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.
npx skills add SponsioLabs/Sponsio --skill configuregit clone --depth 1 https://github.com/SponsioLabs/SponsioWrote 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.
[](https://agentmods.dev/skills/sponsiolabs/sponsio/configure)<a href="https://agentmods.dev/skills/sponsiolabs/sponsio/configure"><img src="https://agentmods.dev/badge/skills/sponsiolabs/sponsio/configure/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sponsiolabs/sponsio/configure"><img src="https://agentmods.dev/badge/skills/sponsiolabs/sponsio/configure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 11 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 90 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Privilege Escalation · line 120 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Rogue Agent · line 404 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Tool Misuse · line 470 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 470 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Agent Snooping · line 547 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- medium Rogue Agent · line 45 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 55 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 376 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 543 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 549 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00263 | $0.05744 |
| Opus 5 | $0.00131 | $0.02872 |
| Sonnet 5 | $0.00053 | $0.01149 |
| Haiku 4.5 | $0.00026 | $0.00574 |
Grade A, and why
configure 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sponsio-claude-code — configure the host shield
You are walking the user through configuring the sponsio-claude-code plugin so it actually wraps tool calls in this Claude Code session. Without these steps, the plugin loads but every per-plugin library is empty and every tool call passes through unguarded.
The flow has two halves: setup (steps 1–2, 4–6) covers the common case where the user runs popular MCP servers we ship starters for; scan (step 3) covers plugins / MCP servers without a bundled starter and lives inline because most sessions touch both halves.
Prerequisites (check silently first)
Run:
sponsio --version
- Not found → tell the user to install:
pip install sponsio(orpip install -e ".[all]"from a local clone). Stop here until they confirm. - Present → continue.
If the user owns the agent code and wants to wire Sponsio into their
own framework integration (LangGraph, OpenAI Agents, Claude Agent
SDK, …) instead of running it as a Claude Code host plugin,
delegate to the sponsio skill (sponsio onboard .). This skill is
only for the host-plugin case where the user is gating tool calls
inside their Claude Code session.
Routing rules from a policy document
Sponsio has two layers, and rules must land in the right YAML or they do nothing. When the user hands you a policy document / instruction file / "list of things the agent must not do" and asks you to encode it, classify each rule before writing anywhere.
| Signal | → Layer 1 (this skill — write to ~/.sponsio/plugins/<id>/sponsio.yaml) |
→ Layer 2 (delegate to sponsio skill — writes <project>/sponsio.yaml) |
|---|---|---|
| Tool names mentioned | Bash, Edit, Write, Read, mcp__* |
tool names from the user's project's tool inventory |
| Path form | absolute or ~/... paths outside the user's project |
paths relative to the project (src/...) |
| Subject of the rule | "Cursor must not…", "Claude Code must not…" | "the loan agent must…", "the chatbot should…" |
| Domain language | shell, git, file system, MCP server primitives | AML, KYC, refund, PII, approval, faithfulness, hallucination |
./sponsio.yaml exists in cwd |
weaker signal — Layer 2 is in play, but rule may still be Layer 1 | stronger signal — most rules belong here |
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.
- 11d ago First seen · 558 lines · 263 tokens per session scan E c038457a4ea6
configure is a skill published in the GitHub repository SponsioLabs/Sponsio (440 stars, last pushed 3d ago), licensed Apache-2.0. It adds 263 tokens to every session and 5,744 once invoked, about $0.0013 per session on Opus 5. 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.
Other skills, from other repositories
evaluating-bitrouter-routes
Use when evaluating BitRouter route decisions or Eval Exchange subjects with task-native verifiers, human reviewers, private enterprise evaluators, agentic judges, or genuinely uncategorized evaluator sources.
run-bitrouter-benchmark
Use when a user wants to run, compare, resume, audit, share, or submit a Harbor benchmark through BitRouter, including choosing a Harbor dataset and agent, confirming routed providers and models, or optionally operating BitRouter OSS on AWS.
bitrouter
Use when installing, configuring, running, or troubleshooting BitRouter from its CLI — a self-hosted LLM proxy on 127.0.0.1:4356 routing OpenAI- or Anthropic-shaped traffic to any provider, via a coding-agent subscription, hosted BitRouter, or your own keys. Covers bro init, provider credentials, starting the default…
agent-fables-preflight
Retrieve revision-pinned software-agent failure evidence and unresolved verification gates without authorizing execution. Use before destructive, irreversible, privileged, broad-scope, production, infrastructure, database, filesystem, permission, MCP configuration, or supply-chain operations; when reviewing a…
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).