage (issue #657) all merge an already-open PR by dispatching this workflow rather than reimplementing merge logic — the merge gate, AC verification, and squash-merge live here so every caller stays consistent.
Execution Model
/wrap is a set-and-forget command. Once invoked, it runs all 4 phases end-to-end without mid-run confirmation prompts. It stops early only for explicit stop conditions (for example: no PR on current branch, human change requests on HEAD, recovery iteration cap, failed merge gate after recovery, /fixpr delegation failure, AC verification failure).
What ships with it
3 files 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.
- 28d ago Changed 817a876f89d8
- 1mo ago Changed · +5 lines 9d76de4dec32
- 1mo ago Changed · +9 lines 68b14908f2fa
- 2mo ago First seen · 972 lines · 52 tokens per session scan A 28b2a1e1fdd3
wrap is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 19,092 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
upload
Pre-upload gate for track handoff. Verifies review status, HLD approvals, deploy checklist, and validator chain before git upload or PR submission.
bump-version
Bump the Logic-Lens version across all six metadata locations at once (package.json, the four plugin manifests, and the README badge), then validate. Use when cutting a release or when npm run validate reports a version mismatch.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
otto-drive-pr
PR mergeability, CI, and live preview.
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…