Skip to content
Critique/docs
Reference

Chat Tools

What Critique Chat can look up, inspect, and do on your behalf — with confirmation for writes.

Critique Chat calls tools automatically based on your question. You do not pick tools manually; knowing what exists helps you ask better questions.

Write tools (start Remedy, create issue, post PR comment) always show a confirmation card before anything changes in GitHub or sandboxes.

Repository & GitHub

ToolUse when you want to…
searchRepositoryFind files, symbols, or patterns in the connected repo
inspectPullRequestSee PR metadata, files, checks, and comment summaries
inspectWorkflowRunDebug a CI run or job with log excerpts
commentOnPullRequestDraft a PR comment (confirmed before post)
createGitHubIssueDraft an issue from chat context (confirmed before post)

Repository tools require a selected repo and GitHub App access.

Review & Remedy

ToolUse when you want to…
listRecentReviewRunsSee recent Critique reviews
inspectReviewRunDeep-dive one run’s findings and Remedy state
inspectRemedyRuntimeUnderstand how Remedy executes in your environment
startRemedyQueue Remedy for a run (confirmation required)
checkRemedyStatusPoll an in-flight or finished Remedy run

Workspace & memory

ToolUse when you want to…
getWorkspaceStatusCheck GitHub connection, installs, automation readiness
getActiveContextRead current workspace / run context bundle
searchSharedMemoryRecall promoted learnings and board notes

Memory search respects repository and run scope. See Memory & context.

Slack (Connections)

ToolUse when you want to…
postToSlackDraft a channel message and confirm before posting to your connected workspace

Requires Slack under Settings → Connections (bot token or incoming webhook). Write tool — always shows a confirmation card.

Linear & roadmap (Connections)

ToolUse when you want to…
searchIssuesAndRoadmapSearch Linear issues, assignees, and roadmap context tied to your question

Requires an active Linear connection with chat enabled under Settings → Connections. If Linear is not connected, the tool is omitted from the agent registry.

External documentation

ToolUse when you want to…
searchLibraryDocsVersion-aware library docs (when Context7 is enabled)
searchDocsWeb/doc search via Firecrawl (when enabled)
fetchDocPagePull one doc page as markdown after a search hit

Unavailable integrations return a clear error in chat — use repository search for code-local answers.

Agent handoff

ToolUse when you want to…
prepareClaudeCodeHandoffExport the thread as Markdown for Claude Code (Anthropic key saved locally in this browserSettings)

Server-side BYOA vs chat handoff

Critique uses two different key models for external agents:

IntegrationWhere the key livesHow you trigger it
Cursor Cloud AgentEncrypted server-side — Settings → CursorQueue Cursor agent on a completed review run
Claude Managed AgentEncrypted server-side — Settings → AnthropicQueue Claude agent on a completed review run
OpenAI CodexEncrypted server-side — Settings → OpenAIQueue Codex run on a completed review run
Claude Code (chat)Browser local storage onlyprepareClaudeCodeHandoff in Critique Chat

Server-side keys never return to the browser after save; they are used only when you queue a run. The chat handoff tool is for thread-scoped work — use review-run queueing for PR-scoped fixes.

For Copilot or agents without a queue integration, use Fix prompt on a review run. See BYOA. For OpenRouter-backed review, see BYOK. For MCP or REST access from an external agent, see Connections & Platform API.

Side effects

KindTools
Read-onlySearch, inspect, status, memory, docs
Write (confirmed)startRemedy, createGitHubIssue, commentOnPullRequest

Promotion of review or Remedy outcomes into long-term memory uses internal tools invoked only after explicit operator intent — not from casual chat UI buttons.

Tips

  • Name the PR number or review run when asking about a specific review.
  • Ask for workspace status first if setup questions fail mysteriously.
  • Prefer searchRepository before asking for file contents from memory — memory may be stale; code search is fresh.