Skip to content

Conversation

@szokeasaurusrex
Copy link
Member

Caution

This PR is a Proof of Concept and is NOT intended to be merged.
It demonstrates the feasibility of integrating Sentry's Seer AI code review into the agent skill workflow.

Summary

  • Add new seer-review skill that invokes sentry-cli review for AI-powered code review
  • Supports SENTRY_CLI_PATH env var override for testing with dev builds
  • Provides instructions for processing predictions and auto-fixing issues

Features

  • Invokes sentry-cli review to analyze HEAD vs HEAD~1 diff
  • Interprets human-readable output with severity levels (HIGH/MEDIUM/LOW)
  • Guides agent to apply suggested fixes and re-run review for verification

Testing

# Build sentry-cli from the PoC branch
cd /path/to/sentry-cli && cargo build

# Set the CLI path
export SENTRY_CLI_PATH=/path/to/sentry-cli/target/debug/sentry-cli

# Load the plugin for testing
claude --plugin-dir /path/to/skills/plugins/sentry-skills

Then invoke via /seer-review or ask Claude to "review my commit with sentry".

Related

🤖 Generated with Claude Code

szokeasaurusrex and others added 4 commits January 15, 2026 14:05
Add new seer-review skill that invokes `sentry-cli review` to get
AI-powered code review feedback on local changes before creating a PR.

Features:
- Invokes sentry-cli review to analyze HEAD vs HEAD~1
- Supports SENTRY_CLI_PATH env var override for testing
- Provides instructions for processing predictions and auto-fixing

Co-Authored-By: Claude <noreply@anthropic.com>
- Rename get-sentry-cli.sh to run-review.sh and execute review directly
- Add allowed-tools for full workflow support (Task, AskUserQuestion, etc.)
- Add skeptical evaluation workflow for Seer comments:
  - Spawn Plan sub-agents to evaluate each comment against user context
  - Present results to user with AskUserQuestion
  - Plan and implement fixes for accepted issues
  - Re-run review in a loop until done
- Update error handling (auth token URL, CLI upgrade instructions)
- Emphasize that Seer's confidence/severity ratings should not be
  blindly trusted when agent context suggests otherwise

Co-Authored-By: Claude <noreply@anthropic.com>
- Add SUMMARY field to Plan sub-agent output format for concise issue descriptions
- Update Step 4 with two-phase presentation:
  1. Print raw Seer output with reference numbers (emphasizing it's uninterpreted)
  2. Use AskUserQuestion with sub-agent summaries citing issue numbers
- Summaries must be standalone so users can decide without reading full output

Co-Authored-By: Claude <noreply@anthropic.com>
Make the SUMMARY output format instructions more explicit about
distinguishing Seer's concern from the agent's assessment.

Co-Authored-By: Claude <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

2 participants