Is the Configure skill free?

Yes. The skill itself is free from SponsioLabs/Sponsio. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Configure SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Configure?

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 Configure 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.

Configure

Wires up the sponsio-claude-code plugin so tool calls get contract-guarded and blocked

by SponsioLabs · SponsioLabs/Sponsio

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 4dc3409

Installed the real sponsio CLI (pip, v0.1.1) in a temp venv and ran the skill's flow under a throwaway $HOME. Following Step 1 (`sponsio plugin init`) wrote ~/.sponsio/plugins/_host/sponsio.yaml and passed its allow+block smoke test; Step 5 (`echo '{"hook_event_name":"PreToolUse","tool_name":"Bash","tool_input":{"command":"rm -rf /"}}' | sponsio plugin guard --stdin`) returned a real deny JSON: permissionDecision "deny", reason "Bash.command must not match forbidden patterns". BASELINE (same guard call but WITHOUT the Step 1 bootstrap) returned empty stdout — the `rm -rf /` passes through unguarded — proving the skill's setup step is load-bearing, exactly as its intro warns. Referenced files verified live (starter_pack.py:_per_tool_rules at line 199, plugin.json all HTTP 200); no security smells (it is itself a guardrail tool, and §4.5 explicitly refuses to ghostwrite YAML to resist injection). One doc drift: the skill still tells you to run `sponsio plugin init`, but the CLI now prints a deprecation notice steering to `sponsio host install` (docs 4/5). Did not exercise the scan/LLM-extraction and tuning halves (Steps 3-4) end to end.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Configure does

Guides the setup of the sponsio-claude-code plugin so its contract libraries actually gate tool calls in a Claude Code session: bootstraps the ~/.sponsio/plugins tree, installs or scans starter rule libraries for MCP servers, tunes thresholds to the environment, and runs a deny-path smoke test. Triggers on phrases like "configure sponsio-claude-code", "set up sponsio", "add Sponsio guardrails for my MCP tools", "the plugin is too strict/too loose", or "what should sponsio block". Requires the separate sponsio CLI (pip install sponsio) to do anything.

How to install Configure

git clone --depth 1 https://github.com/SponsioLabs/Sponsio.git /tmp/configure-src
mkdir -p ~/.claude/skills
cp -R /tmp/configure-src/plugins/sponsio-claude-code/skills/configure ~/.claude/skills/configure
# REQUIRES the sponsio CLI (the skill is inert without it):
#   pip install sponsio          # PyPI v0.1.1, Homepage points back to this repo
# The skill drives sponsio's plugin runtime: `sponsio plugin init` bootstraps
# ~/.sponsio/plugins/_host/sponsio.yaml, `sponsio plugin guard --stdin` is the hook.
# Full enforcement also needs the sponsio-claude-code PLUGIN installed in Claude Code
# (/plugin install) so the PreToolUse hook is wired; the skill only configures it.

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

Commands — how to trigger Configure

/configure Wires up the sponsio-claude-code plugin so tool calls get contract-guarded and blocked

It also activates on plain-language prompts like these:

Configure Sponsio for my current environment
Set up starter contract libraries for my MCP servers
Finish wiring the Sponsio runtime after install

Frequently asked questions

Is the Configure skill free?: Yes. The skill itself is free from SponsioLabs/Sponsio. SkillProof publishes the install command and an independent test verdict at no cost.
Does Configure work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Installed the real sponsio CLI (pip, v0.1.1) in a temp venv and ran the skill's flow under a throwaway $HOME. Following Step 1 (`sponsio plugin init`) wrote ~/.sponsio/plugins/_host/sponsio.yaml and passed its allow+block smoke test; Step 5 (`echo '{"hook_event_name":"PreToolUse","tool_name":"Bash","tool_input":{"command":"rm -rf /"}}' | sponsio plugin guard --stdin`) returned a real deny JSON: permissionDecision "deny", reason "Bash.command must not match forbidden patterns". BASELINE (same guard call but WITHOUT the Step 1 bootstrap) returned empty stdout — the `rm -rf /` passes through unguarded — proving the skill's setup step is load-bearing, exactly as its intro warns. Referenced files verified live (starter_pack.py:_per_tool_rules at line 199, plugin.json all HTTP 200); no security smells (it is itself a guardrail tool, and §4.5 explicitly refuses to ghostwrite YAML to resist injection). One doc drift: the skill still tells you to run `sponsio plugin init`, but the CLI now prints a deprecation notice steering to `sponsio host install` (docs 4/5). Did not exercise the scan/LLM-extraction and tuning halves (Steps 3-4) end to end.
What is the Configure SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Configure?: 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 Configure 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.