hermes-labs-ai

Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, deterministic checks, built for CI.

1 plugin · hermes-labs-ai/lintlang

Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

1 plugin · hermes-labs-ai/little-canary

Zero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench

1 plugin · hermes-labs-ai/hermes-jailbench

Recovers the original goal of a long Claude Code or Codex session from its first user turn, so you can restate it before continuing — plus a prompt wrapper that adds evidence and hedging constraints to evaluation prompts. Deterministic, local, no model calls. Experimental.

1 plugin · hermes-labs-ai/hermes-blind

quick-gate-js (npm: quick-gate) is a deterministic JS/TS CI quality gate that unifies ESLint, TypeScript, build, and Lighthouse checks into one fail-fast result, with bounded auto-repair and structured escalation evidence for humans or agents. Works with Next.js, React, Vue, Svelte, or any Node project. A gate-and-escalate wrapper, not a dashboard.

2 plugins · hermes-labs-ai/quick-gate-js

Deadline-bounded local search fan-out with source-explicit JSON receipts for agents and engineers.

1 plugin · hermes-labs-ai/supersearch

Static analyzer for AI system prompts: parses a prompt into normative rules and reports contradictions, coverage gaps, priority ambiguities, and absolute-rule edge cases - no LLM calls. Deterministic pure-Python lint with CLI, Python API, and CI exit codes. pip install rule-audit

1 plugin · hermes-labs-ai/rule-audit

Recoverable deletion guard and trash workflow for Claude Code, Codex, and Gemini CLI agents

2 plugins · hermes-labs-ai/agent-trash-guard

csv-quality-gate is a command-line data quality gate that runs CSV preflight validation, failing fast before an ML or LLM pipeline ingests broken, incomplete, duplicated, or junk input. It checks missing columns, empty files, empty cells, and duplicate rows, returning pass, warn, or fail with matching exit codes. Stdlib-only, CI-ready.

1 plugin · hermes-labs-ai/csv-quality-gate

intent-verify is a deterministic, zero-LLM CLI that checks whether a repo's source still lexically covers the acceptance items in a markdown spec, INTENT.md, or handoff doc, returning verified, partial, or missing. A fast guardrail for catching spec-vs-code drift before review, release, or handoff. Lexical coverage, not semantic proof.

1 plugin · hermes-labs-ai/intent-verify

Canonical generated plugin catalog for Claude Code, Codex, GitHub Copilot, and portable Agent Plugins

14 plugins · hermes-labs-ai/plugins

Compatibility feed for existing GitHub Copilot plugin installations

12 plugins · hermes-labs-ai/copilot-plugins

quick-gate-python (PyPI: pygate-ci) is a deterministic Python CI quality gate that normalizes Ruff, Pyright, and pytest results into one fail-fast decision, attempts bounded auto-repair, and escalates with machine-readable evidence for humans or agents when it cannot finish safely. A gate-and-escalate wrapper, not a lint dashboard.

1 plugin · hermes-labs-ai/quick-gate-python

Experimental work in progress: local quality gate for coding agents that runs repository-declared checks and emits input-bound PASS/FAIL receipts. Source install only; no PyPI release.

2 plugins · hermes-labs-ai/kwik-e-gate