Index of every page on this site: llms.txt
All skills
shubhamsaboo avatar

/scope-creep-detector

@14c5f8f
Run it yourself

Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too broad, or what unrelated stuff they touched, and wants keep, split, or justify guidance. Operates locally and offline.

Use this Skill: https://skilld.dev/gh/shubhamsaboo/awesome-llm-apps/scope-creep-detector

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

README.md

≈308 tokens on demand. Your agent reads this file only when SKILL.md points to it.

🔭 Scope Creep Detector

Checks a working, staged, saved, or branch diff against a one-line intent. It flags unrelated paths, new dependencies, public API renames, config or CI edits, oversized hunks, formatting-only files, and subsystem spread. The output is a local JSON report for keep, split, or justify decisions.

Scope Creep Detector demo

The demo analyzes a "fix null deref in parser" change that also touched CI config, added a dependency, and dropped in an unrelated file. The parser fix is kept; the rest is flagged.

Install

npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/scope-creep-detector

Run

Ask the agent:

Did my change grow beyond the parser fix I intended?

Or run the deterministic core directly:

python3 scripts/scope_creep.py --repo /path/to/repo \
  --intent "fix null dereference in parser" --json

Use --staged for the index, --base main for a branch diff, or --diff - for unified diff input on stdin. The script uses only the Python standard library, makes no network calls, and does not modify the repository.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning6d3 checks · Risk SAFE
  • Gen Agent Trust Hub6d

    The skill analyzes git diffs to detect unrelated changes. It executes local git commands via Python's subprocess module and processes external diff data. The primary risks are local command execution and the potential for indirect prompt injection via malicious diff content.

  • Socket4mo

    No alerts

  • Snyk6d

    Risk: MEDIUM · 1 issue

Signed by skilld at 14c5f8f. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 4 months ago
Other metadata
metadata
{
  "author": "Matt Van Horn",
  "version": "1.0.0",
  "source": "https://github.com/Shubhamsaboo/awesome-llm-apps"
}

README badge

README badge for shubhamsaboo/awesome-llm-apps/scope-creep-detector