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/ericboehs/claude-plugins/setup-agent-desktopnpx skills add ericboehs/claude-plugins --skill setup-agent-desktopgit clone --depth 1 https://github.com/ericboehs/claude-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 | $0.00052 | $0.00988 |
| Opus 5 | $0.00026 | $0.00494 |
| Sonnet 5 | $0.00010 | $0.00198 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade B, and why
setup-agent-desktop scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
If this returns a tree with refs, it's working; suggest `/agent-desktop`. Clean up: `rm -rf /tmp/ad-trusted`. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup agent-desktop CLI
Install the agent-desktop CLI (lahfir/agent-desktop) and grant permissions. Eric's environment has two supply-chain gates that block the normal install; this skill works through both.
Step 1: Check if already installed
which agent-desktop && agent-desktop version && agent-desktop status
- If
versionprints JSON andstatusshowsaccessibility: granted, it's set up; suggest/agent-desktop. - If "Native binary not found": the wrapper installed but the build step was skipped; go to Step 3 (approve build).
- If "command not found": install from scratch, Step 2.
Step 2: Verify a trusted binary, then install via aube
agent-desktop (npm) is a thin JS wrapper; its postinstall downloads the platform binary from GitHub Releases (SHA-256 only, no Sigstore). We verify it ourselves first, then hand it to the postinstall so no unreviewed network fetch runs.
VER=$(gh release view --repo lahfir/agent-desktop --json tagName --jq '.tagName' | tr -d v)
mkdir -p /tmp/ad-trusted && cd /tmp/ad-trusted
gh release download "v$VER" --repo lahfir/agent-desktop \
--pattern "agent-desktop-v$VER-aarch64-apple-darwin.tar.gz" --pattern checksums.txt --clobber
grep aarch64-apple-darwin checksums.txt | grep -v ffi > my.sum
shasum -a 256 -c my.sum # must say OK
gh attestation verify "agent-desktop-v$VER-aarch64-apple-darwin.tar.gz" --repo lahfir/agent-desktop # Sigstore
tar -xzf "agent-desktop-v$VER-aarch64-apple-darwin.tar.gz" && chmod +x agent-desktop
Install globally with aube (Eric's Node package manager). Two gates fire:
- Low-download guard (
ERR_AUBE_LOW_DOWNLOAD_PACKAGE, ~800/wk < 1000) →--allow-low-downloads. - Build-script skip →
approve-builds+rebuildbelow.
export AGENT_DESKTOP_BINARY_PATH=/tmp/ad-trusted/agent-desktop
aube add -g agent-desktop --allow-low-downloads
Step 3: Approve and run the build script
export AGENT_DESKTOP_BINARY_PATH=/tmp/ad-trusted/agent-desktop # set if a new shell
aube approve-builds -g agent-desktop # name the pkg to skip the picker
# approve-builds prints the global dir, e.g. ~/.local/share/aube/global-aube/<hash>
aube -C <global-dir> rebuild # runs postinstall; copies our binary, no download
hash -r
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.
- yesterday First seen · 80 lines · 52 tokens per session scan B 94ee7bc08251
setup-agent-desktop is a skill published in the GitHub repository ericboehs/claude-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 52 tokens to every session and 988 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…