claude

enigma

Local-only MCP secret request/reveal server (CLI + Claude Code plugin): request a named secret via a one-time URL; the value is not returned in MCP tool responses, but child-process output can expose it. `enigma_reveal` discloses it to the human directly; `enigma run` injects it into a child process's environment (ADR-001). Repo-level project scope (0.3.0): secrets saved from a worktree, symlinked clone path, or submodule need `enigma migrate-scope` after upgrade.

2 on GitHubby Clarit AIv0.3.5Apache-2.0updated 4 days ago
/

Plugin enigma from marketplace kha-marketplace in KHAEntertainment/marketplace. Commands read from the repo's manifest — 3 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (1)

  • enigma

    Use whenever a task needs a secret value — an API key, token, password, or connection string — to configure, run, or test something, or whenever you are about to read a .env file, an environment variable, or a credential store. Also use immediately when a tool call is denied by Enigma's read-guard h

Slash commands (6)

  • /enigma:doctor

    Report Enigma's platform, depository, and configuration health

  • /enigma:import

    Import secrets from a .env file into Enigma and rewrite the file in place. Human-initiated only — this destroys the plaintext values.

  • /enigma:list

    List Enigma secrets known for this project and globally (names only, never values)

  • /enigma:remove

    Delete a secret from Enigma after the user confirms. Destructive and cannot be undone — human-initiated only, never invoke this on your own judgment.

  • /enigma:request

    Ask the user to enter one or more secrets out of band via Enigma

  • /enigma:reveal

    Reveal one secret's value to the user, out of band. Human-initiated only — never invoke this on your own judgment.

MCP servers (1)

  • enigma

    runs: node ${CLAUDE_PLUGIN_ROOT}/dist/mcp-server.mjs

Hooks (3)

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT}/dist/hooks.mjs" SessionStart

  • PreToolUse

    node "${CLAUDE_PLUGIN_ROOT}/dist/hooks.mjs" PreToolUse

  • PostToolUse

    node "${CLAUDE_PLUGIN_ROOT}/dist/hooks.mjs" PostToolUse

View source on GitHub khaentertainment.com

More from KHAEntertainment/marketplace

All 9 plugins →

view-limits

claude

Check coding-plan credit and rate-limit status across providers before dispatching sub-agents.

10 skills · 4 commands · hooks

2

self-updating-skills

claude

Self-updating Agent Skills framework and harness authoring suite (self-updating-skills, claude-code-authoring, codex-authoring, opencode-authoring) powered by a single-file upkeep.sh runtime for version pin checks, reference freshness, live doc fetching, and SHA-256 frozen owner-policy blocks.

4 skills

2

dev-skill

claude

Turns Claude Code into a Tech Lead running an Issue-to-PR SOP: requirements, worktrees, delegated workers, QA, review, and retro gates.

2 skills

2

authoring-kit

claude

Author Claude Code skills, hooks, subagents and plugins against the live code.claude.com docs instead of stale training data or bundled guides.

1 skill

2

jev

claude

Decide when and how to integrate TypeSafe's Jev decision model: access paths (TypeSafe, OpenRouter, Vercel, Cloudflare), framework choice, harness patterns (tool gates, routers, triage), calibration and production ops.

1 skill

2

npm-publish

claude

Current npm publishing methodology — OIDC trusted publishing, staged publishing, provenance, and 2FA enforcement, token-free. Overrides stale training data that defaults to `npm token create` and `NPM_TOKEN` secrets.

1 skill

2

Maintain enigma?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins9 plugins