Skip to content
Back to skills

Workflow Skills

ASecurity

Onboard onto an unfamiliar repository or measure the blast radius of a planned change using the CodeLens index. Use for structure mapping, symbol/reference tracing, and "what breaks if I change X". Not for single-file reads or plain text/string audits — use native tools for those.

  • 3 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added October 11, 2026
ai-agents

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned October 11, 2026

npx -y skills add mupozg823/codelens-mcp-plugin --skill workflow-skills --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Workflow Skills?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Workflow Skills
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mupozg823-workflow-skills/badge)](https://www.skillsdirectory.com/skills/mupozg823-workflow-skills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
id: explore-impact
title: Explore and Impact
risk: read
implicit: true
description: >
  Onboard onto an unfamiliar repository or measure the blast radius of a planned
  change using the CodeLens index. Use for structure mapping, symbol/reference
  tracing, and "what breaks if I change X". Not for single-file reads or plain
  text/string audits — use native tools for those.
tools:
  - prepare_harness_session
  - overview
  - search
  - graph
  - get_ranked_context
  - find_symbol
---

# Explore & Impact

1. **Bind first.** `prepare_harness_session(project=<abs repo root>)` — verify
   `activated: true` and index health before any query; if the index is stale beyond
   the reported threshold, trigger refresh and say so.
2. **Map before drilling.** `overview` for the area of interest, then `search`
   (mode=symbol|refs) to locate anchors. Prefer one ranked query over many greps.
3. **Trace structure, not text.** `graph` (callers/callees/trace/impact) for
   relationships; `find_symbol`/`get_ranked_context` for bounded evidence packs.
   Batch symbol lookups in one array call where supported.
4. **Report with provenance.** Every claim carries file:line plus the index
   generation/freshness from the response envelope. If CodeLens fails, fall back to
   native tools and label the evidence as unindexed.

Files in this skill

  • explore-impact.skill.md1.3 KB
  • review.skill.md1.3 KB
  • safe-refactor.skill.md1.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.