enigma-cli 1.6.2 → 1.6.4

package/README.md

@@ -30,11 +30,6 @@ enigma check           Integrity gate: verify skills are well-formed and sealed
 enigma help | version
 ```
 
-Everything is modular and opt-in via [`@clack/prompts`](https://github.com/bombshell-dev/clack):
-the menu lets you enable or disable each feature, and `enigma security` lets you
-toggle each protection. Nothing touches your git config unless you run
-`enigma security` or accept its prompt.
-
 ## Agent skills
 
 Skills are authored once and deployed to every selected agent (no per-agent
@@ -71,12 +66,22 @@ Bypass once with `git commit --no-verify`.
 
 ## Multiple Claude Code accounts
 
-If you use one Claude Code login for work and another for personal projects,
-`enigma` lets you keep both side by side and switch without logging out. Claude
-Code reads its credentials and session from the directory in `CLAUDE_CONFIG_DIR`
-(default `~/.claude`), so each account just needs its own directory. Rather than
-hand-editing per-shell aliases, `enigma` launches Claude for you with that
-variable set - the same command on macOS, Linux and Windows.
+Work across separate workflows with different Claude Code accounts/profiles - for
+example your **company** Claude Code account and your **personal** one - keeping
+each fully isolated and switching between them without ever logging out. Each
+profile has its own credentials, session, and history, so client work never mixes
+with personal projects.
+
+> This is for legitimate, professional account separation (one account per
+> employer/context, as many organizations require). It is **not** a way to evade
+> usage limits or Anthropic's terms - each account still authenticates as itself
+> and is subject to its own limits. Use the account that each piece of work
+> belongs to.
+
+Claude Code reads its credentials and session from the directory in
+`CLAUDE_CONFIG_DIR` (default `~/.claude`), so each profile just needs its own
+directory. Rather than hand-editing per-shell aliases, `enigma` launches Claude
+for you with that variable set - the same command on macOS, Linux and Windows.
 
 ```bash
 enigma account add work --login   # create 'work' and run /login to authenticate
@@ -120,6 +125,44 @@ enigma config commit-emoji off -g    # global (~/.enigma.json)
 
 Precedence: built-in default (on) -> `~/.enigma.json` -> repo `.enigma.json`.
 
+## Parallel sub-agents
+
+The memory file always tells agents to break long or complex tasks into smaller
+subtasks and complete them incrementally. The parallel part - delegating
+independent subtasks to sub-agents that run at the same time to finish faster -
+is opt-in, because spawning sub-agents multiplies token cost:
+
+```bash
+enigma config parallel-subagents on        # add the parallel section to the memory file
+enigma config parallel-subagents off       # remove it (default)
+enigma config parallel-subagents on -g      # global (~/.enigma.json)
+```
+
+This toggle edits the deployed agent memory file (adds or removes the section),
+so **restart Claude Code / Codex / OpenCode** after changing it for the new
+session to pick it up. Subtask decomposition itself is always on and is never
+removed.
+
+## Token-efficient output
+
+Optionally compress the agent's chat prose to cut output tokens while keeping
+full technical accuracy (inspired by [caveman](https://github.com/JuliusBrussee/caveman)).
+Chosen at install or via config; off by default:
+
+```bash
+enigma config output-style lite     # professional terse (drop filler, keep grammar)
+enigma config output-style full     # caveman-style fragments
+enigma config output-style ultra    # telegraphic, maximum compression
+enigma config output-style off      # back to full prose (default)
+enigma install --output-style lite  # set it during install
+```
+
+`on`/`off` also work (`on` = `lite`). Like the toggle above it edits the memory
+file, so **restart your agent** after changing it. Code, comments, commits, and
+PRs stay normal, the agent reverts to full prose for security warnings and other
+safety-critical replies, and the level is switchable mid-session by asking
+("be more terse", "ultra", "normal mode").
+
 ## License
 
 [Apache-2.0](LICENSE).

package/assets/memory/AGENTS.md

@@ -25,6 +25,28 @@
 - End files with exactly one trailing newline and no trailing whitespace.
 - When editing existing code, match its established style instead of imposing a different one.
 
+### Task Execution (Always-On)
+
+- For long or complex tasks - or any task you judge to warrant it - break the work into smaller, well-scoped subtasks and complete them incrementally, validating each subtask before moving to the next.
+- Map the dependencies between subtasks before starting, and do only the decomposition the task genuinely needs - never over-decompose simple work.
+
+<!-- enigma:parallel-subagents:start -->
+- When subtasks are genuinely independent and your runtime can spawn sub-agents (parallel task or sub-agent tools), delegate them to sub-agents that run in parallel to finish faster, then reconcile their results into a coherent whole. If the runtime has no sub-agent support, execute the subtasks sequentially.
+- Only parallelize independent work; never spawn sub-agents for trivial, tightly-coupled, or strictly sequential tasks. Keep each sub-agent's responsibility well-scoped and validate what it returns.
+<!-- enigma:parallel-subagents:end -->
+
+<!-- enigma:output-style:start -->
+### Output Style (Token-Efficient)
+
+- Default to **{{output-level}}** compression in conversational prose: cut filler, pleasantries, and hedging while keeping every technical fact, exact identifier, and code block intact. Brevity must never drop substance or change a technical claim.
+- Levels (the user can switch any time by asking - e.g. "be more terse", "full", "ultra", or "normal mode" to turn it off):
+  - **lite** - professional and tight: drop filler and hedging, keep correct grammar and the user's language. The safe default.
+  - **full** - drop articles and use fragments where meaning stays unambiguous; prefer short synonyms ("fix", not "implement a solution for").
+  - **ultra** - telegraphic: one word where one word suffices, arrows for causality (X -> Y). Never abbreviate code symbols, function/API names, paths, or error strings.
+- Auto-clarity: revert to full prose for security warnings, irreversible or destructive action confirmations, and any multi-step sequence where compression would make the order or meaning ambiguous. Resume after the critical part.
+- Boundaries: code, comments, commit messages, and PR text are always written normally - compression applies only to chat prose. Always respond in the user's language regardless of level.
+<!-- enigma:output-style:end -->
+
 ---
 
 ## Core Identity

package/assets/memory/CLAUDE.md

@@ -25,6 +25,28 @@
 - End files with exactly one trailing newline and no trailing whitespace.
 - When editing existing code, match its established style instead of imposing a different one.
 
+### Task Execution (Always-On)
+
+- For long or complex tasks - or any task you judge to warrant it - break the work into smaller, well-scoped subtasks and complete them incrementally, validating each subtask before moving to the next.
+- Map the dependencies between subtasks before starting, and do only the decomposition the task genuinely needs - never over-decompose simple work.
+
+<!-- enigma:parallel-subagents:start -->
+- When subtasks are genuinely independent and your runtime can spawn sub-agents (parallel task or sub-agent tools), delegate them to sub-agents that run in parallel to finish faster, then reconcile their results into a coherent whole. If the runtime has no sub-agent support, execute the subtasks sequentially.
+- Only parallelize independent work; never spawn sub-agents for trivial, tightly-coupled, or strictly sequential tasks. Keep each sub-agent's responsibility well-scoped and validate what it returns.
+<!-- enigma:parallel-subagents:end -->
+
+<!-- enigma:output-style:start -->
+### Output Style (Token-Efficient)
+
+- Default to **{{output-level}}** compression in conversational prose: cut filler, pleasantries, and hedging while keeping every technical fact, exact identifier, and code block intact. Brevity must never drop substance or change a technical claim.
+- Levels (the user can switch any time by asking - e.g. "be more terse", "full", "ultra", or "normal mode" to turn it off):
+  - **lite** - professional and tight: drop filler and hedging, keep correct grammar and the user's language. The safe default.
+  - **full** - drop articles and use fragments where meaning stays unambiguous; prefer short synonyms ("fix", not "implement a solution for").
+  - **ultra** - telegraphic: one word where one word suffices, arrows for causality (X -> Y). Never abbreviate code symbols, function/API names, paths, or error strings.
+- Auto-clarity: revert to full prose for security warnings, irreversible or destructive action confirmations, and any multi-step sequence where compression would make the order or meaning ambiguous. Resume after the critical part.
+- Boundaries: code, comments, commit messages, and PR text are always written normally - compression applies only to chat prose. Always respond in the user's language regardless of level.
+<!-- enigma:output-style:end -->
+
 ---
 
 ## Core Identity

package/assets/skills/backend-policy/skill.json

@@ -3,6 +3,6 @@
   "version": "1.0.0",
   "provider": "FJRG2007/enigma",
   "description": "Backend/API architecture: controller-service-repository layering, API and request optimization, server-side caching (Redis), and Zod boundary validation.",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "c442bc9e39a7710cb709ef2abb8d15ecd8aa16ed4f5c8af92b7af6877401cba4"
 }

package/assets/skills/ciphera-style-policy/skill.json

@@ -3,6 +3,6 @@
   "version": "1.1.1",
   "provider": "FJRG2007/enigma",
   "description": "Ciphera code style conventions (formatting, naming, imports, comments, code-level anti-patterns; TypeScript-first, language-agnostic).",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "74f638aec13e8c93257fe1ad604c28b07e9a7c456796a4ceefcc99217d9e7039"
 }

package/assets/skills/code-review-policy/skill.json

@@ -3,6 +3,6 @@
   "version": "1.0.0",
   "provider": "FJRG2007/enigma",
   "description": "Pre-delivery self-review gate, prioritized review dimensions, and change-quality criteria.",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "3d3bbe0602d5bbb4afe37648fe3c2fa39376b1bcbac5d8c441f01fad1e866ed0"
 }

package/assets/skills/core-engineering-policy/skill.json

@@ -3,6 +3,6 @@
   "version": "1.4.0",
   "provider": "FJRG2007/enigma",
   "description": "Core engineering execution policy and harness orchestration (highest-authority rules).",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "c9c69c59516794311cb7b306ed4d4ad971824de3689a39c2b86c7669c73f2e8b"
 }

package/assets/skills/database-expert/skill.json

@@ -3,6 +3,6 @@
   "version": "1.0.0",
   "provider": "FJRG2007/enigma",
   "description": "Senior database architecture policy: query optimization, anti-duplication/normalization, scalability, and RGPD/GDPR encryption.",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "c4617ee8d1a57d9621c81bef3093e94de91f79eec0cc0ead41f6d18dd443e623"
 }

package/assets/skills/debugging-policy/skill.json

@@ -3,6 +3,6 @@
   "version": "1.0.0",
   "provider": "FJRG2007/enigma",
   "description": "Reproduce-isolate-fix debugging methodology with root-cause discipline and regression verification.",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "14b0064c8b33a0dc85e51464b05005cf5801c756b1101789a6924b9548420f6b"
 }

package/assets/skills/dependency-policy/skill.json

@@ -3,6 +3,6 @@
   "version": "1.0.0",
   "provider": "FJRG2007/enigma",
   "description": "Dependency and supply-chain security: lockfiles and reproducible installs, version pinning, vulnerability auditing, vetting/minimizing packages, vendoring, and SBOM/provenance.",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "6375d835c2aef2c9bd31ce116444dc3d796f510f9970a213aa3ac4696d7e21b9"
 }

package/assets/skills/frontend-policy/skill.json

@@ -3,6 +3,6 @@
   "version": "1.1.0",
   "provider": "FJRG2007/enigma",
   "description": "Frontend architecture: reusable components, abstraction thresholds, state management, and optimistic UI with rollback.",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "33fa1e9f667ef26203a3d6c892121efe12b0cddb706c195492fa97e080fba115"
 }

package/assets/skills/git-policy/skill.json

@@ -3,6 +3,6 @@
   "version": "1.2.0",
   "provider": "FJRG2007/enigma",
   "description": "Git & contribution policy (senior engineering standards).",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "ada4b7eb5bb7e013429e23703c271c0f34b0d76327c059efa148ea2794f96178"
 }

package/assets/skills/security-policy/skill.json

@@ -3,6 +3,6 @@
   "version": "1.0.0",
   "provider": "FJRG2007/enigma",
   "description": "Application and AI-agent security: secrets, authn/authz (least privilege), OWASP Top 10, transport/crypto baseline, secure logging, and agent/MCP/tool-use safety.",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "9971e9d9127397d0152e89d24aad3191e2935e55a8483db7fd15f5d4d7a60e7a"
 }

package/assets/skills/testing-policy/skill.json

@@ -3,6 +3,6 @@
   "version": "1.0.0",
   "provider": "FJRG2007/enigma",
   "description": "Test strategy, coverage gates, deterministic tests, mocking discipline, and regression-first bug fixing.",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "d19fa8ec7985ed231478be504d3c80360897f555d0bc0624bea19c091f459fb0"
 }

package/assets/skills/validation-policy/skill.json

@@ -3,6 +3,6 @@
   "version": "1.0.0",
   "provider": "FJRG2007/enigma",
   "description": "Strict frontend + backend schema validation, schema consistency, and safe client-facing error handling.",
-  "cliVersion": "1.6.2",
+  "cliVersion": "1.6.4",
   "sha": "a33622a2f810ee4cea39824cb1a7ca34b355a917d4224025df50d77dd74f0b3a"
 }

package/bin/checksums.json

@@ -1,6 +1,6 @@
 {
-  "enigma-darwin-arm64": "5bdd4b725004ea85a75b27505b692a311249ce39bda42effa59d57671c513ffe",
-  "enigma-linux-arm64": "4d806aca990e698e181b827ddfb96a8861e9bd195f66ee999856747968a97286",
-  "enigma-linux-x64": "9b2577d0d763aff4611691845a4ae72e9b41f33cd8af2ba9755b93e53d0fd709",
-  "enigma-win32-x64.exe": "f68f45ff1466593289ddef332edbbaa1652ea4b3db03dedee4817e3ced462cfb"
+  "enigma-darwin-arm64": "0250f3304140999cf52c768e658e631e3b791df6c254c94e9aab0df5b41750d2",
+  "enigma-linux-arm64": "c652278b26ab717e8d1a9d2729b342cebd4b07b99716bb0e22f60a832271ae8e",
+  "enigma-linux-x64": "b5dc8ffd1f9e870b99936b114eca90a5192a7933acca93a2df524f9ba2df25dd",
+  "enigma-win32-x64.exe": "f7e16827e385d48fb1298c1eee1fe4e5f3f212b2d7eb0cbffab1c631eeb76725"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "enigma-cli",
-  "version": "1.6.2",
+  "version": "1.6.4",
   "description": "Everything you need to work with a coding agent: install shared policy skills for Claude Code, OpenAI Codex and opencode, and set up portable git security hooks.",
   "type": "module",
   "bin": {