agentleFS
r3bl-orgr3bl-org/r3bl-open-core/.agents/skills/batch-refactor-with-sub-agents/SKILL.md

batch-refactor-with-sub-agents

Skill486 starsChanged 15 days agoApache-2.0View on GitHub

Use a sub-agent (like `generalist`) to perform repetitive code transformations across multiple files in a single turn.

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 1 is distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write a custom, disposable Rust script.

    line 15
  2. Very specific:

    Use std::fs to read files, apply string replacements (replace()), and write back (only if not a dry-run).

    line 17
  3. Very specific:

    Run cargo check to verify.

    line 19
  4. Very specific:

    Locate targets: Use grep_search to find all absolute file paths and line numbers that need modification.

    line 23
  5. Very specific:

    Draft a precise prompt: Call the generalist (or similar) tool with Model: "inherit" and a prompt that includes:

    line 24
  6. Very specific:

    fix: Read the modified files and use targeted replace calls to fix the syntax errors.

    line 39
  7. Very specific:

    Run ./check.fish --check (or cargo check -q --message-format=short --all-targets) to confirm zero compilation errors.

    line 42
  8. Very specific:

    Run ./check.fish --clippy (or cargo clippy -q --message-format=short --all-targets) to find and fix any unused_import or style warnings …

    line 43
  9. Distinctive:

    Run relevant integration tests for the modified files.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

When to Use Sub-Agents

  • Renaming symbols or updating function signatures across many files (but not the entire repository).
  • Migrating code from one pattern to another (e.g., manual error handling to a common helper).
  • Replacing literals with centralized constants across the codebase.
  • Performing repetitive tasks that require semantic understanding and cannot be solved with a simple string replace.

When to Use Custom Rust Scripts (Priority for Massive Refactors)

For massive, repository-wide bulk refactoring (typically 6+ files, e.g., renaming a string or trait across 100+ files), you MUST NOT use sed, awk, perl, python, bash, or fish (which are strictly prohibited). Furthermore, spawning sub-agents for a simple find-and-replace across 6+ files is inefficient. Instead:

  1. Write a custom, disposable Rust script. Save this script in tmpfs (e.g., /tmp/).
  2. Implement a --dry-run CLI argument to test the script before making destructive changes.
  3. Use std::fs to read files, apply string replacements (replace()), and write back (only if not a dry-run).
  4. Compile it natively with rustc and execute it.
  5. Run cargo check to verify.

Procedure for Sub-Agents

  1. Define the transformation: Identify the exact "before" and "after" patterns. Create a representative code snippet for the sub-agent to follow.
  2. Locate targets: Use grep_search to find all absolute file paths and line numbers that need modification.
  3. Draft a precise prompt: Call the generalist (or similar) tool with Model: "inherit" and a prompt that includes:
    • Goal: Clear statement of the refactoring objective.
    • Scope: A bulleted list of absolute file paths to modify.
    • Example: A code block showing the old_string vs new_string transformation.
    • Constraints: Instructions to preserve specific logic (e.g., "preserve original closure logic while changing the call site").
    • Verification: Instructions to run ./check.fish --check (or cargo check -q --message-format=short --all-targets) or specific tests after finishing.
  4. Delegate: Execute the sub-agent call using invoke_subagent with Model: "inherit".
  5. Review and Cleanup: Sub-agents may introduce minor issues like unused_import warnings. Perform a final sweep with ./check.fish --clippy (or cargo clippy -q --message-format=short --all-targets) and fix manually or via a second batch call.

Pitfalls and Fixes

  • symptom: Sub-agent misses some files or applies incorrect logic.
  • likely cause: Prompt was too vague or the transformation was too complex for a single turn.
  • fix: Break the task into smaller, more homogeneous batches (e.g., "refactor all files in directory A first").
  • symptom: cargo check fails after the sub-agent finishes.
  • likely cause: Sub-agent clobbered a symbol or messed up indentation/syntax.
  • fix: Read the modified files and use targeted replace calls to fix the syntax errors.

Verification

  • Run ./check.fish --check (or cargo check -q --message-format=short --all-targets) to confirm zero compilation errors.
  • Run ./check.fish --clippy (or cargo clippy -q --message-format=short --all-targets) to find and fix any unused_import or style warnings introduced by the refactor.
  • Run relevant integration tests for the modified files.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.