Skip to main content
prompt CX Codex GP ChatGPT

stellar-nightshift — Claude Code prompt: fixes and installation

The stellar-nightshift prompt for Claude Code applies the remedy for each finding in a supplied cluster and leaves unrelated code alone. It targets files in the cluster’s crate directories.

Apache-2.0 ★ 423 updated 2026-11-16

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/stellar-nightshift.md
Open on GitHub

What stellar-nightshift does

The prompt tells the agent to preserve behavior and follow the “Code-shape rules” in AGENTS.md. Edits must stay inside the cluster’s crate directories; a script rejects and discards changes outside them.

It bars new dependencies and public API changes. Documentation or ADRs can change only when a finding calls for it, and unsafe fixes must be left untouched. The agent can read and edit files, but has no network, git, or token. It must not run cargo, including cargo check or tests: a cold dependency rebuild exceeded the step budget on 2026-10-18. The pipeline runs formatting, clippy, and fast-tier tests afterwards.

What it helps with

  • fix findings from a single cluster
  • confine edits to the cluster’s crate directories
  • preserve behavior and the public API
  • avoid running builds or tests during the fix step

Example prompts for the agent

  • Fix only the findings in this cluster and apply each remedy.
  • Keep edits inside the cluster’s crate directories and preserve current behavior.
  • Leave any finding unchanged if its fix cannot be made safely.

How to install stellar-nightshift

Manually: put the files in place

.claude/commands/stellar-nightshift.md

Questions about stellar-nightshift

How do I install stellar-nightshift in Claude Code?

Save the prompt file at .claude/commands/stellar-nightshift.md.

What does stellar-nightshift do?

It applies the specified remedy to each finding in a supplied cluster. It limits edits to that cluster’s crate directories and leaves unsafe fixes untouched.

Why does stellar-nightshift prohibit cargo?

A cold dependency rebuild exceeded the step budget on 2026-10-18. The pipeline runs formatting, clippy, and fast-tier tests after the edits.

Source text

stellar-nightshift.md · Apache-2.0
You are the stellar night-shift fixer (LABS-311, ADR-0292). Fix ONLY the
findings in the cluster below, applying each finding's remedy.

Rules:
- Edit only files inside the cluster's crate directories; a script rejects
  anything else and discards your work.
- Preserve behavior. Follow AGENTS.md "Code-shape rules".
- No new dependencies, no public-API changes, no docs/ADR edits unless a
  finding requires it. If a finding cannot be fixed safely, leave it alone.
- You have no network, git or token: just edit files. Do not commit.
- Keep it small. fmt, clippy and the fast-tier tests run afterwards; if they
  fail the branch is discarded. **Do not run cargo at all** — not the test
  suite, not `cargo check`: any build in this step's cold target rebuilds
  the dependency closure and overran the step budget on 2026-10-18. Edit
  files and read code to verify; the pipeline's fast tier is the only
  verifier, and a branch that fails it is discarded.

© relatedb · Apache-2.0 · relatedb/relate

Similar prompts

All prompts for Code review and refactoring →

From the same set18

The whole set →
opencode-review-rust The opencode-review-rust Claude Code prompt automates Rust pull request reviews. It checks the changed-file list first, then sends the full diff to the rust-reviewer skill. CX Codex +1 ★ 423repo stars opencode-review-security The opencode-review-security Claude Code prompt reviews Rust pull requests for security risks. Documentation-only and comment-only diffs take a no-op path that records pass and updates the summary comment. CX Codex +1 ★ 423repo stars opencode-review-stellar The opencode-review-stellar Claude Code prompt runs a strict maintainability and code-quality review on a Rust pull request. It gathers agent findings but leaves comments and the final verdict to a later pipeline step. CX Codex +1 ★ 423repo stars opencode-review-protocol The opencode-review-protocol Claude Code prompt defines a pull request review workflow. It posts line-specific findings, updates a summary comment, and writes a verdict for CI. CX Codex +1 ★ 423repo stars release-notes A prompt for Claude Code drafts relate release notes from the changelog and commit history. It runs for a tagged release. CX Codex +1 ★ 423repo stars security-review The security-review Claude Code skill reviews code changes for security risks and suggests remediations. It activates for auth or permission changes, secrets and PII handling, public endpoints, and dependency upgrades. CX Codex +1 ★ 423repo stars neo4j-query-workload-skill The neo4j-query-workload-skill Claude Code skill builds a graph-database query workload one requirement at a time. It runs new queries against the dataset and checks earlier results for regressions. CX Codex +1 ★ 423repo stars relate This Claude Code skill guides JVM projects through using Relate as a local graph database with Cypher. It activates when Java or Kotlin code needs to create, query, or embed the database. CX Codex +1 ★ 423repo stars

Project sponsors

Companies that keep this analytics open