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 type-tiered-bridge-command-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/type-tiered-bridge-command-gating)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/type-tiered-bridge-command-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/type-tiered-bridge-command-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/type-tiered-bridge-command-gating"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/type-tiered-bridge-command-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 | $0.00045 | $0.00548 |
| Opus 5 | $0.00023 | $0.00274 |
| Sonnet 5 | $0.00009 | $0.00110 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
type-tiered-bridge-command-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 8d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Type Tiered Bridge Command Gating
Domain: command-architecture Trigger: Use when a remote or bridged client can invoke slash commands and you need a simple safety rule that separates text-expanding commands from local UI commands and plain local actions. Source Pattern: Distilled from reviewed remote-control, bridge transport, and capability-advertising implementations.
Core Method
Classify bridge safety by command type before inspecting individual command names. Treat local-jsx commands as unsafe by construction because they render local UI, treat prompt commands as safe by construction because they only expand into model text, and apply a narrow explicit allowlist only to plain local commands. This creates a three-tier gate where only one class needs per-command review, so remote/mobile surfaces stay predictable and new command types inherit the right default behavior.
Key Rules
- Put the type check first so the bridge gate does not need ad hoc per-command exceptions for UI-rendering commands.
- Block every
local-jsxcommand by default; if a command depends on local Ink or terminal state, it should fail the bridge gate without consulting any allowlist. - Allow
promptcommands by type, since their output is text passed back into the model flow rather than a local side effect. - Require explicit allowlist membership for plain
localcommands, making denial the default for any local command that has not been reviewed for remote execution. - Keep the allowlist static and easy to audit so adding a new remotely safe local command is an intentional registry change, not an incidental side effect of command loading.
Example Application
When a mobile client submits summary, model, and research, run the bridge gate on the resolved command objects. model is rejected immediately because it is local-jsx, research is admitted because it is prompt, and summary only passes if it appears in the reviewed local allowlist.
Anti-Patterns (What NOT to do)
- Do not maintain one flat allowlist for every command type; that obscures why prompt commands are safe and makes UI commands easier to admit accidentally.
- Do not treat plain
localcommands as safe by default just because they stream text; bridge safety requires explicit review. - Do not special-case individual
local-jsxcommands after the fact; the value of the pattern is that the type already encodes the unsafe class.
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.
- 8d ago First seen · 30 lines · 45 tokens per session scan A 3b88b63bd279
type-tiered-bridge-command-gating is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 548 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.
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
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.