Skip to content

ci: review PRs with Claude Code + superpowers plugin - #3

Merged
ahrzb merged 4 commits into
masterfrom
add-claude-pr-review
Jul 22, 2026
Merged

ci: review PRs with Claude Code + superpowers plugin#3
ahrzb merged 4 commits into
masterfrom
add-claude-pr-review

Conversation

@ahrzb

@ahrzb ahrzb commented Jul 20, 2026

Copy link
Copy Markdown
Owner

What

Adds .github/workflows/claude-review.yml — a GitHub Actions workflow that runs an automated Claude Code review on every pull request (opened, synchronize, reopened).

How it works

  • Loads the superpowers plugin marketplace and drives the review through the superpowers:requesting-code-review skill, so reviews follow a consistent, defined procedure rather than an ad-hoc prompt.
  • fetch-depth: 0 on checkout so the skill can diff against the merge-base with the PR's base branch, not just the tip.
  • concurrency group keyed on the PR number with cancel-in-progress: true — a new push supersedes the in-flight review instead of stacking duplicate runs.
  • permissions: contents: read + pull-requests: write (needs write to post the review).
  • Prompt constrains output to verified findings only — no speculative issues, no style nits, and an explicit "say so in one line" when nothing needs changing.

Reviewer notes

🤖 Generated with Claude Code

ahrzb and others added 4 commits July 20, 2026 19:59
Runs anthropics/claude-code-action on pull_request, installing the
superpowers plugin via the action's plugin_marketplaces/plugins inputs.
Requires a CLAUDE_CODE_OAUTH_TOKEN repo secret.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…-in)

- m-1 priorities set: High spine (TASK-5/6/13), Medium (TASK-2/3/15/16), Low (TASK-14/17)
- decision-7 accepted + renamed: native is the default engine, codegen is opt-in;
  TASK-29/34 declassified from blocked-on-open to decided-Low
- Closed: TASK-27/30 (CASE both engines), TASK-28 (re-scoped to match-DataFusion
  folding + retitled), TASK-31, TASK-32, TASK-7 (suite now 0 xfailed)
- New: TASK-31 (CASE-branch transformer test), TASK-32 (pydantic-v3 probe),
  TASK-33 (stale .pyd rebuild guard), TASK-34 (codegen transformer support)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Benchmarks the serving-path options -- ONNX vs the native Rust interpreter vs
Python codegen vs WASM. Authored in the benchmarking/QA session (Fermi);
committed here at AmirHossein's request.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
claude-code-action needs id-token:write to fetch its OIDC token — without it
the run failed 'Could not fetch an OIDC token'. Also bump actions/checkout
v4->v5 (Node 20 deprecation).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@ahrzb
ahrzb merged commit 594ecfa into master Jul 22, 2026
2 of 3 checks passed
@ahrzb
ahrzb deleted the add-claude-pr-review branch July 23, 2026 16:33
claude-agent-ahrzb Bot pushed a commit that referenced this pull request Jul 26, 2026
… via wave-1 builtins (TASK-47 AC #3)

Titanic 24->31, Ames 42->54, IEEE-CIS fraud 41->57, Rossmann 44->56
output features, all parity-gated (specializer == DuckDB == handcrafted
on 300 seeded rows, cranelift asserted). The compromises the original
scenario designs recorded are now real features: ln(1+x) skew
transforms everywhere, decade buckets via round(x,-1) and floor,
Deotte cents, IN-set membership flags (rare titles, suspicious
domains, PUD classes, holiday codes), starts_with/ends_with/instr
domain parsing, sin/cos cyclical hour/day/month encodings with pi(),
least/greatest clamps and NULL-ignoring join-miss handling. Three
store_sales compromise expressions rewrote to their natural builtin
forms with identical values.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
claude-agent-ahrzb Bot pushed a commit that referenced this pull request Jul 26, 2026
… via wave-1 builtins (TASK-47 AC #3)

Titanic 24->31, Ames 42->54, IEEE-CIS fraud 41->57, Rossmann 44->56
output features, all parity-gated (specializer == DuckDB == handcrafted
on 300 seeded rows, cranelift asserted). The compromises the original
scenario designs recorded are now real features: ln(1+x) skew
transforms everywhere, decade buckets via round(x,-1) and floor,
Deotte cents, IN-set membership flags (rare titles, suspicious
domains, PUD classes, holiday codes), starts_with/ends_with/instr
domain parsing, sin/cos cyclical hour/day/month encodings with pi(),
least/greatest clamps and NULL-ignoring join-miss handling. Three
store_sales compromise expressions rewrote to their natural builtin
forms with identical values.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant