chore(deps): update all dependencies

[gw0-bot]

This PR contains the following updates:

Package	Change	Age	Confidence	Type	Update
@anthropic-ai/claude-code	2.1.245 → 2.1.247				patch
github/codeql-action (changelog)	db488dd → cdf488f			action	digest
rtk-ai/rtk	0.45.0 → 0.46.0				minor
sickn33/agentic-awesome-skills	16.0.0 → 16.2.0				minor

---

Release Notes

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

v2.1.247

Compare Source

• Added the SendFeedback tool: when something goes wrong in a session, Claude can draft a feedback report for you to review and send from /feedback (turn off with the feedbackDrafts setting)
• Added {id, text, cooldownSessions, priority} entries, tipsFile, and label to spinnerTipsOverride, so organizations can rotate their own tips alongside the built-in ones
• Added a tip on Bash permission prompts pointing to auto mode, with a one-keystroke "Yes, and switch to auto mode" option
• Added /claude-api cost-optimize to profile an existing project's Claude API spend and work through cost levers (caching, token hygiene, batch, effort, model choice) one measured change at a time
• Updated the /claude-api skill with Admin API coverage (organization members, invites, workspaces, API keys, rate limit reports, workload identity federation, CMEK)
• Fixed fast arrow-key + Enter sequences acting on the row above the one you navigated to in history search, /config, /mcp, /skills, background tasks, and /model
• Fixed sub-agents dying on a first-call model 404: they now use the session's fallback model chain, and the error returned to the parent includes the error type, status, request id, and model
• Fixed a hook or background agent that printed megabytes of error output being able to overflow the conversation and wedge the session on "Prompt is too long"
• Fixed Ctrl keyboard shortcuts not firing under non-Latin (e.g. Cyrillic) keyboard layouts in kitty-protocol terminals
• Fixed text like <35;150;7M being inserted into the prompt when a mouse report arrived split across reads right after the escape prefix
• Fixed the Bash sandbox's after-command cleanup deleting a dotfile-managed ~/.claude/settings.json symlink (nix/home-manager, stow) when it is repointed outside the sandbox's writable area
• Fixed /terminal-setup overwriting your entire Zed keymap.json instead of merging in its keybinding
• Fixed /rename silently confirming when the session registry could not be updated; it now says other sessions may still show the old name
• Fixed /compact and "Summarize from here" in sessions started with --agent summarizing under the default system prompt instead of the conversation's own
• Fixed a background session showing "opening…" forever in claude agents after its terminal host process died; the row now fails within seconds with the reason, and Enter restarts it
• Fixed unbounded memory growth when a hook's or background task's output file could not be written; the file now notes where output was lost
• Fixed /install-github-app over SSH: the copy shortcut now says how the sign-in URL was copied instead of always claiming success, and the URL appears immediately when no browser can open
• Fixed shell commands carried over from the foreground logging an internal error or showing a misleading [exited with code -1] line when they finish in background sessions
• Fixed a version-less marketplace plugin's live cache directory being deleted and recreated on a second-scope install, which could disrupt a running session using it
• Fixed Remote Control sessions started with /remote-control not reporting the working-tree diff to connected clients
• Fixed self-hosted runner sessions reporting running before Claude Code had started, which could trigger a premature "Claude is waiting for your input" notification from the Claude desktop app
• Fixed first-run setup exiting with "Unable to connect to Anthropic services" when managed settings configure Claude apps gateway sign-in and Anthropic endpoints are unreachable
• Fixed cloud sessions (Claude Code on the web, desktop and mobile apps) sometimes showing the previous permission mode when you switch modes right after sending a message
• Fixed cloud sessions going silent when the session's container restarts between turns while a background agent, shell, or monitor is still running — the resumed session now reports the lost work
• Improved plugin marketplace hardening: names containing control or invisible characters are rejected, and marketplace-supplied text in /plugin and claude plugin output is escape-safe
• Improved Bedrock, Vertex, and Foundry sessions (and any with telemetry disabled): Claude is now told when a configured MCP server failed to connect, instead of concluding its tools don't exist
• Changed Sonnet 5's default auto-compact window to its full 1M context, so sessions on the 1M window now auto-compact at about 967K tokens instead of about 934K
• Changed cross-session peer messages to collapse by default to a one-line Message from @<sender>: <first line> preview; Ctrl+O expands the full body
• Changed terminal hyperlinks in rendered markdown: link targets that point at a network or automounter path, contain a control character, or lead with an invisible character now render as plain text
• Changed the prompt-footer PR badge to skip its GitHub re-check on terminal refocus when the last check is under a minute old
• Changed analytics to stay off from startup, not only after login, when managed settings force gateway login or a custom OAuth deployment is configured
• Changed Claude apps gateway sign-in requests to identify Claude Code (a surface=claude_code device-authorization parameter and a claude-code/<version> User-Agent)
• Changed organization sign-in enforcement to exit at start when the administrator's managed settings cannot be read, even if host-supplied or per-user Windows registry settings exist

v2.1.246

Compare Source

• Added a startup warning for Bash allow rules with a wildcard before the subcommand (e.g. Bash(git * main)), since they also match options inserted before the subcommand
• Added an Auto mode tab to /permissions for viewing and editing auto mode classifier rules
• Added the turn's completion time to the end-of-turn duration line, e.g. ✻ Sautéed for 23s · done 6:05 PM
• Fixed fullscreen mode showing a blank transcript after resizing the terminal and jumping to the bottom until the next keypress
• Fixed a severe transcript slowdown when a diff contained a very long single line (e.g. a base64 string); such lines now render truncated with a marker
• Fixed erratic fullscreen scrolling when positioned at an earlier message, including jump-to-bottom getting stuck mid-transcript
• Fixed background sessions failing to open after 45 seconds when Claude Code's starting directory had been deleted, the machine had slept, or the host is slow to start processes
• Fixed background sessions failing to open with "Couldn't start the background service … EACCES" when another Claude Code process was re-installing the npm package at that moment
• Fixed markdown rendering being disabled for a whole message when its first 500 characters contained no markdown, and for +/N) lists and setext headings
• Fixed MCP tool calls interrupted by an incoming message in headless/remote sessions being reported to the model as "completed with no output" instead of an explicit interrupted error
• Fixed MCP tool arguments being sent as JSON strings when the parameter's schema is empty ({}), instead of their real type
• Fixed a command interrupted mid-run showing as "Ran 1 shell command" with no sign it was cut
• Fixed pressing ← or running /background during a dynamic workflow restarting its finished subagents; it now asks first and says how many subagents would restart
• Fixed opening a just-started session in claude agents while its worker was still booting (common on Windows) stopping it with "was stopped while the respawn was in flight"
• Fixed claude agents listing a backgrounded named session twice; backgrounding the same conversation again now numbers the new row (e.g. my-session (2))
• Fixed the background retention sweep removing git worktrees under .claude/worktrees/ that you created yourself when an old background-session record pointed at them
• Fixed auto mode tool calls being denied as "temporarily unavailable" on very large sessions by scaling the safety-check deadline with prompt size
• Fixed the plugin cache creating duplicate SHA-named directories for the same plugin
• Fixed plugin skills whose frontmatter name already includes the <plugin>: prefix showing it doubled in the slash menu (e.g. /plugin:plugin:skill)
• Fixed claude plugin update failing for an installed plugin given its bare name (only the fully-qualified name worked)
• Fixed plugin installation failing when plugin.json was saved with a UTF-8 byte-order mark (BOM)
• Fixed /reload-plugins reporting 0 skills for plugins that define skills under skills/*/SKILL.md
• Fixed hook error messages showing a literal ${CLAUDE_PLUGIN_ROOT} instead of the resolved plugin path
• Fixed /rename replacing the theme's prompt border color (including a custom theme's promptBorder) with the default cyan; the border now keeps your theme's color unless you pick one with /color
• Fixed custom theme diff colors (diffAdded/diffRemoved and their dimmed variants) being ignored in diffs and the /theme preview
• Fixed a keybindings.json binding with an unknown action name silently deadening that key; it is now skipped so the default binding keeps working, and a warning is logged under --debug
• Fixed /stats activity heatmap showing each day's activity one cell off (Sunday's count under Monday) in timezones east of UTC
• Fixed /fork from an already-forked or backgrounded session starting the new session with an empty conversation
• Fixed prompts beginning with /-- (e.g. Lean doc comments) being rejected as an unknown slash command instead of being sent to Claude
• Fixed the @ file picker staying open after the typed text stopped matching a real path
• Fixed the status line's cost and duration resetting to zero after navigating to the agents view and back
• Fixed fullscreen mode moving keyboard focus onto the control under the pointer when you clicked the terminal window only to bring it back into focus
• Fixed path completion failing when the completion token or working directory contained a null byte
• Windows/macOS: Fixed headless sessions not cleaning up stale entries in ~/.claude/sessions left by sessions that exited uncleanly
• Fixed the UI stopping with a render error on the first tool call when a third-party Anthropic-compatible endpoint (ANTHROPIC_BASE_URL) streams a tool_use block without an id
• Fixed the Write tool reporting "Out of memory" or freezing for a long time after overwriting a very large existing file, even though the file had been written
• Fixed claude plugin install <name> exiting silently (or hanging in a terminal) instead of reporting an error when ~/.claude/plugins/known_marketplaces.json is empty or corrupted
• Fixed resumed sessions failing every turn with a 400 when the saved history contains tool blocks the Anthropic API does not accept (typically written by a third-party API proxy)
• Fixed curl -fsSL https://claude.ai/install.sh | bash failing with "Raw mode is not supported" for some Team/Enterprise users with server-managed settings
• Fixed sessions that ended in plan mode resuming outside plan mode in the VS Code extension, and in claude -p --continue/--resume with a permission prompt tool, when no permission mode was set
• Fixed the Notification hook not firing while the sandbox "Network request outside of sandbox" permission prompt is waiting
• Fixed Bash permission checks to always require approval for malformed commands with a dangling && or || operator
• Fixed --strict-mcp-config sessions prompting to approve .mcp.json servers they would never load, which left background sessions waiting at startup
• Fixed telemetry and metrics requests to Anthropic carrying the API key configured for a third-party gateway (ANTHROPIC_BASE_URL); a credential is now only sent to its own host
• Fixed a visible API error on the first prompt after idle when apiKeyHelper returns short-lived JWTs: an expired cached token is now refreshed before sending, and 401/403 auth errors retry quietly
• Fixed memory growing with session length in the fullscreen and Ctrl+O transcript views: each rendered message row no longer retains a full copy of the transcript-wide tool lookups
• Fixed /ultrareview runs and cloud sessions launched at the same time from one repository (e.g. from several worktrees) sometimes starting with another launch's uncommitted changes
• Fixed the task progress count (e.g. 3/5) shown for background cloud sessions such as /autofix-pr occasionally missing a task
• Fixed Remote Control sessions keeping their placeholder name in claude.ai and the Claude app until the second prompt; the auto-generated title now appears after the first prompt
• Fixed MCP tools marked requiresUserInteraction still offering "Yes, and don't ask again" in their permission prompt; the option wrote an allow rule the tool then ignored
• Fixed the self-hosted runner ending its live sessions or exiting when a work-poll response is malformed (e.g. an intercepting proxy's HTML page); it now retries the poll
• Improved /cd: the new directory's project settings, hooks, .mcp.json servers (behind the usual approval prompt), skills, and agents now take effect right after the move instead of on --resume
• Improved Bash tool latency on bash shells by replaying snapshot functions without a base64 subshell per function
• Improved subagent results: a subagent that stops at its maxTurns limit now returns its output marked as partial, with a hint to continue it via SendMessage, instead of appearing finished
• Improved non-interactive sessions (-p, SDK, cloud sessions) to automatically continue a response cut off mid-stream by a server error, connection loss, or stall instead of ending with an error
• Improved attribution of usage telemetry to your organization for workload identity federation sessions, events sent while apiKeyHelper runs at startup, and after a login token expired while idle
• Changed /code-review so Claude can also start it on its own on Bedrock, Vertex AI, and Foundry, through the Claude apps gateway, and when telemetry or non-essential traffic is disabled
• /goal: Changed idle sessions to start at most three check-ins on long-running background work per goal; your next message allows three more
• Changed claude install and claude update to defer a pending managed-settings consent prompt to the next interactive session instead of prompting mid-command
• Changed OpenTelemetry plugin events for plugins synced from claude.ai: plugin_id_hash now reflects the plugin's real marketplace, and enabled_via is admin-install for admin-installed plugins
• Fixed the command sandbox's filesystem configuration not respecting --setting-sources

rtk-ai/rtk (rtk-ai/rtk)

v0.46.0

Compare Source

Features

• find: dispatch on find's grammar; compress find output for unmodeled predicates (#​3603)
• find: tee tail hint when rtk imposes the result cap (#​3603)

Bug Fixes

• find: never-worse guard, recovery hint, and dispatch on find's grammar (#​3603)
• git: don't misdetect a value-taking option's argument as a patch flag (#​3575)
• cicd: stop benchmark.sh deleting the tracked scripts/benchmark harness (#​3595)
• tee: hash long recovery-file slugs to prevent collisions and shorten hints (#​3266)
• benchmark: avoid negative curl/cargo cases that fail the benchmark job (#​3430)
• test: accept both Ask and Allow verdicts in rewrite tests (#​3147) — Closes #​3146
• core: decode process output using Windows console code page (#​2717) — Closes #​2452
• git: preserve patch output from log commands (#​2951) — Closes #​2944
• discover: sanitize drive-letter colon so Windows discover finds sessions (#​2952) — Closes #​2919
• stream: decode lossily instead of dropping lines on invalid UTF-8 (#​2997) — Closes #​2994

Other

• test(find): use the platform temp dir instead of /tmp (#​3717)

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

v16.2.0

Compare Source

[16.2.0] - 2026-08-26 - "Security Operations Expansion and Safer Integrations"

Added a reviewed 43-skill security and reverse-engineering collection,
introduced API rate-limit, media-generation, and repository-instruction
workflows, corrected install guidance, and refreshed dependency safety. The
published catalog contains 2,074 skills.

This release expands defensive security, authorized assessment, reverse
engineering, incident-response, and threat-intelligence coverage while keeping
high-impact operations behind explicit scope, authorization, evidence, and
environment-safety gates.

Added

• Added 43 security skills adapted from the MIT-licensed
  zhaoxuya520/reverse-skill
  collection, spanning reverse engineering, malware analysis, forensics,
  threat hunting, API and identity security, firmware, wireless, cloud,
  supply-chain, and authorized assessment workflows
  (#​1247).
• Added instructree for generating and validating
  scoped repository instruction trees without walking outside the selected
  project root
  (#​1251).
• Added muapi-media for authenticated MuAPI image,
  video, and music generation with explicit cost, credential, and output
  handling
  (#​1257).
• Added api-rate-limit-handler for
  retry-aware API clients with bounded backoff, jitter, idempotency guidance,
  and billable-request safeguards
  (#​1258).

Changed

• Updated express-rate-limit from 8.6.1 to 8.6.2 in the generated Loki Mode
  example dependency set
  (#​1256).
• Regenerated the canonical catalog, offline AAS Core data, tracked web assets,
  marketplaces, editorial bundles, compatibility reports, and Codex/Claude
  plugin distributions for 2,074 skills.

Fixed

• Corrected tree-ring-memory installation
  guidance to target the reviewed v0.15.0 release and aligned its declared
  risk with its install and update mutations
  (#​1253).
• Sanitized embedded NUL bytes from imported Markdown in the security pack so
  the complete canonical skill subtrees remain text-safe and reviewable.
• Kept API retry guidance bounded and prevented automatic retries from silently
  multiplying non-idempotent or billable operations.

Security

• Excluded upstream runtime bootstrap scripts and the GPLv3 sidecar from the
  imported security collection; only reviewed Markdown skill content and
  references are distributed.
• Preserved explicit authorization, target-scope, lab-isolation, evidence, and
  stop-condition gates across offensive and dual-use security workflows.
• Classified credentialed media generation and repository-mutating install
  guidance as critical risk, with secrets supplied through environment or
  secure input rather than command-line arguments.

v16.1.0

Compare Source

[16.1.0] - 2026-08-25 - "Specification-First Delivery and Mistake-Proofing"

Added specification-first delivery and software mistake-proofing workflows,
aligned durable project-state lifecycle semantics, refreshed Lore's complete
operating surface, and hardened the protected skill-review path. The
published catalog contains 2,028 skills.

This release helps Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and
related AI coding assistants freeze requirements before implementation, design
controls that prevent predictable mistakes, preserve consistent project-state
transitions, and query durable repository knowledge without weakening approval,
provenance, or path-safety boundaries.

Start here:

• Install: npx agentic-awesome-skills
• spec-driven-loop for a specification-first
  workflow with frozen artifacts, non-overlapping agent ownership, and an
  independent delivery judgment.
• poka-yoke for replacing reminders with controls,
  warnings, and bounded detection that make software mistakes impossible or
  immediately visible.
• Choose your tool
• Bundles

Added

• Added spec-driven-loop with PRD, technical
  design, acceptance-criteria, ownership, and completion artifacts; explicit
  approval before implementation; bounded rework; and independent lead-agent
  judgment backed by diffs, tests, and evidence
  (#​1242).
• Added poka-yoke for identifying software error traps
  and selecting the strongest practical device on a control, warning,
  detection, or instruction ladder
  (#​1240).

Changed

• Aligned project-state-governor
  workstream completion with COMPLETED and retained CANCELLED in the
  canonical milestone lifecycle vocabulary
  (#​1241).
• Synchronized lore to its reviewed upstream layout, moved
  workflow guidance into the supported reference tree, refreshed its scripts
  and compatibility documentation, and preserved the repository's stricter
  mirror-target containment rules
  (#​1244).
• Upgraded the catalog web app from @supabase/supabase-js 2.111.0 to 2.112.0,
  including upstream authentication, PostgREST, storage, retry, and opt-in
  tracing fixes (#​1244).
• Bounded the external semantic skill-review attempt to ten minutes and routed
  timeouts to the truthful manual-review-required path instead of allowing an
  indefinitely running review job
  (#​1244).
• Regenerated the canonical catalog, offline AAS Core data, tracked web assets,
  marketplaces, editorial bundles, compatibility reports, and Codex/Claude
  plugin distributions for 2,028 skills.

Fixed

• Fixed Lore full-history queries so the absence of a since value no longer
  injects Git's epoch cutoff and silently omits existing commits.
• Kept multi-entry successor-history results bound to each entry's own code
  path and time boundary while retaining fail-closed path validation.

Security

• Kept spec-driven-loop implementation behind explicit specification
  approval, separated agent ownership, and evidence-based completion instead
  of treating generated artifacts or self-reported status as proof.
• Kept poka-yoke read-only and analysis-first: consequential code or process
  changes still require proposal, authorization, and validation, and detection
  is not presented as equivalent to a preventive control.
• Preserved Lore's canonical path-containment hardening, rejected unsafe mirror
  targets, and pinned license provenance to the reviewed upstream commit.
• Made a timed-out or unavailable external semantic review fail into an exact
  head maintainer-review requirement; it is never reported as an automated
  semantic pass.

Who should care

• Teams coordinating multi-agent implementation that need requirements,
  ownership, acceptance evidence, and final judgment to stay independently
  inspectable.
• Maintainers and reviewers who want software error traps converted into
  concrete preventive or self-announcing controls.
• Long-running projects using durable state or Lore histories across sessions,
  repositories, mirrors, and successor entries.
• Catalog web-app users relying on current Supabase authentication, storage,
  PostgREST, retry, and tracing behavior.

Validation

• Passed repository and reference validation, documentation-security checks,
  warning-budget enforcement, the complete 113-group repository test suite,
  web-app tests and production build, npm package dry-run, plugin compatibility,
  bundle checks, and protected canonical synchronization.
• Reviewed the complete tracked trees for both added skills and the full Lore
  refresh for semantics, safety, provenance, declared risk, limitations,
  references, scripts, and exact-head evidence before protected merge.
• Added regression coverage for bounded skill-review execution and retained
  upstream Lore test coverage for history, containment, and mirror behavior.

Limitations

• spec-driven-loop structures planning and evidence; it does not prove domain
  correctness, replace stakeholder approval, or authorize implementation
  outside the approved scope.
• poka-yoke helps select stronger controls, but compatibility and system
  constraints may leave only warning or detection fallbacks; those weaker
  rungs must remain explicit.
• Lore can only query repository and entry history that still exists locally;
  it cannot reconstruct missing commits or validate external systems by itself.
• Supabase remains an independently evolving upstream dependency, so its live
  documentation and service behavior remain authoritative.

Credits

• @​Linji-x and the MIT-licensed
  spec-driven-loop source for
  spec-driven-loop in
  PR #​1242.
• @​rainmanjam for
  poka-yoke in
  PR #​1240.
• @​Ghost011118 for the project-state
  lifecycle correction in
  PR #​1241.
• @​TheaDust for the reviewed Lore upstream
  synchronization proposed in
  PR #​1237 and
  integrated through
  PR #​1244.
• Snyk for the Supabase dependency update proposed in
  PR #​1239 and
  integrated through
  PR #​1244.

---

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.