Agent Stack — Development skill for Claude Code
The Agent Reliability Stack: fit, guard, snap, vet, cast.
How to install Agent Stack
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open MukundaKatta/agent-stack and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agent Stack does
The Agent Reliability Stack: fit, guard, snap, vet, cast. One landing page for all 11 npm + 6 PyPI packages.
Alternatives in Development
- npm 71.9k ★
- SRE — SRE (Site Reliability Engineer) Agent 9.1k ★
- Anthropic SDK Python — PyPI version 3.9k ★
README
agent-stack
Six small, single-concern reliability libraries for production LLM agents — TypeScript, Python, and MCP servers. Zero runtime dependencies. Adopt one or all.
[](https://doi.org/10.5281/zenodo.20074702) [](https://doi.org/10.57967/hf/8720) [](#license) [](https://huggingface.co/spaces/mukunda1729/agent-stack-demo)
**Landing page:** https://mukundakatta.github.io/agent-stack/ **Paper:** [Six Reliability Primitives for LLM Agents: An Artifact Pattern for Stackable, Single-Concern Libraries](https://doi.org/10.5281/zenodo.20074702) **HuggingFace Hub:** [mukunda1729/agent-stack](https://huggingface.co/mukunda1729/agent-stack)
The six primitives
| Library | Concern |
|---|---|
| AgentFit | Token-aware context-window fitting |
| AgentGuard | Network egress allowlist for tool calls |
| AgentSnap | Snapshot tests for tool-call traces |
| AgentVet | Tool-arg validation with retry hints |
| AgentCast | Structured-output validate-and-retry for LLM JSON |
| AgentBudget | Per-run token + dollar caps |
Each ships in three forms: TypeScript on npm, Python on PyPI, MCP-server variant.
Install
# TypeScript
npm i @mukundakatta/agentfit @mukundakatta/agentguard @mukundakatta/agentsnap \
@mukundakatta/agentvet @mukundakatta/agentcast @mukundakatta/agentbudget
# Python
pip install agentfit agentguard agentsnap agentvet agentcast agentbudget
// MCP server (Claude Desktop config)
{
"mcpServers": {
"agentvet": { "command": "npx", "args": ["-y", "@mukundakatta/agentvet-m
Related Skills
Evolveguard
Detects capability drift in Claude Agent Skills and MEMORY.md files before an edit ships. npm + PyPI CLI.
Random Repo
Pick and clone a random top-100 open-source package from a major package registry (npm, PyPI, crates.io, Go mo
Automation Publish
Automation Package Publishing Command - Publish both orchestration and automation packages to PyPI
Setuhq Vet
Vet a TESS target or a light curve for a transit with SetuHQ's own search, vetting, fit and false-alarm probab
Publishing
Use when publishing Buoy packages to npm, bumping versions, or debugging workspace: dependency leaks. Covers t
Skilltotal
Claude Code plugin that scans a package before the agent runs npx, npm install, pip install, uvx or claude mcp
Related Agents
Compliance Guard
Advertising policy and compliance audit subagent. Screens proposed ad copy, creative angles, landing page clai
Researcher Context7
Library documentation research agent using context7 MCP. Specializes in up-to-date official docs for React, Ne
Stock Scout
Fetches and VETS realistic VISUAL stock from Pixabay (real photos, video b-roll, detailed 3D models; GIFs/illu