AgentStack
SKILL verified MIT Self-run

Noslop Setup

skill-45ck-skill-harness-noslop-setup · by 45ck

Install and configure noslop quality gates in an existing repository, including git hooks, CI workflows, and Claude Code guardrails.

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

Install

$ agentstack add skill-45ck-skill-harness-noslop-setup

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

About

Use this skill when setting up noslop in a repository for the first time or verifying an existing install.

Installation:

  • install noslop globally: npm install -g @45ck/noslop
  • go to the target repo root (must be an existing git repo)
  • run noslop init — detects language pack, copies templates, wires git hooks via git config core.hooksPath .githooks
  • run noslop doctor to confirm all enforcement layers are present

What gets installed:

  • .githooks/pre-commit — runs noslop check --tier=fast before every commit
  • .githooks/pre-push — runs noslop check --tier=slow before every push
  • .githooks/commit-msg — rejects CI-bypass patterns and enforces Conventional Commits
  • .github/workflows/quality.yml — required CI check on every PR and push to main
  • .github/workflows/guardrails.yml — blocks PRs touching protected files without noslop-approved label
  • .claude/settings.json — denies --no-verify, --force, and edits to protected paths
  • .claude/hooks/pre-tool-use.sh — intercepts every Claude Code tool call, blocks bypass patterns
  • AGENTS.md — plain-language rules for AI agents working in the repo

Configuring AGENTS.md rules:

The generated AGENTS.md must state:

  • run noslop check --tier=fast before every commit
  • run noslop check --tier=slow before opening a PR
  • never use git commit --no-verify
  • never use git push --force without explicit human approval
  • never use [skip ci], skip-checks, or SKIP_CI
  • do not weaken quality gates in .githooks/, .github/workflows/, or .claude/hooks/
  • additive changes to infrastructure files are allowed; removal or weakening is not

Two-tier check system:

  • --tier=fast — format, lint, spell check; must complete in seconds; runs on every commit
  • --tier=slow — type checking and full test suite; runs before every push and before opening a PR
  • --tier=ci — full pipeline; authoritative; cannot be skipped by any local trick

Verify setup:

noslop doctor

Expected healthy output confirms: hooks present and executable, core.hooksPath set, CI workflow files present, Claude settings and hook present.

For multi-pack repos, pass --pack repeatedly: noslop init --pack typescript --pack python.

Source & license

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

  • Author: 45ck
  • Source: 45ck/skill-harness
  • License: MIT
  • Homepage: https://github.com/45ck/skill-harness/releases/tag/v0.1.0

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.