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/skillpanel/claude-plugins/serena-setupnpx skills add SkillPanel/claude-plugins --skill serena-setupgit clone --depth 1 https://github.com/SkillPanel/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 | $0.00059 | $0.00569 |
| Opus 5 | $0.00030 | $0.00284 |
| Sonnet 5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
serena-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Overview
Configures Serena MCP to work in a git worktree. Copies cache and memories from the main repo, installs a post-checkout hook for future worktrees, and activates the project.
project.yml should be committed to git. memories/ are copied from main repo by the setup script (like cache/).
If running in the main repository
Run setup-serena.sh — it detects the main repo and installs the post-checkout hook only. Report the output to the user.
If running in a worktree
Step 1 — Run setup script:
<base-directory>/setup-serena.sh
Replace <base-directory> with the actual base directory shown at the top of this skill's context.
If it fails, show the error and stop. If it succeeds, check the output for [warn] lines and report them to the user.
Step 2 — Activate project:
Serena MCP is shared across sessions and won't auto-activate the worktree project. Activate it explicitly:
- Call
activate_projectwith the worktree path ($PWD) - Call
check_onboarding_performed - If memories exist: done — move to Step 3
- If no memories: do NOT run onboarding. The setup script should have copied them from main. Tell the user: "Memories missing — run onboarding in the main repo first, then re-run /serena-setup"
Step 3 — Verify:
Call list_dir with relative_path: "." to confirm Serena is reading the worktree (not the main repo or a parent directory).
Tell user: "Serena setup complete. Future worktrees will get .serena/cache automatically via post-checkout hook."
Common Mistakes
| Mistake | Consequence |
|---|---|
| Running in main repo | Script installs hook only — no worktree setup needed |
| Running onboarding in worktree | Wastes time recreating memories that exist in main repo — never do this |
.serena/project.yml not committed to git |
Worktrees won't have it after checkout — script warns and copies as workaround |
What ships with it
2 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.
- 2d ago First seen · 51 lines · 59 tokens per session scan A 853d9fd3b6e0
serena-setup is a skill published in the GitHub repository SkillPanel/claude-plugins (3 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 569 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.