AgentStack
SKILL verified MIT Self-run

Code Reader

skill-corrame-skill-refinement-code-reader · by Corrame

>

No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-corrame-skill-refinement-code-reader

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Code Reader? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Code Reader Skill

Use this when the work is source understanding, not source modification.

Method

  1. Restate the exact question and allowed scope.
  2. Search before reading.
  3. Read narrow slices; expand only when needed.
  4. Separate fact from inference.
  5. Return file paths, line anchors, and uncertainty.

Avoid

  • Bulk-reading without a routed question.
  • Treating old docs as source truth.
  • Making final architecture decisions.

Output

Question:
Scope searched:
Findings:
Evidence:
Uncertainty:
Suggested next check:

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.