>_Skillful
Need help with advanced AI agent engineering?Contact FirmAdapt
Mukunda Rao Katta

Mukunda Rao Katta

@mukundakatta

AI/ML Engineer | Building agentic workflows & LLM integrations | Anthropic Certified | Open Source |

Open to opportunities Las Vegas, NV@katta_mukunda On GitHub since February 2022

51

Published Tools

0

Total Stars

10

Weekly Downloads

12

GitHub Followers

683

Public Repos

Published Tools

10 MCP Servers21 Skills20 Agentsacross 6 categories

llm-trace-sampler-py

Mukunda Katta <[email protected]>

Sample LLM traces by risk, errors, latency, and deterministic ids. Python port of @mukundakatta/llm-trace-sampler.

Agentuncategorised
2 dirs

@mukundakatta/mcpcheck

mukundakatta

Validate MCP (Model Context Protocol) config files for Claude, Cursor, Cline, Windsurf, and Zed. CLI + GitHub Action with SARIF output.

...more
MCP Serveruncategorised
10/wk1 dir

@mukundakatta/tool-call-contracts

mukundakatta

Validate LLM tool-call payloads with small JSON-like contracts.

SkillLLM Tool
1 dir

@mukundakatta/codex-skill-kit

mukundakatta

Scaffold and validate Codex skills from the command line.

SkillLLM Tool
1 dir

@mukundakatta/prompt-injection-shield

mukundakatta

Prompt-injection risk scanner for untrusted AI context.

SkillLLM Tool
1 dir

@mukundakatta/model-fallback-planner

mukundakatta

Plan model fallback chains from capability, cost, and health data.

SkillLLM Tool
1 dir

@mukundakatta/tool-permission-gate

mukundakatta

Policy-check agent tool calls before execution.

SkillLLM Tool
1 dir

@mukundakatta/rag-quality-kit

mukundakatta

Heuristic quality metrics for RAG retrieval and grounded answers.

SkillRAG
1 dir

@mukundakatta/rag-staleness-auditor

mukundakatta

Find stale RAG chunks by age, version, and freshness requirements.

SkillLLM Tool
1 dir

@mukundakatta/retrieval-acl-filter

mukundakatta

Enforce document ACLs after retrieval and before prompting.

SkillLLM Tool
1 dir

@mukundakatta/context-window-packer

mukundakatta

Pack context chunks into a budget by relevance and priority.

SkillLLM Tool
1 dir

@mukundakatta/streamparse

mukundakatta

Streaming JSON parser that yields partial valid trees as tokens arrive. Built for LLM tool-call payloads, structured output streams, and any place a regular JSON.parse waits too long.

...more
SkillLLM Tool
1 dir

@mukundakatta/agentsnap-mcp

mukundakatta

MCP server: snapshot tests for tool-call traces. Capture, normalize, and diff agent tool-use traces to catch silent regressions. Wraps @mukundakatta/agentsnap for Claude Desktop, Cursor, Cline, Windsurf, and Zed.

...more
MCP ServerLLM Tool
1 dir

@mukundakatta/agentfit

mukundakatta

Fit your messages into the LLM context window. Token-aware truncation with multiple strategies (drop-oldest, drop-middle, priority), pluggable tokenizers, zero dependencies.

...more
SkillLLM Tool
1 dir

@mukundakatta/system-prompt-leak-scan

mukundakatta

Detect system prompt leakage in model outputs.

SkillLLM Tool
1 dir

io.github.MukundaKatta/agentcast

Structured-output enforcer: extract and validate JSON from messy LLM text.

MCP Serveruncategorised
1 dir

agentcast-py

Structured output for any LLM call. Validate-and-retry loop for JSON responses; BYO LLM and validator. Python port of @mukundakatta/agentcast.

...more
Agentai-agents
1 dir

io.github.MukundaKatta/agentfit

Token-aware message truncation: fit a chat history into your model's context budget.

MCP Serveruncategorised
1 dir

agentfit-py

Fit your messages into the LLM context window. Token-aware truncation with multiple strategies, pluggable tokenizers. Python port of @mukundakatta/agentfit.

...more
Agentai-agents
1 dir

io.github.MukundaKatta/agentguard

Network-egress firewall for agent tools: check URLs against a declarative policy.

MCP Serveruncategorised
1 dir

io.github.MukundaKatta/agentsnap

Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.

MCP Serveruncategorised
1 dir

io.github.MukundaKatta/agentvet

Validate tool-call args before execution. Returns LLM-friendly retry hints.

MCP Serveruncategorised
1 dir

agentvet-py

Validate LLM-generated tool args before execution. Wraps tool functions with arg validation, raises ToolArgError with LLM-friendly retry hint. Python port of @mukundakatta/agentvet.

...more
Agentai-agents
1 dir

ai-eval-forge

Zero-dependency eval harness for LLM and agent regression testing. Scores outputs with exact, contains, regex, JSON, citation, and token-F1 checks.

...more
Agentai-agents
1 dir

ai-supply-chain-manifest-py

Mukunda Katta <[email protected]>

Build and validate lightweight AI model / data / tool manifests. Python port of @mukundakatta/ai-supply-chain-manifest.

Skilluncategorised
1 dir

claude-commands-check

Linter for Claude Code slash-command files (.claude/commands/*.md). Validates YAML frontmatter, allowed-tools shape, description quality, and flags hardcoded secrets.

...more
Skillai-ml
1 dir

claude-hooks-check

Linter for Claude Code hooks configuration (the 'hooks' block of settings.json). Validates event names, matcher shape, command entries, and flags dangerous commands or hardcoded secrets.

...more
Skillai-ml
1 dir

claude-skill-check

Linter for Claude Code SKILL.md files. Validates YAML frontmatter, required fields, description length, and common secret patterns.

...more
Skillai-ml
1 dir

context-forge-py

Context engineering toolkit for ranking, packing, and risk-scanning RAG context. Python port of @mukundakatta/context-forge.

...more
Agentai-agents
1 dir

eval-flake-detector

Detect flaky LLM eval cases across repeated runs. Pass-rate + standard-deviation per case, with per-case severity. Python port of @mukundakatta/eval-flake-detector.

...more
Agentai-agents
1 dir

hallucination-risk-meter

Estimate hallucination risk in LLM answers from uncertainty language, unsupported specifics, citations, and context coverage. Python port of @mukundakatta/hallucination-risk-meter.

...more
Agentai-agents
1 dir

jailbreak-corpus-mini-py

Mukunda Rao Katta <[email protected]>

Small local jailbreak and prompt-injection fixture set for tests. Python port of @mukundakatta/jailbreak-corpus-mini.

Agentuncategorised
1 dir

llm-cost-guard-py

Estimate LLM request cost and enforce per-request or per-session budgets. Python port of @mukundakatta/llm-cost-guard.

Agentai-agents
1 dir

llm-output-sanitizer-py

Sanitize LLM outputs before HTML, SQL, shell, or markdown sinks. Python port of @mukundakatta/llm-output-sanitizer.

Agentai-agents
1 dir

llm-response-schema-lite-py

Tiny schema validator for structured LLM responses. Python port of @mukundakatta/llm-response-schema-lite.

Agentai-agents
1 dir

llm-usage-report

Parse LLM API response logs (Anthropic, OpenAI, Google) and generate token / cost reports. No framework adoption required.

...more
Skillai-ml
1 dir

mcp-config-check

Linter for MCP (Model Context Protocol) config files used by Claude Desktop, Cursor, Cline, Windsurf, and Zed. CLI + library API.

...more
MCP Servermcp
1 dir

mcpcheck-py

Lint MCP config files for Claude Desktop, Claude Code, Cursor, Cline, Windsurf, and Zed. Stdlib-only Python port of @mukundakatta/mcpcheck.

...more
MCP Servermcp
1 dir

model-fallback-planner-py

Mukunda Katta <[email protected]>

Plan model fallback chains from capability, cost, and health data. Python port of @mukundakatta/model-fallback-planner.

Skilluncategorised
1 dir

model-router-policy-py

Mukunda Katta <[email protected]>

Policy-based model routing by capability, cost, latency, and privacy. Python port of @mukundakatta/model-router-policy.

Skilluncategorised
1 dir

partial-json-stream

Streaming JSON parser that yields partial valid trees as tokens arrive. For LLM tool calls, structured outputs, and partial recovery.

...more
Skillai-ml
1 dir

prompt-injection-shield-cli

Mukunda Rao Katta

CLI wrapper for prompt-injection-shield-py: scan a file or stdin for prompt-injection patterns.

Skilluncategorised
1 dir

rag-quality-kit

Heuristic quality metrics for RAG retrieval and grounded answers. Python port of @mukundakatta/rag-quality-kit.

Agentai-agents
1 dir

rag-staleness-auditor-py

Find stale RAG chunks by age, version, and freshness requirements. Python port of @mukundakatta/rag-staleness-auditor.

Agentai-agents
1 dir

semantic-cache-key

Stable semantic cache keys for LLM requests. Invariant to whitespace, casing, and key ordering; sensitive to model swaps, tool list, and retrieval context. Python port of @mukundakatta/semantic-cache-key.

...more
Agentai-agents
1 dir

skillint-py

Lint Claude Code SKILL.md files for frontmatter, required fields, descriptions, and hardcoded secrets. Stdlib-only Python port of @mukundakatta/skillint.

...more
Agentai-agents
1 dir

io.github.MukundaKatta/streamparse

Parse partial / truncated / messy JSON for LLM tool calls and structured outputs.

MCP Serveruncategorised
1 dir

system-prompt-leak-scan

Detect system prompt leakage in LLM model outputs via known patterns, configured-prompt substring matching, and unique fingerprint phrases. Python port of @mukundakatta/system-prompt-leak-scan.

...more
Agentai-agents
1 dir

tool-call-contracts-py

Validate LLM tool-call payloads with small JSON-like contracts. Python port of @mukundakatta/tool-call-contracts.

Agentai-agents
1 dir

tool-result-taint-py

Mukunda Rao Katta <[email protected]>

Track untrusted tool output before it enters prompts or actions. Python port of @mukundakatta/tool-result-taint.

Agentuncategorised
1 dir

vector-poison-score

Score (query, document) pairs for vector/RAG poisoning signals: vector-text mismatch, instruction-like payloads, NaN, suspiciously round numbers. Python port of @mukundakatta/vector-poison-score.

...more
Agentai-agents
1 dir