enigma-cli 1.28.1 → 1.29.0

package/assets/memory/AGENTS.md

@@ -18,6 +18,7 @@
 - dependency-policy: adding/upgrading/auditing dependencies, lockfiles, and supply-chain risk.
 - testing-policy, code-review-policy, debugging-policy, git-policy: tests and test-suite layout (structured subfolders, never a flat tests/ dump), pre-delivery review, debugging, and commits/PRs.
 - technical-writing-policy: any user-facing copy - UI labels, descriptions, hints, empty/error states, panel intros, README/doc prose - concise and realistic, no over-explaining or restating the obvious.
+- logo-sourcing-policy: adding any real brand/platform/technology logo or icon - source the official asset (never fabricate one), prefer SVG (WebP for web), keep brand colors, and check contrast.
 - task-completion-policy: long or multi-item tasks (1:1 ports, migrations, repo-wide changes) - work-unit inventory, persistent coverage ledger, and verified completion before any "done" claim.
 
 ### Always-On Rules (never skipped, even if no skill loads)
@@ -55,18 +56,6 @@
 - 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 -->
 
-<!-- enigma:minimal-code:start -->
-### Minimal Code (Anti-Overengineering)
-
-- Default to **{{minimal-level}}** minimal-code discipline (full detail in anti-overengineering-policy). The best code is the code never written; before writing any, stop at the first rung that holds: 1) Does this need to exist at all? (YAGNI) 2) Does the standard library do it? 3) Does a native platform feature cover it? 4) Does an already-installed dependency solve it? 5) Can it be one line? 6) Only then the minimum code that works.
-- No unrequested abstractions, no boilerplate "for later", deletion over addition, fewest files, shortest working diff. Mark deliberate shortcuts with an `enigma:` comment naming the ceiling and upgrade path.
-- Levels (the user can switch any time, e.g. "be more lazy", "full", "ultra", or "stop minimal-code" to turn it off):
-  - **lite** - build what was asked, but name the lazier alternative in one line; the user picks.
-  - **full** - the ladder enforced: stdlib and native first, shortest diff and explanation. The default when enabled.
-  - **ultra** - YAGNI extremist: deletion before addition, ship the one-liner and challenge the rest of the requirement in the same response.
-- Never simplify away: input validation at trust boundaries, error handling that prevents data loss, security, accessibility, hardware calibration, or anything explicitly requested. Non-trivial logic leaves ONE runnable check behind (testing-policy owns test strategy).
-<!-- enigma:minimal-code:end -->
-
 <!-- enigma:recall:start -->
 ### Session Memory (Recall)
 

package/assets/memory/CLAUDE.md

@@ -18,6 +18,7 @@
 - dependency-policy: adding/upgrading/auditing dependencies, lockfiles, and supply-chain risk.
 - testing-policy, code-review-policy, debugging-policy, git-policy: tests and test-suite layout (structured subfolders, never a flat tests/ dump), pre-delivery review, debugging, and commits/PRs.
 - technical-writing-policy: any user-facing copy - UI labels, descriptions, hints, empty/error states, panel intros, README/doc prose - concise and realistic, no over-explaining or restating the obvious.
+- logo-sourcing-policy: adding any real brand/platform/technology logo or icon - source the official asset (never fabricate one), prefer SVG (WebP for web), keep brand colors, and check contrast.
 - task-completion-policy: long or multi-item tasks (1:1 ports, migrations, repo-wide changes) - work-unit inventory, persistent coverage ledger, and verified completion before any "done" claim.
 
 ### Always-On Rules (never skipped, even if no skill loads)
@@ -55,18 +56,6 @@
 - 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 -->
 
-<!-- enigma:minimal-code:start -->
-### Minimal Code (Anti-Overengineering)
-
-- Default to **{{minimal-level}}** minimal-code discipline (full detail in anti-overengineering-policy). The best code is the code never written; before writing any, stop at the first rung that holds: 1) Does this need to exist at all? (YAGNI) 2) Does the standard library do it? 3) Does a native platform feature cover it? 4) Does an already-installed dependency solve it? 5) Can it be one line? 6) Only then the minimum code that works.
-- No unrequested abstractions, no boilerplate "for later", deletion over addition, fewest files, shortest working diff. Mark deliberate shortcuts with an `enigma:` comment naming the ceiling and upgrade path.
-- Levels (the user can switch any time, e.g. "be more lazy", "full", "ultra", or "stop minimal-code" to turn it off):
-  - **lite** - build what was asked, but name the lazier alternative in one line; the user picks.
-  - **full** - the ladder enforced: stdlib and native first, shortest diff and explanation. The default when enabled.
-  - **ultra** - YAGNI extremist: deletion before addition, ship the one-liner and challenge the rest of the requirement in the same response.
-- Never simplify away: input validation at trust boundaries, error handling that prevents data loss, security, accessibility, hardware calibration, or anything explicitly requested. Non-trivial logic leaves ONE runnable check behind (testing-policy owns test strategy).
-<!-- enigma:minimal-code:end -->
-
 <!-- enigma:recall:start -->
 ### Session Memory (Recall)
 

package/assets/skills/anti-overengineering-policy/SKILL.md

@@ -85,16 +85,26 @@ deferred optimization stays visible and owned.
 
 ## Intensity (minimal-code setting)
 
-The aggressiveness is set by `enigma config minimal-code <off|lite|full|ultra>`
-(it edits the deployed memory file). When the user asks to be "more/less lazy"
-mid-session, follow that for the session.
+The aggressiveness is set by `enigma config minimal-code <off|lite|full|ultra>`,
+rendered into the active-configuration block below when this skill is deployed.
+When the user asks to be "more/less lazy" mid-session, follow that for the session.
 
 | Level | Behavior |
 |-------|----------|
+| **off** | Discipline is opt-in only: build what was asked without pushing minimalism, and apply the ladder only when the user explicitly asks to simplify. |
 | **lite** | Build what was asked, but name the lazier alternative in one line. The user picks. |
 | **full** | The ladder enforced: stdlib and native first, shortest diff, shortest explanation. The default when enabled. |
 | **ultra** | YAGNI extremist. Deletion before addition. Ship the one-liner and challenge the rest of the requirement in the same response. |
 
+<!-- enigma:config:start -->
+### Active configuration
+
+- **minimal-code** = `{{minimalCode}}` - apply this intensity (see the table above).
+
+This block is rendered by enigma from the user's `.enigma.json` at deploy time; do
+not edit it by hand (it is regenerated on the next sync).
+<!-- enigma:config:end -->
+
 Example - "Add a cache for these API responses":
 
 - lite: "Done. FYI: `functools.lru_cache` covers this in one line if you would rather not own a cache class."

package/assets/skills/anti-overengineering-policy/skill.json

@@ -1,9 +1,12 @@
 {
   "name": "anti-overengineering-policy",
-  "version": "1.2.0",
+  "version": "1.3.0",
   "provider": "FJRG2007/enigma",
   "description": "Minimal-code discipline - YAGNI ladder, deletion over addition, no unrequested abstractions, and the enigma: shortcut-marking convention; intensity via the minimal-code setting.",
-  "updated": "2026-06-25T17:21:31+02:00",
-  "cliVersion": "1.28.1",
-  "sha": "b9517e7d520e83a9f881fb1917ca2d4cec4aea4f2c5e753ea02641d9bc06c6b6"
+  "config": [
+    "minimalCode"
+  ],
+  "updated": "2026-07-16T23:37:57+02:00",
+  "cliVersion": "1.29.0",
+  "sha": "fe9eb12dc280fee88fba32265394c83bdedd4820b4c23048e716b0954034ab51"
 }

package/assets/skills/anti-overengineering-review/skill.json

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "On-demand over-engineering review - diff review, whole-repo audit, and enigma: debt-marker ledger (tags delete/stdlib/native/yagni/shrink, line/dep scoring); lists cuts, applies nothing.",
   "updated": "2026-06-16T11:24:30+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "f742a2be3f328b9ea1ff9a35a449177c2cbec35ad16e46f7054b7a873a2ab017"
 }

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

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Backend/API architecture: controller-service-repository layering, API and request optimization, server-side caching (Redis), and Zod boundary validation.",
   "updated": "2026-06-16T12:06:06+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "a46c3cd00aa5f47adb1e7907f1d2bc6f5562f7a272890dee9b1121976ac04ae1"
 }

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

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Ciphera code style conventions (formatting, naming, imports, comments, code-level anti-patterns; TypeScript-first, language-agnostic).",
   "updated": "2026-06-26T13:40:52+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "dc9ceb784004b05a0117c464e4bed05946835a04acea282586c0b735ee7c2284"
 }

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

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Pre-delivery self-review gate, prioritized review dimensions, and change-quality criteria.",
   "updated": "2026-06-01T00:45:28+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "3d3bbe0602d5bbb4afe37648fe3c2fa39376b1bcbac5d8c441f01fad1e866ed0"
 }

package/assets/skills/core-engineering-policy/SKILL.md

@@ -41,6 +41,7 @@ description: Highest-authority engineering rules - priority hierarchy, modular a
   - Any bug, crash, failing test, or unexpected behavior -> debugging-policy.
   - Any commit, branch, or pull request -> git-policy.
   - Any user-facing copy (UI labels, descriptions, hints, empty/error states, panel intros, README/doc prose) -> technical-writing-policy.
+  - Any logo or brand/technology icon added, embedded, or referenced (websites, READMEs, app UI, integration lists, tech-stack badges, social icons) -> logo-sourcing-policy.
   - Any long, multi-item, or porting/migration task (1:1 ports, "migrate all", repo-wide changes, work spanning many files or sessions) -> task-completion-policy.
 - When a task spans multiple domains, compose the relevant skills instead of re-deriving their rules.
 - Never duplicate a specialized skill's rules inside another skill; reference it.
@@ -87,6 +88,7 @@ This core policy owns orchestration, architecture, and the global rules. Each co
 - debugging-policy: reproduce-isolate-fix methodology and root-cause discipline.
 - git-policy: commits, branches, and pull request standards.
 - technical-writing-policy: concise, realistic user-facing copy - UI microcopy, labels, descriptions, hints, empty/error states, panel intros, and README/doc prose that informs without over-explaining, restating the obvious, or leaking implementation detail.
+- logo-sourcing-policy: source real brand/platform/technology logos instead of fabricating them - vendor brand kits and vector-logo registries, SVG (WebP for web) preference, official colors, and contrast-aware placement; color-conflict resolution via the logo-color-policy setting.
 - ciphera-style-policy: Ciphera code style conventions - formatting, naming, quotes, string interpolation, length-sorted imports, indentation, comments/JSDoc, and code-level anti-patterns (TypeScript-first, language-agnostic).
 - anti-overengineering-policy: minimal-code discipline - the YAGNI ladder (stdlib/native/installed-dependency/one-line before custom code), deletion over addition, no unrequested abstractions, the enigma: shortcut-marking convention, and intensity via the minimal-code setting. Owns the detail behind the Anti-Overengineering Rule below.
 - anti-overengineering-review: on-demand complexity-only review - diff review, whole-repo audit, and the enigma: debt-marker ledger (tags delete/stdlib/native/yagni/shrink, line/dep scoring). Lists cuts, applies nothing; correctness/security/performance stay with code-review-policy.

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

@@ -1,9 +1,9 @@
 {
   "name": "core-engineering-policy",
-  "version": "1.10.0",
+  "version": "1.11.0",
   "provider": "FJRG2007/enigma",
   "description": "Core engineering execution policy and harness orchestration (highest-authority rules).",
-  "updated": "2026-06-25T17:54:55+02:00",
-  "cliVersion": "1.28.1",
-  "sha": "5e68e2a25c8e3dac6251562062f7fe4c57143baaaee8fd6de83adca9ec24a6e6"
+  "updated": "2026-07-16T22:43:53+02:00",
+  "cliVersion": "1.29.0",
+  "sha": "d132f20db08806054d95e58d3d56c2aa7ebc8e6dd24d902b0a0ed9ddfae216c5"
 }

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

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Senior database architecture policy: query optimization, anti-duplication/normalization, scalability, and RGPD/GDPR encryption.",
   "updated": "2026-06-03T14:19:50+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "2883bcecb3202683ae6f81b073c3d6a9cec9c55029e011bdd06ba7ac3537297e"
 }

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

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Reproduce-isolate-fix debugging methodology with root-cause discipline and regression verification.",
   "updated": "2026-06-01T00:45:28+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "14b0064c8b33a0dc85e51464b05005cf5801c756b1101789a6924b9548420f6b"
 }

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

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Dependency and supply-chain security: lockfiles and reproducible installs, version pinning, vulnerability auditing, vetting/minimizing packages, vendoring, and SBOM/provenance.",
   "updated": "2026-06-01T00:45:28+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "6375d835c2aef2c9bd31ce116444dc3d796f510f9970a213aa3ac4696d7e21b9"
 }

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

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one.",
   "updated": "2026-06-25T15:51:43-04:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "fb78be3233bf9caa67d1f522c19831542b23f47e440b02211b5a950c898318b9"
 }

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

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Frontend architecture: reusable components, abstraction thresholds, state management, no-op save detection, large-list rendering (infinite scroll/pagination, virtualization, skeletons, progressive loading), and optimistic UI with rollback.",
   "updated": "2026-06-26T13:57:02+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "41cb938c9022efcdadc3056417cc7d442511adee40b09a141f11bb5fd9d56514"
 }

package/assets/skills/git-policy/SKILL.md

@@ -25,6 +25,16 @@ description: Commit, branch, and pull request standards - conventional commits,
 
 ---
 
+## Branch Cleanup
+
+- Short-lived topic branches (fix/*, feat/*, chore/*) created for one change are disposable. Once that change has landed in the default branch - or the branch is otherwise dead (abandoned experiment, superseded work) - delete it, both local and remote, so the branch list does not rot.
+- Delete a branch only when its work is safely preserved. Safe: the branch is fully merged into the default branch (`git branch --merged <default>` lists it). Careful: a squash-merged or rebase-merged branch does NOT show up as merged even though its content is already in the default branch - confirm the change is really there (compare content, or check the merged PR) before deleting.
+- When in ANY doubt that a branch still holds unmerged, unreleased, or otherwise relevant commits, do NOT delete it - ask the user first. Leaving a stale branch is cheap; losing a branch that held unique work is not.
+- Never delete a protected or long-lived branch (the default branch, release/*, or any branch the repo marks as protected) unless the user explicitly asks.
+- Prune deleted upstreams periodically with `git fetch --prune` so gone remote branches stop lingering locally.
+
+---
+
 ## Cloning & Fetch Efficiency
 
 - When cloning or pulling a repository, do not fetch the full history unless it is actually needed. A shallow fetch saves disk space, bandwidth, and time.

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

@@ -1,9 +1,9 @@
 {
   "name": "git-policy",
-  "version": "1.4.0",
+  "version": "1.5.0",
   "provider": "FJRG2007/enigma",
   "description": "Git & contribution policy (senior engineering standards).",
-  "updated": "2026-06-25T17:14:54+02:00",
-  "cliVersion": "1.28.1",
-  "sha": "9298bf572c6186de65bfae5cc008af247731fac3e07d9320ddfc12fe886d6afe"
+  "updated": "2026-07-16T22:44:02+02:00",
+  "cliVersion": "1.29.0",
+  "sha": "e6dfbc33884000d9d25841bd9c5a84d6558ffd374882cb7b34451eb2cebc2161"
 }

package/assets/skills/logo-sourcing-policy/SKILL.md

@@ -0,0 +1,110 @@
+---
+name: logo-sourcing-policy
+description: Source real brand, product, platform, and technology logos instead of fabricating them - search the web and vector-logo registries (Simple Icons, svgl, worldvectorlogo, cdnlogo, Iconify, devicon, the vendor's own brand/press kit), prefer SVG (and optimized WebP for web targets), keep official brand colors, and check contrast so a monochrome logo does not vanish on a matching background. Use whenever adding, embedding, or referencing a logo or brand/technology icon in any project - websites, READMEs, app UI, integration lists, tech-stack badges, social icons, footers, or splash/marketing pages. Color-conflict resolution follows the logo-color-policy setting (ask|adapt-background|adapt-logo).
+---
+
+# Logo Sourcing Policy
+
+Models fabricate the logos of real companies, products, platforms, and
+technologies: they invent a plausible-looking mark, guess the wrong shape or
+colors, or draw an outdated version. A fabricated brand logo is wrong output -
+it misrepresents a trademark and looks amateur. This skill's rule is simple:
+**never draw a real logo from memory - find the official asset.**
+
+## The Rule
+
+- If a task needs the logo or brand icon of a real entity (a company, product,
+  platform, framework, language, tool, social network, payment provider, etc.),
+  SOURCE the real asset. Do not redraw it, approximate it, or emit hand-written
+  SVG path data for it from memory.
+- The only marks you may author are ones that do not exist yet: the user's own
+  project logo, a generic/placeholder glyph, or an abstract icon they asked you
+  to design.
+- When you cannot obtain the real asset (no web access, not in any installed
+  package, unclear which variant), ask the user for it or leave a clearly
+  marked placeholder. Never fill the gap with an invented logo.
+
+## Where to Source (in order)
+
+1. **The vendor's own brand / press kit.** The authoritative source, and the
+   one that respects trademark guidelines. Search "<brand> brand assets" /
+   "<brand> press kit" / "<brand> logo svg". Many host a downloadable SVG.
+2. **Curated vector-logo registries** (prefer these for breadth and SVG):
+   - Simple Icons - `simpleicons.org` (npm `simple-icons`, CDN via jsdelivr) - monochrome brand SVGs, huge coverage.
+   - svgl - `svgl.app` - modern, often includes light/dark variants.
+   - worldvectorlogo - `worldvectorlogo.com`, VectorLogoZone - `vectorlogo.zone`.
+   - cdnlogo - `cdnlogo.com`, seeklogo - `seeklogo.com`.
+   - Iconify - `iconify.design` (the `logos` set by gilbarbara, `simple-icons`, `devicon`) - one API for many logo sets.
+   - devicon - `devicon.dev` - developer/technology stack logos (languages, frameworks, tools).
+   - browser-logos - `github.com/alrra/browser-logos` (the cdnjs mirror) for browsers.
+3. **An already-installed icon package** when the project has one - `react-icons`
+   (`si`/`fa` sets), `simple-icons`, `@iconify/*`, `lucide`/`devicons`. Reuse it
+   instead of fetching a file (dependency-policy owns adding a NEW one).
+4. **A general web/image search** as the fallback - but verify you grabbed the
+   genuine current logo, not a fan edit, a competitor, or an old version.
+
+Prefer the web when available; you may fetch and inspect these sources. If the
+runtime has no web access, drop to an installed package, then to asking the user.
+
+## Format Preference
+
+- **SVG first**, always, when the target supports it: scalable, tiny, and its
+  colors are editable in the markup (which the contrast check below needs).
+- **For web or WebP-capable targets**, when a raster is genuinely required
+  (a photo-real mark, a complex multi-gradient logo, or a surface that cannot
+  embed SVG), prefer an optimized **WebP** (or AVIF) over PNG - it is smaller
+  and loads faster. Keep a PNG fallback only if the target needs one.
+- Never use JPEG for a logo (block artifacts, no transparency).
+- Keep the asset at the resolution the layout needs; do not upscale a small
+  raster - fetch a vector or a larger source instead.
+
+## Color and Contrast
+
+Placing a logo without checking contrast produces an invisible mark - e.g. the
+Apple logo is solid black or white, so a white Apple logo on a white background
+disappears.
+
+- When the asset is SVG, READ its `fill`/`stroke`/`stop-color`/`currentColor`
+  to learn its real colors. A single-color mark (all one `fill`, or driven by
+  `currentColor`) is monochrome and WILL clash with a same-tone background.
+- Know the brand's official colors and preserve them; brand fidelity matters.
+  Many brands publish a full-color, a solid-black, and a solid-white variant -
+  pick the variant that fits the surface rather than recoloring the full-color
+  one.
+- Ensure the placed logo meets a visible contrast against its actual background
+  before shipping it.
+
+When a monochrome logo would clash with its background, resolve it per the
+**logo-color-policy** setting (`enigma config logo-color-policy`):
+
+| Value | Behavior |
+|-------|----------|
+| **ask** (default) | Stop and ask the user how to resolve it - recolor the background, add a container/badge behind the logo, swap to a different brand variant, or recolor the logo. Do not silently pick one. |
+| **adapt-background** | Auto-resolve by giving the logo a contrasting container/background (a chip, card, or badge) and KEEP the logo's official colors. Preferred for brand fidelity. |
+| **adapt-logo** | Auto-resolve by switching to the brand's opposite monochrome variant (or recoloring the mark) so it fits the existing background. |
+
+The active mode is rendered into the block below when this skill is deployed, so
+you always know which one applies without reading config.
+
+<!-- enigma:config:start -->
+### Active configuration
+
+- **logo-color-policy** = `{{logoColorPolicy}}` - resolve a contrast clash using this mode.
+
+This block is rendered by enigma from the user's `.enigma.json` at deploy time; do
+not edit it by hand (it is regenerated on the next sync).
+<!-- enigma:config:end -->
+
+## Trademark Respect
+
+Brand logos are trademarks. Follow the brand's usage guidelines: respect clear
+space, do not distort, stretch, or rotate the mark, and do not recolor it beyond
+the contrast resolution above (and even then, prefer an official variant). Use
+each logo only to identify the real product it represents.
+
+## Boundaries
+
+This skill governs sourcing and placing REAL logos. Designing an original
+project logo or a generic icon is normal creative work and is out of scope.
+Adding a NEW icon dependency is owned by dependency-policy; visual/layout
+design is owned by frontend-design.

package/assets/skills/logo-sourcing-policy/skill.json

@@ -0,0 +1,12 @@
+{
+  "name": "logo-sourcing-policy",
+  "version": "1.1.0",
+  "provider": "FJRG2007/enigma",
+  "description": "Source real brand/platform/technology logos instead of inventing them - vector-logo registries and vendor brand kits, SVG (WebP for web) preference, official colors, and contrast-aware placement; color-conflict resolution via the logo-color-policy setting.",
+  "config": [
+    "logoColorPolicy"
+  ],
+  "updated": "2026-07-16T23:37:57+02:00",
+  "cliVersion": "1.29.0",
+  "sha": "e2c8b8898ab02d3e6b337533dfb1a955c30a4f5a33f0fb67e738ca3cb35eeac7"
+}

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

@@ -4,6 +4,6 @@
   "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.",
   "updated": "2026-06-01T00:45:28+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "9971e9d9127397d0152e89d24aad3191e2935e55a8483db7fd15f5d4d7a60e7a"
 }

package/assets/skills/skill-creator/skill.json

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Create new skills, modify and improve existing skills, and measure skill performance with evals and benchmarks.",
   "updated": "2026-06-16T16:39:13+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "699586cce82ec0a5458288b598ee7e5ebdddb3dfcf19db354d8bc5e85e47c1c7"
 }

package/assets/skills/task-completion-policy/skill.json

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Exhaustive completion discipline for long/multi-item tasks - inventory, coverage ledger, verified done.",
   "updated": "2026-06-10T22:11:09+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "6e3facba307eb2b55cefbab2e4b2a346a2b82f93c3ef47e11ebeb78c3c9453a8"
 }

package/assets/skills/technical-writing-policy/skill.json

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Concise, realistic technical copy - UI microcopy, descriptions, hints, empty/error states, and README/doc prose that informs without over-explaining or restating the obvious.",
   "updated": "2026-06-26T14:09:06+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "e750988b8de51d8a69be621673dceca5413ebad7e1a48e40acd18aad526d9928"
 }

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

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Test strategy, coverage gates, deterministic tests, mocking discipline, regression-first bug fixing, and test-suite organization (layout by type/domain, mirrored paths, file naming, fixture/helper placement).",
   "updated": "2026-06-16T17:11:49+02:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "3bdf591057b760f674fb2b1425f63acb426cda2c4f042e1a74c5a5d3807df664"
 }

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

@@ -4,6 +4,6 @@
   "provider": "FJRG2007/enigma",
   "description": "Strict frontend + backend schema validation, schema consistency, and safe client-facing error handling.",
   "updated": "2026-06-25T18:21:50-04:00",
-  "cliVersion": "1.28.1",
+  "cliVersion": "1.29.0",
   "sha": "50349f5b3c55cc337f828dd510c163550614832acb28714871210a7c115a1501"
 }

package/bin/checksums.json

@@ -1,6 +1,6 @@
 {
-  "enigma-darwin-arm64": "973b7408eb848a08efa11f954c27df875b651c7b211b75576bf5434f64d5e889",
-  "enigma-linux-arm64": "b5c0bd3b04395bd4bf6310c4afb168a54a7bbc876778a4b7a4c64eaf9f258cba",
-  "enigma-linux-x64": "2ea0381859109c1aa3d2c908a486285bac9044587d3f99ed4e12aeb28ce8d06d",
-  "enigma-win32-x64.exe": "8f7054b16fe80954d8e38d9cdbd776e747060bddc9f65dd063c1bac3f723326a"
+  "enigma-darwin-arm64": "c52f05f96a6bf94d1e8b49bc6254129c891205044f9ff93896ad0bec7a02860d",
+  "enigma-linux-arm64": "9fa10c39807a135737e2c3282b177314cdf17f45ab3a0ed12840999e100d120c",
+  "enigma-linux-x64": "7875a966d0c28a44060a2ce4d27895175455ce5cc547426751600896d9416dd2",
+  "enigma-win32-x64.exe": "9bf80ef1a2c62c90b1412235e3099a0a6d83047a5db4f1d42f6b146562f4149f"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "enigma-cli",
-  "version": "1.28.1",
+  "version": "1.29.0",
   "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": {