AgentStack
SKILL verified MIT Self-run

Run Lint

skill-sgaunet-claude-plugins-run-lint · by sgaunet

Auto-detect project linter and run it. Internal utility skill used by feature-flow commands for the lint phase.

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

Install

$ agentstack add skill-sgaunet-claude-plugins-run-lint

✓ 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 Run Lint? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Run Lint Skill

Auto-detect the project's linter from build files and run it. Returns pass/fail status with output.

Detection Logic

Probe for build/config files using first match wins:

| Trigger | Command | Fallback | |---------|---------|----------| | Taskfile.yml (lint task) | task lint | -- | | Makefile (lint target) | make lint | -- | | go.mod | golangci-lint run ./... | go vet ./... | | package.json (lint script) | npm run lint | npx eslint . | | pyproject.toml / setup.py | ruff check . | python -m flake8 . | | Cargo.toml | cargo clippy -- -D warnings | -- | | None detected | Warn: "No linter detected" and skip | -- |

Execution

  1. Detect linter using the table above
  2. Run the detected command
  3. On success: report "Lint passed"
  4. On failure: display errors, attempt auto-fix if supported (--fix flag for the tool), re-run once
  5. Return final status (pass/fail) and output

Working Directory

If a working_directory context is provided (e.g., a worktree path), run all commands prefixed with cd &&. Otherwise, use the current directory.

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.