nightly-scan

nightly-scan is a command for Claude Code from liortesta/ClawdAgent. It costs 0 tokens per session (494 once invoked), scanned A, original, Apache-2.0.

An automated project health report for a software codebase. It checks dependencies, code, types, tests, security, and performance.

In plain words
What is it for?
Use it for a regular scan of dependency health, code complexity, type coverage, test coverage, security risks, bundle size, and unusually large files.
Why use it?
It brings common maintenance and quality checks into one report, making issues such as unused code, vulnerable packages, secrets, flaky tests, or slow builds easier to spot.

Command for Claude Code

Written for Claude Code: context: fork in frontmatter.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/liortesta/clawdagent/nightly-scan
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for nightly-scan

README.md
[![agentmods](https://agentmods.dev/badge/commands/liortesta/clawdagent/nightly-scan.svg)](https://agentmods.dev/commands/liortesta/clawdagent/nightly-scan)
Your own site
<a href="https://agentmods.dev/commands/liortesta/clawdagent/nightly-scan"><img src="https://agentmods.dev/badge/commands/liortesta/clawdagent/nightly-scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 494 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00494
Opus 5 $0.00000 $0.00247
Sonnet 5 $0.00000 $0.00099
Haiku 4.5 $0.00000 $0.00049

Measured 6d ago against content hash 950623710785, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

nightly-scan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/nightly-scan.md · 75 lines

What it actually says

Nightly Quality Scan

Run a comprehensive project health check and generate a quality report.

Scan Categories:

1. Dependencies

  • Invoke the dependency-guardian agent to run a full dependency health check
  • The agent will: run security audit, check freshness, find unused deps, check licenses
  • Include the dependency-guardian's report in the Dependencies section of the quality report

2. Code Quality

  • Dead code detection (unused exports, unreachable code)
  • Unused imports
  • Code complexity metrics (cyclomatic complexity)
  • File size violations (>300 lines)

3. Type Safety

  • Type coverage percentage
  • Count of any types
  • Missing return types on exported functions

4. Test Health

  • Test coverage percentage (if coverage tool configured)
  • Flaky test detection (tests that sometimes fail)
  • Slow tests (>5 seconds)
  • Missing test files for source files

5. Security

  • SAST scan on all source files
  • Secrets detection (API keys, passwords, tokens)
  • Dependency vulnerabilities

6. Performance

  • Bundle size analysis (if applicable)
  • Performance regression check (if benchmarks exist)
  • Large file detection (>1MB in repo)

Output Format:

Generate a report as markdown:

## Quality Report — [DATE]

### Overall Health: [A/B/C/D/F]

| Category | Score | Status | Key Finding |
|----------|-------|--------|-------------|
| Dependencies | X/10 | OK/WARN/FAIL | ... |
| Code Quality | X/10 | OK/WARN/FAIL | ... |
| Type Safety | X/10 | OK/WARN/FAIL | ... |
| Tests | X/10 | OK/WARN/FAIL | ... |
| Security | X/10 | OK/WARN/FAIL | ... |
| Performance | X/10 | OK/WARN/FAIL | ... |

### Action Items (ordered by priority)
1. [CRITICAL] ...
2. [HIGH] ...
3. [MEDIUM] ...

### Trends (vs previous scan)
- [improved/degraded/stable] ...

Rules:

  • Save report to docs/quality-reports/[YYYY-MM-DD].md
  • Compare with previous report if it exists
  • Flag any category that dropped below 7/10

$ARGUMENTS

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 75 lines · 0 tokens per session scan A 950623710785

Subscribe to this mod's changes

nightly-scan is a command published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 494 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.