Is the Agent Interaction Audit skill free?

Yes. The skill itself is free from JasonxzWen/harness-hub. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agent Interaction Audit SkillProof Score?

8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Agent Interaction Audit?

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 Agent Interaction Audit 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.

Agent Interaction Audit

Turns Codex/Claude Code session traces into a private, evidence-tiered retrospective with an actionable improvement queue.

by JasonxzWen · JasonxzWen/harness-hub

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · e3da52e

Applied its Report Contract to this very benchmarking session: it forced a BLUF plus evidence-tiered insight/bottleneck/recommendation structure instead of a flat timeline, and correctly self-labeled the single-session sample 'under-evidenced' rather than inflating a verdict — matching the skill's own built-in bad-vs-good example almost exactly.

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 8/10
Docs & honesty 4/5

What Agent Interaction Audit does

Collects local Codex and Claude Code trace, automation-log, and prompt/rule evidence for a repository, then builds a private Markdown audit plus a machine-readable improvement-queue JSON covering collaboration bottlenecks, stale rules, and repeated agent mistakes. Triggers on requests for agent-interaction retrospectives, collaboration-friction audits, or trace-based workflow-improvement queues.

How to install Agent Interaction Audit

git clone https://github.com/JasonxzWen/harness-hub
cd harness-hub
mkdir -p ~/.claude/skills
cp -r skills/agent-interaction-audit ~/.claude/skills/agent-interaction-audit

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agent Interaction Audit

/agent-interaction-audit Turns Codex/Claude Code session traces into a private, evidence-tiered retrospective with an actionable improvement queue.

It also activates on plain-language prompts like these:

Audit my Claude Code sessions this month for collaboration issues
Give me a retrospective on how my agent interactions went
Analyze my Codex and Claude Code traces and build an improvement queue

Frequently asked questions

Is the Agent Interaction Audit skill free?: Yes. The skill itself is free from JasonxzWen/harness-hub. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agent Interaction Audit work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Applied its Report Contract to this very benchmarking session: it forced a BLUF plus evidence-tiered insight/bottleneck/recommendation structure instead of a flat timeline, and correctly self-labeled the single-session sample 'under-evidenced' rather than inflating a verdict — matching the skill's own built-in bad-vs-good example almost exactly.
What is the Agent Interaction Audit SkillProof Score?: 8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Agent Interaction Audit?: 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 Agent Interaction Audit 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.