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 ychampion/cskill-agents --skill plugin-only-agent-surface-gatinggit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/plugin-only-agent-surface-gating)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/plugin-only-agent-surface-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/plugin-only-agent-surface-gating/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/ychampion/cskill-agents/plugin-only-agent-surface-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/plugin-only-agent-surface-gating.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.00362 |
| Opus 5 | $0.00017 | $0.00181 |
| Sonnet 5 | $0.00007 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
plugin-only-agent-surface-gating 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 7d 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.
What it actually says
SKILL: Plugin-Only Agent Surface Gating
Domain: permission-gating Trigger: Apply this when an agent tries to extend its MCP surface while the session enforces plugin-only MCP access. Source Pattern: Distilled from reviewed agent trust-boundary and plugin-only surface-gating implementations.
Core Method
Before connecting any agent-specific MCP servers, check whether the session is locked to plugin-only extension mode. If it is, allow the extra MCP connections only for trusted agent definitions such as built-ins or approved plugins. Untrusted or user-controlled agent definitions should continue without creating new clients, while logging the gating decision clearly. This prevents policy bypasses without breaking trusted packaged agents.
Key Rules
- Check the plugin-only policy before any MCP initialization begins.
- Treat approved built-in or packaged agents as trusted, so their declared MCP integrations remain honored.
- Log a warning when skipping servers so telemetry captures the change in behavior.
- Always return the parent clients and an empty cleanup callback when gating is active to avoid downstream failures.
Example Application
When running in a highly regulated environment, reuse this heuristic before initializing agent MCP servers so only pre-approved agents can expand the MCP surface and user scripts cannot sneak new servers in.
Anti-Patterns (What NOT to do)
- Don’t let user-specified agents create external MCP connections while plugin-only mode is enabled; that defeats the security setting.
- Don’t apply the gate uniformly without checking admin trust; built-in agents still need their MCP servers even when plugin-only is true.
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.
- 7d ago First seen · 29 lines · 34 tokens per session scan A 537b8a599c4b
plugin-only-agent-surface-gating is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 362 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.