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/kolodkin/devpowers/setup-mcpnpx skills add kolodkin/devpowers --skill setup-mcpgit clone --depth 1 https://github.com/kolodkin/devpowersWhat 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 | $0.00108 | $0.01687 |
| Opus 5 | $0.00054 | $0.00843 |
| Sonnet 5 | $0.00022 | $0.00337 |
| Haiku 4.5 | $0.00011 | $0.00169 |
Grade A, and why
setup-mcp 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup MCP
Register one of the MCP servers listed in ./mcps.json into either the project's .mcp.json, the user's Claude Code config, or via a manual file edit. The skill is bounded — it will not install MCPs outside the manifest. To add a new server, append an entry to mcps.json first (see "Adding a new MCP" below).
Invocation
/setup-mcp # list known MCPs, prompt to pick one
/setup-mcp <name> # set up the named MCP
Flow
1. Resolve which MCP
Read ./mcps.json. It maps each <name> to its config template, prerequisites, detection tool, and source URL.
- No argument → present a numbered list of
<name> — descriptionand ask the user to pick. <name>in the manifest → use that entry.<name>not in the manifest → tell the user: "<name>isn't in the bounded list. Append an entry toskills/setup-mcp/mcps.jsonfirst, then re-run." Show them an existing entry as a template. Stop — do not search the web for install instructions.
2. Detect whether it's already configured
Two checks:
- Is the entry's
detection_tool(e.g.mcp__github__list_pull_requests) visible in your tool list right now? - Is
<name>already registered? Tryclaude mcp list 2>/dev/nulland grep for it; also check./.mcp.json(if it exists) formcpServers.<name>.
If already configured, report where it's registered and stop. Don't reconfigure unless the user explicitly asks ("force", "reconfigure", "overwrite").
3. Verify prerequisites
For each command in the entry's required_cli, run command -v <cmd> >/dev/null && echo OK || echo MISSING. If anything is missing, surface the entry's notes (which should explain how to install it) and stop. Don't write any config until prerequisites are in place.
4. Show the proposed config
Print the exact JSON snippet that would be added under mcpServers.<name> — i.e. the entry's config_template verbatim. Also list any required_env and auth_alternatives so the user knows which env vars / tokens need to be set in their shell.
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.
- 2d ago First seen · 121 lines · 108 tokens per session scan A f837d2ab700c
setup-mcp is a skill published in the GitHub repository kolodkin/devpowers (2 stars, last pushed 23d ago), licensed MIT. It adds 108 tokens to every session and 1,687 once invoked, about $0.0005 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.