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/mcs-cli/mcs/techpack-creatornpx skills add mcs-cli/mcs --skill techpack-creatorgit clone --depth 1 https://github.com/mcs-cli/mcsWhat 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 | $0.00190 | $0.03919 |
| Opus 5 | $0.00095 | $0.01959 |
| Sonnet 5 | $0.00038 | $0.00784 |
| Haiku 4.5 | $0.00019 | $0.00392 |
Grade A, and why
techpack-creator scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
fixCommand: '/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"' How it starts
The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TechPack Creator
You analyze repositories that already have Claude Code configuration and package them into MCS tech
packs for distribution. A tech pack is a Git-distributable bundle of Claude Code configuration — MCP
servers, hooks, skills, commands, agents, templates, and settings — defined in a single
techpack.yaml manifest that the mcs CLI syncs and maintains.
Two approaches — choose based on what's available:
-
mcs exportfirst (recommended when MCS is installed): Runmcs export ./pack-outputto capture the live Claude Code configuration as a starting point. Then review and improve the generatedtechpack.yaml— add dependencies between components, add prompts for env vars, add doctor checks, and wire up templates. This is the fastest path when the user already has a working Claude Code session. -
Direct scan (when no live config or MCS is not installed): Analyze the repo's files and directory structure directly — read hook scripts, skill directories, command files, settings JSON, CLAUDE.md content, and project manifests to understand what the repo provides. Generate the
techpack.yamland supporting files from scratch.
Both approaches produce the same output: a complete pack directory ready for mcs pack add.
Bundled references (read on demand, not upfront):
references/techpack-schema.md— Complete field-by-field schema fortechpack.yamlreferences/stack-detection.md— File-to-stack mapping and component recommendationsreferences/examples/— Realistic example techpacks (swift-ios.yaml, node-web.yaml, python-ml.yaml)
Remote documentation — use these for the latest info and link them in generated READMEs:
- MCS CLI: https://github.com/mcs-cli/mcs
- Schema reference: https://github.com/mcs-cli/mcs/blob/main/docs/techpack-schema.md
- Creating tech packs guide: https://github.com/mcs-cli/mcs/blob/main/docs/creating-tech-packs.md
- Claude Code hooks: https://docs.anthropic.com/en/docs/claude-code/hooks
- MCS CLI reference: https://github.com/mcs-cli/mcs/blob/main/docs/cli.md
- MCS troubleshooting: https://github.com/mcs-cli/mcs/blob/main/docs/troubleshooting.md
If the bundled references are unavailable (skill installed without reference files), fetch the remote documentation using WebFetch on the URLs above. The remote docs are the canonical source of truth.
What ships with it
5 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 · 370 lines · 190 tokens per session scan A aab54eb0c978
techpack-creator is a skill published in the GitHub repository mcs-cli/mcs (93 stars, last pushed 1mo ago), licensed MIT. It adds 190 tokens to every session and 3,919 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.