agentleFS
AsiaOstrichAsiaOstrich/EngramGraph/.agents/skills/sweep/SKILL.md

sweep

Skill4 starsChanged 29 days agoMITView on GitHub

Scan codebase for debug artifacts and code quality issues; optionally auto-fix safe patterns. Use when: before committing, during PR review, or periodic codebase cleanup. Not for: structural code improvement — use /refactor; security-specific scanning — use /scan. Keywords: sweep, debug cleanup, console.log, debugger, TODO, ts-any, code quality.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use diagnose, triage and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    diagnose

    Use to systematically diagnose why scenarios fail — identifies root causes by analyzing agent traces, codebase, and behavioral patterns

    Also in 4 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 4 projects that use this

  • GoogleSkill

    codebase-design

    Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    Use Glob tool to find all source files under the target path.

    line 48
  2. Very specific:

    Default excludes: node_modules/, dist/, .git/, *.min.js, coverage/.

    line 49
  3. Very specific:

    If --fix flag is set AND total fixable findings exceed 20:

    line 69
  4. Distinctive:

    Pause and require explicit user confirmation: before applying fixes. Show the list of files that will be modified.

    line 70
  5. Distinctive:

    Use Edit tool to apply changes file by file.

    line 78
  6. Very specific:

    Write findings to .uds/sweep-report.json:

    line 82
  7. Very specific:

    After /sweep completes, suggest:

    line 120

“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “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

Sweep Assistant | 掃碼助手

Language: English | 繁體中文

Scan the codebase for debug artifacts, code quality issues, and technical debt markers. Optionally auto-fix safe patterns (console.log, debugger statements).


Scan Patterns | 掃描模式

Pattern IDLabelAuto-fixableDescription
console-logconsole.log / console.debug / console.trace✅ YesDebug output left in production code
debuggerdebugger statement✅ YesDebugger breakpoints left in code
todo-fixmeTODO / FIXME / HACK / XXX❌ Report onlyTechnical debt markers
ts-anyTypeScript any type❌ Report onlyType safety violations

Usage | 使用方式

/sweep                        # Scan current directory, report findings
/sweep --fix                  # Scan and auto-fix fixable patterns
/sweep --report               # Scan and save report to .uds/sweep-report.json
/sweep --path src/            # Scan specific directory
/sweep --exclude "**/*.test.ts"  # Exclude patterns (glob)

Workflow | 執行工作流程

Step 1: Discover Files

Use Glob tool to find all source files under the target path. Default excludes: node_modules/, dist/, .git/, *.min.js, coverage/.

Step 2: Scan Each Pattern

For each pattern, use Grep to find matches across all files. Collect findings: { file, line, column, pattern_id, label, fixable, content }.

Step 3: Report Findings

Output a structured summary:

📊 Sweep Results
─────────────────────────────────────
console-log:   12 findings  (auto-fixable)
debugger:       2 findings  (auto-fixable)
todo-fixme:    28 findings  (report only)
ts-any:         5 findings  (report only)
─────────────────────────────────────
Total: 47 findings  |  Fixable: 14

Step 4: HITL Gate (if --fix and findings > 20)

If --fix flag is set AND total fixable findings exceed 20: Pause and require explicit user confirmation before applying fixes. Show the list of files that will be modified.

Step 5: Apply Fixes (if --fix confirmed)

For each fixable finding:

  • console-log: Remove the line if it contains only the console statement
  • debugger: Remove the line if it contains only the debugger statement

Use Edit tool to apply changes file by file. Report: "Fixed N findings in M files."

Step 6: Save Report (if --report)

Write findings to .uds/sweep-report.json:

{
  "timestamp": "<ISO8601>",
  "total_findings": 47,
  "fixable": 14,
  "fixed": 14,
  "findings_by_pattern": { "console-log": 12, "debugger": 2, "todo-fixme": 28, "ts-any": 5 },
  "files_modified": ["src/auth.ts", "src/utils.ts"]
}

Configuration | 設定

Configure via uds.project.yaml:

sweep:
  default_path: "src/"
  exclude_patterns:
    - "**/*.test.ts"
    - "**/*.spec.ts"
    - "**/fixtures/**"
  hitl_threshold: 20       # Require confirmation if fixable findings exceed this
  patterns:
    enabled:
      - console-log
      - debugger
      - todo-fixme
      - ts-any

Next Steps Guidance | 下一步引導

After /sweep completes, suggest:

  • Run /checkin to verify overall code quality before committing
  • Run /code-review to review the cleaned-up changes
  • Run /commit to commit the fixes

Related Standards | 相關標準

  • Checkin Standards — Pre-commit quality gates
  • Code Review — Code review assistant
  • Testing Guide — Testing standards

Version History | 版本歷程

VersionDateChanges
1.0.02026-04-28Initial release — XSPEC-097 Phase 1 (從上游遷移)

License | 授權

This skill is released under MIT License and CC BY 4.0.

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.