All skills
mblode avatar

/dx-audit

@b690e67
by Matthew Blodemblode/agent-skills134 stars
12

Audits libraries, CLIs, and SDKs using 38 rules for public contracts, package exports, piped output, errors, and configuration. Use when asked to "audit my CLI", "review my SDK", or diagnose package type resolution. For public site or docs agent scores use agent-ready; for agentic product trust use ax-audit; for docs prose use ghostwriter.

Use this Skill: https://skilld.dev/gh/mblode/agent-skills/dx-audit

This session only. Nothing lands on disk.

rulescli-delta-polling.md

≈335 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Expose Compact State Snapshots for Polling

A script or agent watching a long-running operation calls status on a timer. When the only status output is the full object with logs, every tick costs as much as the first and the caller has to diff prose to learn whether anything moved. Give status a compact structured snapshot with a stable fingerprint (stateHash, etag, or updatedAt), and where the operation supports it a wait that returns only on change or timeout. Full detail stays behind --verbose or a logs command.

Incorrect (every poll returns the whole object; change is invisible without a diff):

$ mytool job status 42
# 400 lines: full config, every log line so far, timestamps, identical to the previous tick

Correct (compact snapshot with a fingerprint; wait blocks until the fingerprint changes):

$ mytool job status 42 --json
{"id":"42","state":"running","stateHash":"9f3a","blocker":null}
$ mytool job wait 42 --since 9f3a --timeout 300 --json
{"id":"42","state":"blocked","stateHash":"b71c","blocker":"approval"}

Source: SKILL.md on GitHub

No alerts9d3 checks · Risk SAFE
  • Gen Agent Trust Hub9d

    The dx-audit skill is a developer experience auditing tool designed to review public APIs, CLIs, and SDKs. It demonstrates a strong security posture by including explicit instructions to validate inputs against path traversal and shell injection, and by warning the agent to inspect potentially malicious lifecycle scripts in audited repositories before running packaging probes. All external tools mentioned are industry-standard utilities.

  • Socket9d

    No alerts

  • Snyk9d

    Risk: LOW · No issues

Signed by skilld at b690e67. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated last week

README badge

README badge for mblode/agent-skills/dx-audit