https://aitoolchain.io/tools/claudoscope New releases and features in Claudoscope, tracked by The AI Toolchain. en Wed, 26 Aug 2026 14:21:05 GMT https://github.com/cordwainersmith/Claudoscope/releases/tag/v1.1.0 https://github.com/cordwainersmith/Claudoscope/releases/tag/v1.1.0 Wed, 26 Aug 2026 14:21:05 GMT Claudoscope v1.1.0 adds Insights, Hooks Runtime, Tasks & Jobs, Context, and six new config checks to its observability rails. • Adds six new configuration checks (`CFG013` through `CFG018`) covering filesystem isolation, sandbox network allowlist, credential `mode: "mask"` without TLS, sandbox binary overrides, `remoteControlAtStartup` in project settings, and cross-session messages auto-accepted under bypassed permissions. • Adds new `CHN` check family (`CHN001` through `CHN003`) in the Plugins category of Config Health: `CHN001` flags each enabled channel plugin (Telegram, Discord, iMessage, fakechat) as a prompt-injection and permission-relay surface; `CHN002` notes channel plugins enabled under Vertex or Bedrock where they are silently ignored; `CHN003` surfaces the `channelsEnabled` org-policy key. • Adds new `SKL014` check flagging a skill restricted only to `TodoWrite` or `Task*` tools, which Claude Code 2.1.233 removed from Opus 4.8, Sonnet 5, Fable 5, Mythos 5, and newer models unless `CLAUDE_CODE_ENABLE_TODO_TOOLS=1` is set. • Adds Insights tab inside the Analytics rail (Usage/Insights toggle): reads session facets from `~/.claude/usage-data/` written by Claude Code's `/insights` command and joins outcome, friction, satisfaction, goal, and session-type data to the cost engine, including outcome distribution, friction frequency, average cost by outcome, and per-session facet detail. • Adds Hooks Runtime tab inside the Hooks rail (Configuration/Runtime toggle): surfaces per-hook fire counts, failures, average and max duration, session counts, and a 'not in config' badge for commands seen in transcripts that match no current hook, with Stop-hook batches marked inline in the chat view. • Adds Tasks & Jobs rail surfacing Claude Code's background jobs from `~/.claude/jobs/` (state, timeline, tokens, result) and per-session task lists from `~/.claude/tasks/` (checklist with dependency chips), with jump-to-session links and a daemon status line; job `providerEnv` maps are never decoded. • Adds Context tab with a per-session chart of context-window utilization per assistant turn against the model's ceiling, compaction events, peak context, peak utilization, and a flag for sessions that mix model generations across the Claude 4.7 tokenizer change. • Adds nine additional GitLab token families to secret detection beyond `glpat-`: runner, OAuth, pipeline-trigger, agent, import, service-account, CI-build, feature-flag, and deploy tokens, with the `glpat-`/`gldt-` pair classified as a critical account-level credential. • Protects the `glab` credential store in the hardening sandbox baseline, matching the existing `gh` entry. • Merges Health, Hardening, and Routing into a single Health rail with a section toggle, reducing icon-rail clutter. • Adds session provenance display: sessions started with `--worktree` or `/fork` show their worktree and branch; sessions that opened a pull request or GitLab merge request link to it from the session header; Claude Code's `ai-title` generated session names are now used as titles. • Recognizes `DirectoryAdded` as a hook event (Claude Code 2.1.219), so matchers targeting it are correctly evaluated rather than flagged as dead config. • Reads `additionalMarketplaces` as an alias for `extraKnownMarketplaces` (Claude Code 2.1.232), and displays source URLs or commands for `archive` and `command` plugin sources (2.1.224/2.1.229). Breaking changes: • Hooks Runtime requires a one-time full reparse of all transcripts on first launch due to a parser version bump.