chore(deps): update all dependencies

[gw0-bot]

This PR contains the following updates:

Package	Change	Age	Confidence	Type	Update
@anthropic-ai/claude-code	2.1.233 → 2.1.238				patch
docker.io/oven/bun	1.3.14-slim → 1.4.0-slim			final	minor
docker/setup-buildx-action (changelog)	bb05f3f → 37fe631			action	digest
sickn33/agentic-awesome-skills	15.14.0 → 15.16.0				minor

---

Release Notes

anthropics/claude-code (@​anthropic-ai/claude-code)

v2.1.238

Compare Source

• Added a keybindingFlavor setting: set it to "readline" to make Ctrl+W in the prompt delete back to the previous whitespace, as in Bash; the default ("classic") is unchanged
• Plugin marketplaces: headersHelper on a url marketplace or a catalog entry runs a command that mints HTTP headers (e.g. a short-lived token) for catalog and same-origin archive fetches
• A catalog entry's headersHelper runs only when you install or update that plugin, after its command is shown; claude plugin install/update ask [y/N] (or pass -y)
• Added claude self-hosted-runner --defer-shutdown-max-min <minutes>: on SIGTERM, keep serving attached sessions, park what is left after that many minutes, then exit
• Added claude self-hosted-runner --proxy-authorization-command / --proxy-authorization-file for egress proxies that require a freshly issued Proxy-Authorization header on every connection
• Fixed unbounded memory growth in long interactive sessions: subagent tool results are now released once they leave the recent display window
• Fixed custom, project, and plugin output styles drifting back to the default voice mid-session
• Fixed CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION=true not keeping prompt suggestions on when your account is near, but not over, its usage limit
• Fixed worktree-isolation Bash refusals telling you to remove a redirect when the command had none
• Fixed self-hosted runners occasionally being removed by the server after a single slow or lost poll request, handing their healthy session to another runner
• Fixed MCP elicitation dialogs showing nothing for URLs longer than 4,096 characters, and permission prompts dropping the "don't ask again" option when the project path didn't fit the terminal width
• Fixed leftover /tmp/claude-*-cwd files when a Bash command is killed, times out, or is interrupted
• Fixed held Backspace being ignored on terminals that send Ctrl+H for Backspace when keystrokes arrive in large bursts (slow SSH/mosh links)
• Fixed text-wrapping in permission prompt diffs: lines containing wide multi-code-point characters (such as emoji) or tabs are no longer clipped
• Fixed killing a suspended (Ctrl+Z) session sometimes leaving the terminal in bracketed-paste mode with the cursor hidden
• Fixed stdio MCP servers receiving a server/discover request before initialize, forcing lazy servers to start their backend on every session open
• Fixed a proxy's refusal of a connection being reported as a generic network error instead of naming the proxy
• Fixed the /model and /effort cache-miss warning appearing when the prompt cache had already expired
• Fixed per-task Stop from the Remote Control tasks panel doing nothing on CLI-hosted sessions
• Fixed remote sessions exiting when a client delivered a user message without a valid role
• Fixed Remote Control sessions started by claude remote-control inheriting session-scoped environment variables from the launching shell
• Fixed a Remote Control session whose process crashed staying unavailable until claude remote-control was restarted; it can now be reused when you next message it
• Fixed Remote Control messages sent from the web or Desktop while Claude is mid-turn disappearing from the transcript after the turn finishes
• Fixed Remote Control model picks made on a phone or web not updating the model shown in the terminal
• Fixed Remote Control disconnecting with "login expired" when a brief network hiccup delays renewing your sign-in; it now retries and stays connected
• Fixed Remote Control reporting a failed reconnect on sign-out; signing out now ends the session with a clear message
• Fixed ListAgents/SendMessage reporting "Remote Control is not connected" in sessions run by claude remote-control (server mode) or Desktop/IDE hosts; they now list and reach Remote Control peers
• Fixed ListAgents and SendMessage exposing the idle worker that the agent view pre-warms for your next background session; it now appears only once a task claims it
• Cross-session messaging: sending to a session on this machine that refuses inbound messages (e.g. crossSessionInbound: "refuse") now reports "refused" to the sender instead of a silent success
• Cross-session messaging: a session whose inbox drops your messages (rate limit or full queue) now tells your session, instead of the messages vanishing silently
• Improved startup: bare claude starts sooner on macOS
• Improved Bash tool permission checking for zsh-specific syntax in shell conditionals
• Improved Remote Control connection resilience: brief HTTP 403 refusals from a network edge, VPN, or proxy are now tolerated for up to 3 minutes, with the refusing party named when a block persists
• Improved startup responsiveness: the automatic update check now runs about 10 seconds after launch instead of competing with startup for CPU
• Updated the bundled claude-api skill for the Managed Agents Aug 19 release: web search/fetch domain settings and memory stores on self-hosted sandboxes
• Changed Ctrl+L and Cmd+K in fullscreen to always just repaint — the double-press /clear shortcut was removed, and 1-row nvim terminals no longer trigger automatic /clear loops
• Changed claude mcp list and claude mcp get to show disabled servers as ⊘ Disabled instead of connecting to them for a health check
• MCP headersHelper in a project .mcp.json, and inline MCP servers in project or --add-dir agent files, now require that folder's trust dialog to have been accepted (also under claude -p)
• MCP headersHelper from a project .mcp.json, plugin, or agent file runs without inherited credential env vars; user, managed and claude.ai-scope helpers now run from the Claude config dir

v2.1.237

Compare Source

• Fixed prompt caching for sessions using an LLM gateway or custom base URL
• Added a built-in "Concise" output style: Claude leads with results and skips preamble and narration, while doing the work just as thoroughly. Select it under Output style in /config.

v2.1.236

Compare Source

• Added ANTHROPIC_DEFAULT_MODEL environment variable: sets the model new sessions start on, while a /model pick still overrides it and persists across restarts (unlike ANTHROPIC_MODEL)
• Added notify_when_idle to cross-session SendMessage: ask another Claude Code session on this machine to send one notice when it next goes idle — opt-in, one-shot, no polling (macOS and Linux)
• Sandbox: on macOS, wildcard read-deny rules (e.g. **/.env) now take precedence inside allowed read regions, cover matched directories' contents, and can't be bypassed by renaming the denied file
• Fixed clipboard copy, background housekeeping, background sessions, and local MCP logs breaking after the directory a session had switched into was removed (since 2.1.229)
• Fixed the fullscreen renderer failing permanently after a single failed start: it now falls back to the classic renderer instead of exiting on every subsequent launch
• Fixed the /model picker rendering taller than the terminal: it now shows only as many models as fit the window, with the rest reachable by scrolling
• Fixed SendMessage calls being rejected when a malformed closing tag left the message text inside the summary field
• Fixed unhandled promise rejections when a subprocess fails to start, for example powershell.exe on WSL with Windows interop disabled (regression in 2.1.234)
• Fixed fullscreen mode sometimes not showing a newly sent message until the next update after the terminal was resized
• Fixed a blank band that could remain above the prompt after clearing a multi-line prompt, and panes not repainting after resizing the terminal away and back, in fullscreen mode
• Fixed the managed-settings approval prompt sometimes not appearing at startup while still capturing the first keypress as approval
• Fixed terminal tab titles jumping in tmux (iTerm tmux integration): the title is now written only when its text changes instead of animating every 960ms
• Fixed an unclear error when the cloud environments list came back empty or malformed
• Fixed the Fable 5 first-time usage-credits prompt auto-selecting the fallback model after 60 seconds with no answer when using Remote Control
• Fixed spinner tips never appearing, with a repeated background error, when the cached guest-pass reward in ~/.claude.json was malformed
• Fixed skills hot-reload in SDK/VS Code sessions raising an error on every skills change after the session's working directory was deleted (2.1.229+)
• Fixed self-hosted runner sessions released on idle, retire, or startup timeout occasionally resuming on another runner before the post-session hook had finished
• Fixed the Clawd mascot's eyes and feet rendering unevenly in iTerm2 at some font sizes
• Fixed occasional runaway session recaps: recap text (automatic and /recap) is now capped at 400 characters, cut at a word boundary
• Improved startup performance: the session counter is now written in the background
• Improved auto mode: Monitor allow rules are now set aside while auto mode is active, so Monitor commands are reviewed the same way Bash commands are
• Improved auto mode on Bedrock, Vertex AI, and Foundry, and when telemetry is disabled: the classifier now uses the same defaults as on the Claude API, including severity-scored classification
• Improved auto mode: the git status check can no longer be fooled by a repo's status.showUntrackedFiles=no setting into reporting a clean tree
• Changed the /model picker to highlight only the newest model's name, so the highlight marks the new release rather than an arbitrary subset of the list
• /goal: an idle session whose goal is parked behind long-running background work now checks in automatically after 30 minutes (then 1h, 2h) instead of waiting for you to return
• /usage now shows the usage-credits spend row for Team and Enterprise members, and shows a capped row at 0% before anything is spent
• SIGTERM in print/SDK mode no longer records an interrupted turn or synthetic tool denials before exiting; running commands are still terminated and the process still exits with code 143
• Pressing Enter on a slash-command typo or a command unavailable in this session now reports it instead of running the closest fuzzy match; prefixes and aliases still run
• Remote Control now marks a session offline within seconds when the CLI exits or its terminal closes
• SendMessage now refuses further messages to a session up front once a rapid burst would exceed what that session's inbox accepts, instead of reporting them sent while they were dropped
• Aligned the session title chip on the prompt border with the footer's right edge
• Right-aligned footer items (goal indicator, session state, background agent status) and truncated notices now share a consistent right margin with the rest of the prompt area
• [VSCode] Added screen reader support for the transcript: live announcements for replies, permission requests, errors, and status changes, plus per-turn heading navigation

v2.1.235

Compare Source

• Added an optional spellcheck setting that underlines misspelled words in the prompt input as you type, using your installed aspell, hunspell, or ispell
• Fixed whole-prompt-cache invalidation when a language server disconnected or reconnected mid-session
• Fixed nested markdown list items misaligning at depth 3+ and added a hanging indent to wrapped list items in the terminal UI
• Fixed prompt input highlights (slash commands, keywords, mentions) appearing shifted by one or more characters in some multi-line prompts
• Fixed Shift+Tab inside the permission prompt's comment field approving the edit and granting session-wide edit permission instead of closing the field
• Fixed the Agent tool advertising a general-purpose default in sessions where that agent is unavailable: an omitted subagent_type there now gets a clear error listing the available agents
• Fixed notebook cell delete/replace approval dialogs silently omitting the existing cell content when the notebook or cell could not be read; the dialog now says why
• Fixed slash commands run while Claude is responding showing HTML entities instead of the actual characters
• Fixed the prompt footer not showing the "Update installed" restart notice after a background auto-update
• Fixed the expanded task list (ctrl+t) always starting collapsed when resuming or relaunching into a session that still has open tasks
• Improved memory and CPU usage while cloud sessions such as /ultrareview or /autofix-pr run in the background — their event streams are no longer re-scanned and re-rendered on every update
• Improved permission dialogs: display text and "don't ask again" options now always match what a grant would cover, and "don't ask again" is withheld when contents cannot be fully displayed
• Improved the embedded grep in native macOS/Linux builds: pathological patterns now fail fast instead of exhausting memory, and -m N with -A/-C prints correct context
• Improved the context-limit error to say when auto-compact is off and point to /config to re-enable it
• Vim mode: NORMAL mode and cursor position are now preserved when toggling the detailed transcript (ctrl+o) or closing a panel
• Dialogs: arrow keys and Enter pressed in quick succession now select the option you navigated to instead of the previously highlighted one
• SendMessage now refuses messages too large for cross-session delivery up front instead of silently dropping them
• Remote Control: claude rc now applies the same enterprise-gateway availability check as interactive startup
• [VSCode] Fixed focus jumping between open Claude tabs on its own when a window with several Claude panels is restored or reloaded

v2.1.234

Compare Source

• Added the optional CLAUDE_CODE_PROJECT_DIR_NAME environment variable: hosts that give each session its own config directory can choose a short name for the per-project transcript directory
• Added the selection:clear keybinding action, so a key can be bound to clear an in-app text selection; also works in the agents view
• Added a GitLab merge request badge to the footer and statusline: repos with a GitLab remote and an authenticated glab CLI show MR !N with draft/pending/green states
• Claude Code now continues your session automatically when a claude.ai usage limit resets; turn it off in /config ("Continue automatically at usage limit")
• Claude is now told to use your account email only to identify you, and not to send it to unrelated services unless you ask
• Security: remote file reads, session restore, CLAUDE.md includes, workflow scripts and file uploads now reject Windows NT-namespace (\??\) paths, hardening the remaining pre-approval file accesses against the NTLM credential-leak vector
• Fixed auto mode in very long sessions repeatedly re-checking and denying sandboxed commands' network access after the conversation had been compacted
• Fixed session-scoped permission answers (including denies) being dropped when answering background subagent tool permission prompts
• Fixed a crash when an API response on the non-streaming fallback path (typically via third-party gateways) contained a thinking block missing its thinking field or a text block missing its text field
• Fixed markdown rendering becoming extremely slow for some messages containing unusual Unicode sequences
• Fixed SendMessage rejecting a recipient copied from ListAgents when the session name is at the 200-character cap or emoji-heavy
• Fixed repository detection mis-reading the host of git remotes with unusual userinfo, producing links and repo-specific behavior for the wrong host
• Fixed MCP diagnostics printing resolved secrets: scope-conflict warnings now show the configured ${VAR} form, and connection-failure details show only the server origin
• Fixed strictKnownMarketplaces allowlists accepting SCP-style git marketplace sources whose host differs from the one git would actually connect to
• Fixed modal text such as the /login OAuth URL losing characters when copied in fullscreen
• Fixed a --- horizontal rule in rendered markdown running into the line after it
• Fixed consecutive shell commands splitting into multiple "Ran 1 shell command" rows when todo/task updates were interleaved between them
• Fixed dialogs like /permissions opened while a ! shell command was running being dismissed when the command finished
• Fixed a queued ! shell command being sent to the model as plain text after pressing up-arrow to edit the queued input
• Fixed queued messages reappearing in the prompt history while still queued, Esc while selecting a queued message no longer interrupts the turn, and ! mode no longer sticks after a mid-turn submit
• Fixed accepting the "Try the new fullscreen renderer?" prompt restarting the session without its permission mode (e.g. --dangerously-skip-permissions), tool allow/deny rules, model or effort flags
• Fixed /tui dropping launch --allowed-tools/--disallowed-tools rules when it restarts; it now declines to switch, with the reason, when the session has restrictions a restart can't carry over
• Fixed trust prompts omitting the repository-wide scope warning when the directory was first seen before the repository existed there
• Fixed a case where an IDE diff tab closing during a permission re-prompt could answer the new prompt with the previous input
• Fixed: files sent to the user during Remote Control sessions hosted by Claude Code Desktop or VS Code now upload, so they open on phone and web instead of showing an empty card
• Fixed: after /login while CLAUDE_CODE_OAUTH_TOKEN is set, the stale-token reminder no longer leaks into Claude's automatically resumed turn — it now appears only to you
• Fixed: permission previews now relay only to channel servers admitted by the inbound trust gate, and a server's explicit permission-capability opt-out is honored
• Fixed: credential masking on relayed permission previews can no longer hide commands, paths, or destinations from the approver; oversized private-key blocks now redact under full-strength redaction
• Fixed: provider API tokens that mask on permission previews now mask even when directly followed by shell delimiters
• Fixed Claude Desktop inter-session messages being silently dropped by the recipient session when cross-session messaging read as disabled, which left the sender's query "thinking" for many minutes
• Remote Control: signing this computer in to a different claude.ai account or organization now stops the running session within seconds and says why, instead of a misleading HTTP 404 hours later
• Remote Control sessions started from Claude Code Desktop or VS Code now keep phones and claude.ai/code updated on the session's permission mode (and claude.ai/code on the model) as they change
• Remote Control: effort picks made on a phone or on claude.ai/code now apply to terminal- and Desktop/VS Code-hosted sessions, and the session publishes its effort level to connected clients
• SendMessage and ListAgents now say when your account's session list was too long to check completely, instead of treating unseen sessions as absent
• Expired Anthropic profile credential now points you at /login when a claude.ai login would take precedence
• Improved the transcript: your own prompts now render markdown (highlighted code blocks, inline code, lists) the same way replies do
• Improved the "API returned an empty or malformed response" error to say what came back (content type, body kind, size, request ID) and why the original streaming request failed
• Improved auto-generated session titles to read as short, specific names (e.g. "Login button bug") rather than sentences restating your request (e.g. "Fix the login button on mobile")
• Reduced the context cost of loading the built-in claude-api skill from ~200k+ tokens to ~25k by loading reference docs on demand
• /permissions can now be opened while Claude is working — rule changes apply to the rest of the current turn
• /add-dir <path> can now be used while Claude is working; /add-dir, /autocompact, /theme, /help, /config and /advisor dialogs open mid-turn in the fullscreen TUI
• /goal now clears itself with a notice when a turn dies on an unrecoverable error (e.g. revoked auth, an exhausted credit balance, or a context overflow) instead of staying armed
• /goal: when background tasks keep a goal waiting for 30+ minutes, Claude now checks in on them instead of waiting indefinitely (set CLAUDE_CODE_GOAL_CHECKIN_MINUTES=0 to opt out)
• claude setup-token now rejects unexpected extra arguments instead of silently ignoring them
• Changed Esc in fullscreen mode to no longer clear a mouse text selection: it interrupts or dismisses as usual and the selection stays highlighted
• Removed the redundant "Allowed by auto mode classifier" line that auto mode showed under every Agent tool call
• Removed the "Default teammate model" setting from /config; agent-team teammates now use the leader's model unless the spawn names one
• Dimmed the elapsed-time counter on the running tool header so it no longer competes with the bold counts
• Background task notifications delivered between turns are now sent to the model inside <system-reminder> tags, matching mid-turn delivery
• Mantle: skip the admin-pin availability probe at startup when a main-loop model is already picked
• Windows: startup no longer stalls on repeated rename retries when ~/.claude.json is read-only

sickn33/agentic-awesome-skills (sickn33/agentic-awesome-skills)

v15.16.0

Compare Source

[15.16.0] - 2026-08-20 - "Agent Reliability, Evidence Integrity, and Stack Audits"

Added six focused skills for asynchronous C++ networking, controlled agent
fault injection, run-evidence auditing, orchestration review, measurable UI
quality, and multi-source research, while adding cross-artifact stack checks
and modernizing YouTube transcript extraction. The published catalog contains
2,025 skills.

This release helps Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and
related AI coding assistants test agent harnesses safely, distinguish run claims
from inspectable evidence, review multi-agent control flow, score recurring UI
failure modes, and keep research conclusions honest when sources disagree.

Start here:

• Install: npx agentic-awesome-skills
• agent-harness-fault-injection for
  bounded resilience testing with explicit cleanup and recovery gates.
• audit-agent-run-evidence for tracing
  agent-run claims back to logs, traces, artifacts, and reproducible checks.
• multi-source-search for provider-optional
  research backed by an offline, schema-validated evidence ledger.
• Choose your tool
• Bundles

Added

• Added boost-asio-pro for production-oriented
  asynchronous C++ networking with Boost.Asio, including composed operations,
  cancellation, coroutine lifetimes, strands, backpressure, and testable error
  paths (#​1186).
• Added
  agent-harness-fault-injection for
  controlled timeouts, malformed outputs, partial failures, and recovery checks
  with explicit blast-radius, consent, rollback, and evidence requirements
  (#​1189).
• Added audit-agent-run-evidence for
  read-only auditing of agent-run claims against recorded events, artifacts,
  timestamps, identifiers, and reproducible verification steps
  (#​1192).
• Added
  review-multi-agent-orchestration
  for reviewing delegation boundaries, shared-state hazards, handoff contracts,
  retry behavior, convergence, and evidence quality in multi-agent systems
  (#​1193).
• Added ui-slop-score for scoring recurring generic
  interface patterns against a concrete product brief, reference evidence,
  accessibility constraints, and a transparent weighted rubric
  (#​1196).
• Added multi-source-search for bounded research
  across optional providers with claim-level citations, source polarity,
  conflict tracking, URL canonicalization, and an offline validation script
  (#​1202,
  #​1205).

Changed

• Added a read-only aas stack audit flow and paired browser-local Workbench
  comparison for detecting digest, catalog, target, and exact skill-set drift
  between stack artifacts without applying either stack
  (#​1199).
• Updated the YouTube transcript extractor for both legacy 0.6.x and modern 1.x
  youtube-transcript-api interfaces, common YouTube URL forms, and UTF-8 output
  on legacy Windows consoles, with isolated network-free regression tests
  (#​1198).
• Hardened multi-source evidence validation so every source is classified as
  supporting or contradicting, conflicts agree with that classification, and
  superficial URL variants cannot inflate source diversity
  (#​1205).
• Regenerated the canonical catalog, offline AAS Core data, web assets,
  marketplaces, editorial bundles, compatibility reports, and Codex/Claude
  plugin distributions for 2,025 skills.

Security

• Kept fault injection opt-in, bounded to an approved environment, and gated by
  explicit preconditions, abort thresholds, rollback, recovery verification,
  and evidence capture before any resilience claim is accepted.
• Kept run-evidence and orchestration review read-only by default: neither skill
  treats missing telemetry as success or authorizes repairs, retries, or
  production actions without a separate user-approved step.
• Kept multi-source provider access optional and explicit, with credentials out
  of report artifacts and an offline validator that fails closed on missing
  evidence, inconsistent conflict state, or duplicate canonical sources.
• Kept stack comparison local and non-applying; artifact mismatches are reported
  before any installation or workspace mutation can be considered.

Who should care

• C++ teams building asynchronous network services that need explicit lifetime,
  cancellation, serialization, backpressure, and shutdown contracts.
• Agent-platform teams testing failure recovery or auditing whether reported run
  outcomes are actually supported by durable evidence.
• Multi-agent system owners reviewing delegation, shared-state, retry, and
  convergence risks before expanding autonomy.
• Product and design teams that want a repeatable anti-generic UI score tied to
  a real brief rather than subjective aesthetic claims.
• Researchers and maintainers who need conflict-aware multi-source reports and
  exact stack-artifact drift detection.

Validation

• Passed repository validation, reference validation, documentation-security
  checks, warning-budget enforcement, the complete repository test suite,
  plugin-compatibility and bundle checks, web-app install/build/prerender, and
  the npm package dry run on the protected release base.
• Reviewed all six added skills and their bundled files for semantics, safety,
  provenance, declared risk, limitations, consent boundaries, and relevant
  regression coverage; also reviewed the YouTube compatibility and stack-audit
  changes against their isolated tests.

Limitations

• Fault injection can demonstrate behavior only in the tested environment and
  scenario; it does not prove resilience to untested failures or authorize
  experiments against production systems.
• Evidence audits and orchestration reviews expose unsupported claims and
  control-flow risks but do not reconstruct missing telemetry or implement the
  fixes they recommend.
• ui-slop-score is a transparent heuristic tied to supplied references and
  constraints, not an objective guarantee of visual quality or user success.
• Multi-source research still depends on source availability and provider
  access; source count cannot replace source quality, and unresolved conflicts
  remain unresolved in the final report.
• Stack audit detects artifact drift but intentionally does not choose a winner
  or mutate an installation.

Credits

• @​alexprivalov for
  boost-asio-pro in
  PR #​1186.
• @​Whxuan0701 for
  agent-harness-fault-injection,
  audit-agent-run-evidence,
  review-multi-agent-orchestration,
  and the paired stack-audit source contributions in
  PRs #​1189, #​1192, #​1193, and #​1199.
• @​FrancoStino and the official
  uizze/uizze source for
  ui-slop-score in
  PR #​1196.
• @​Kormix760 for the modern YouTube
  transcript API compatibility repair ported in
  PR #​1198.
• @​liyangbing and
  @​denial123789 for
  multi-source-search and its evidence-integrity
  follow-up in PR #​1202
  and PR #​1205.

v15.15.0

Compare Source

[15.15.0] - 2026-08-18 - "Evidence, Durable Context, and UI Contracts"

Added six focused skills for deep reading, durable agent context, measurable
UI work, evaluation reporting, and cross-platform contract audits, while
hardening exact-release installation and contributor-credit workflows. The
published catalog contains 2,019 skills.

This release helps Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and
related AI coding assistants keep claims attached to evidence, preserve verified
project knowledge across sessions, evaluate agent outcomes without denominator
drift, and carry product contracts consistently from storage to clients.

Start here:

• Install: npx agentic-awesome-skills
• dsh-deepread for evidence-first document analysis.
• using-lwc for durable, source-grounded project memory.
• anti-ui-slop for product-specific UI contracts and a
  hard finish gate.
• Choose your tool
• Bundles

Added

• Added anti-ui-slop for grounding web and iOS work in
  real interface references, explicit product contracts, required interaction
  states, and a finish gate that rejects generic coding-agent defaults
  (#​1166).
• Added liuguang-banlan-ui for two parameterized
  iridescent UI modes with OKLCH authoring, deterministic WebGL and CSS fallback,
  reduced-motion handling, screenshot QA, and measurable color reports
  (#​1154).
• Added using-lwc for durable, source-grounded agent memory
  across Wiki document and CodeGraph planes, with explicit scope, installation,
  initialization, and write-consent boundaries
  (#​1152).
• Added dsh-deepread for evidence-first reading of
  articles, books, PDFs, web pages, and document sets through claim ledgers,
  argument analysis, knowledge maps, and Feynman checks
  (#​1174).
• Added agent-evaluation-reporting for
  keeping autonomous, assisted, failed, timed-out, and invalid evaluation
  outcomes distinct, with explicit denominators, uncertainty, and readiness
  gates (#​1177).
• Added
  cross-platform-contract-propagation-audit
  for read-only tracing of fields, enums, flags, and API contracts across
  storage, services, clients, analytics, rollout controls, and tests
  (#​1178).

Changed

• Updated the exact-release installer to accept npm 12's valid single-element
  JSON-array response for npm view --json, while rejecting empty or ambiguous
  multi-item results and preserving fail-closed gitHead verification
  (#​1167).
• Hardened zero-diff contributor-credit intake so an authoritative empty raw Git
  diff can proceed without weakening the rejection of missing or non-empty
  evidence
  (#​1171,
  #​1172,
  #​1173).
• Regenerated the canonical catalog, offline AAS Core data, web assets,
  marketplaces, editorial bundles, compatibility reports, and Codex/Claude
  plugin distributions for 2,019 skills.

Security

• Preserved exact npm package-to-Git identity checks across npm 12 output-shape
  changes; missing, empty, changed, or ambiguous registry identity remains a
  hard installer failure.
• Repaired the protected maintainer intake for liuguang-banlan-ui and
  using-lwc with explicit provenance, risk labels, consent gates, pinned LWC
  bootstrap identities, reduced-motion behavior, renderer fallback, and
  regression coverage
  (#​1169).
• Kept optional UIZZE preview inspection behind minimized-payload review and
  explicit network approval, and kept LWC installation, global initialization,
  and durable writes behind current user authorization.

Who should care

• Researchers, students, and analysts who need long-form reading outputs whose
  claims remain linked to inspectable source evidence.
• Coding teams that need verified project decisions and code relationships to
  survive across agent sessions without silently widening workspace authority.
• UI teams that want either a strict anti-generic finish gate or a measurable,
  accessible iridescent rendering workbench.
• Agent-evaluation owners and cross-platform product teams that need honest
  denominators, explicit readiness gates, and evidence for every contract edge.
• Maintainers and npm 12 users who depend on exact-release identity and
  contributor-credit workflows that fail closed on ambiguous evidence.

Validation

• Passed repository validation, reference validation, documentation-security
  checks, warning-budget enforcement, the complete 111-group repository test
  suite, plugin-compatibility and bundle checks, web-app install/build/prerender,
  and the npm package dry run on the protected release base.
• Reviewed all six added skills and their bundled files for semantics, safety,
  provenance, declared risk, limitations, consent boundaries, and relevant
  regression coverage.

Limitations

• dsh-deepread requires readable source material and cannot recover or invent
  content that the host agent could not retrieve.
• using-lwc documents LWC workflows but does not bundle an initialized Wiki,
  trusted project scope, or permission to install software or write memory.
• The UI skills do not guarantee visual quality automatically: external preview
  use needs approval, screenshot claims need actual image inspection, and WebGL
  environments still require the documented fallback and accessibility checks.
• Evaluation reports and contract audits expose evidence gaps; they do not make
  missing data comparable or implement the repairs they identify.

Credits

• @​samuelbushi and the official
  uizze/uizze source for
  anti-ui-slop in
  PR #​1166.
• @​3516027002att-ui for
  liuguang-banlan-ui in
  PR #​1154.
• @​JanYork and
  JanYork/using-lwc for
  using-lwc in
  PR #​1152.
• @​xiehuan123 and
  xiehuan123/dsh-deepread for
  dsh-deepread in
  PR #​1174.
• @​Whxuan0701 for
  agent-evaluation-reporting and
  cross-platform-contract-propagation-audit
  in PR #​1177
  and PR #​1178.
• @​rjvkn for the npm 12 installer identity fix
  in PR #​1167.

---

Configuration

📅 Schedule: (in timezone UTC)

• Branch creation
  • At any time (no schedule defined)
• Automerge
  • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR is behind base branch, or you tick the rebase/retry checkbox.

👻 Immortal: This PR will be recreated if closed unmerged. Get config help if that's undesired.

---

• If you want to rebase/retry this PR, check this box

---

This PR has been generated by Mend Renovate CLI.